diff --git a/.gitignore b/.gitignore index ca3500a6f..63c113b9b 100644 --- a/.gitignore +++ b/.gitignore @@ -178,8 +178,11 @@ artifacts # Temporary typespec folders for typespec generation TempTypeSpecFiles/ -# Base specification files -specification/base/ +# Azure specification files +specification/base/entrypoints/azure.v1 +specification/base/entrypoints/sdk.dotnet.azure +specification/base/typespec.azure +specification/base/typespec.azure.v1 # Generator default TypeSpec output codegen/tsp-output/ diff --git a/scripts/Invoke-CodeGen.ps1 b/scripts/Invoke-CodeGen.ps1 index d6250575d..166961817 100644 --- a/scripts/Invoke-CodeGen.ps1 +++ b/scripts/Invoke-CodeGen.ps1 @@ -1,4 +1,4 @@ -[CmdletBinding(DefaultParameterSetName = 'GitHub')] +[CmdletBinding(DefaultParameterSetName = 'Default')] param( [Parameter(Mandatory = $true, ParameterSetName = 'GitHub')] [string]$GitHubOwner, @@ -214,42 +214,54 @@ $codegenFolderPath = Join-Path $repoRootPath "codegen" $scriptStartTime = Get-Date -$shouldDownload = $true -if (Test-Path $baseSpecificationFolderPath) { - Write-Host "Base specification already exists at: $baseSpecificationFolderPath" +if ($PSCmdlet.ParameterSetName -eq 'Default') { + if (-not (Test-Path $baseSpecificationFolderPath)) { + Write-Error "Base specification path does not exist: $baseSpecificationFolderPath" + throw "Default specification path not found" + } + + Write-Host "Using existing base specification at: $baseSpecificationFolderPath" Write-Host "" +} +else { + $shouldDownload = $true - if ($Force) { - Write-Host "Overwriting existing base specification..." + if (Test-Path $baseSpecificationFolderPath) { + Write-Host "Base specification already exists at: $baseSpecificationFolderPath" Write-Host "" - Remove-Item -Path $baseSpecificationFolderPath -Recurse -Force - } - else { - $shouldDownload = $false + + if ($Force) { + Write-Host "Overwriting existing base specification..." + Write-Host "" + Remove-Item -Path $baseSpecificationFolderPath -Recurse -Force + } + else { + $shouldDownload = $false + } } -} -if ($shouldDownload) { - Write-Host "Retrieving base specification..." - Write-Host "" + if ($shouldDownload) { + Write-Host "Retrieving base specification..." + Write-Host "" - if ($PSCmdlet.ParameterSetName -eq 'GitHub') { - $success = Get-GitHubRepoContent -GitHubOwner $GitHubOwner ` - -GitHubRepository $GitHubRepository ` - -CommitHash $CommitHash ` - -GitHubToken $GitHubToken ` - -SubdirectoryPath "openai-in-typespec" ` - -Destination $baseSpecificationFolderPath - } - elseif ($PSCmdlet.ParameterSetName -eq 'Local') { - $success = Get-LocalRepoContent -LocalRepositoryPath $LocalRepositoryPath ` - -SubdirectoryPath "openai-in-typespec" ` - -Destination $baseSpecificationFolderPath - } + if ($PSCmdlet.ParameterSetName -eq 'GitHub') { + $success = Get-GitHubRepoContent -GitHubOwner $GitHubOwner ` + -GitHubRepository $GitHubRepository ` + -CommitHash $CommitHash ` + -GitHubToken $GitHubToken ` + -SubdirectoryPath "openai-in-typespec" ` + -Destination $baseSpecificationFolderPath + } + elseif ($PSCmdlet.ParameterSetName -eq 'Local') { + $success = Get-LocalRepoContent -LocalRepositoryPath $LocalRepositoryPath ` + -SubdirectoryPath "openai-in-typespec" ` + -Destination $baseSpecificationFolderPath + } - if (-not $success) { - Write-Error "Failed to get repository contents." - throw "Repository content retrieval failed." + if (-not $success) { + Write-Error "Failed to get repository contents." + throw "Repository content retrieval failed." + } } } diff --git a/specification/base/.gitattributes b/specification/base/.gitattributes new file mode 100644 index 000000000..6313b56c5 --- /dev/null +++ b/specification/base/.gitattributes @@ -0,0 +1 @@ +* text=auto eol=lf diff --git a/specification/base/.gitignore b/specification/base/.gitignore new file mode 100644 index 000000000..917f36c94 --- /dev/null +++ b/specification/base/.gitignore @@ -0,0 +1 @@ +codegen_blackhole/ diff --git a/specification/base/entrypoints/sdk.dotnet/main.tsp b/specification/base/entrypoints/sdk.dotnet/main.tsp new file mode 100644 index 000000000..43e676138 --- /dev/null +++ b/specification/base/entrypoints/sdk.dotnet/main.tsp @@ -0,0 +1,5 @@ +// Import order matters. Somehow, importing the server decorated namespace afterwards, +// will cause the the `description` field to be missing in the generated OpenAPI spec. +import "./specialized-types.tsp"; +import "../../typespec/servers/rest.tsp"; +import "../../typespec"; diff --git a/specification/base/entrypoints/sdk.dotnet/specialized-types.tsp b/specification/base/entrypoints/sdk.dotnet/specialized-types.tsp new file mode 100644 index 000000000..b14dac250 --- /dev/null +++ b/specification/base/entrypoints/sdk.dotnet/specialized-types.tsp @@ -0,0 +1,44 @@ +namespace OpenAI; + +// .NET code generation doesn't yet support many-to-one mappings of discriminators; here, we substitute one-to-one +// model mappings that would unnecessarily complicate OpenAPI emission. + +@discriminator("type") +model ComparisonFilter { + type: "eq" | "ne" | "gt" | "gte" | "lt" | "lte"; + key: string; + value: string | float32 | boolean; +} + +model ComparisonFilterEquals extends ComparisonFilter { + type: "eq"; +} +model ComparisonFilterNotEquals extends ComparisonFilter { + type: "ne"; +} +model ComparisonFilterGreaterThan extends ComparisonFilter { + type: "gt"; +} +model ComparisonFilterGreaterThanOrEquals extends ComparisonFilter { + type: "gte"; +} +model ComparisonFilterLessThan extends ComparisonFilter { + type: "lt"; +} +model ComparisonFilterLessThanOrEquals extends ComparisonFilter { + type: "lte"; +} + +@discriminator("type") +model CompoundFilter { + type: "and" | "or"; + filters: (ComparisonFilter | CompoundFilter)[]; +} +model CompoundFilterAnd extends CompoundFilter { + type: "and"; +} +model CompoundFilterOr extends CompoundFilter { + type: "or"; +} + +alias VectorStoreFileAttributes = Record; diff --git a/specification/base/external-specs/latest.yaml b/specification/base/external-specs/latest.yaml new file mode 100644 index 000000000..e2257eb82 --- /dev/null +++ b/specification/base/external-specs/latest.yaml @@ -0,0 +1,44189 @@ +# MSFT: Spec sourced from export-api pipeline +# commit 0804cb67c18879e9f7766cc56dd6cd4dc0a6bd17 +# Date: Wed Jun 11 16:35:51 2025 +0000 +# [Amendments made in sources for OAS3 compliance] + +openapi: 3.0.0 +info: + title: OpenAI API + description: The OpenAI REST API. Please see + https://platform.openai.com/docs/api-reference for more details. + version: 2.3.0 + termsOfService: https://openai.com/policies/terms-of-use + contact: + name: OpenAI Support + url: https://help.openai.com/ + license: + name: MIT + url: https://github.com/openai/openai-openapi/blob/master/LICENSE +servers: + - url: https://api.openai.com/v1 +security: + - ApiKeyAuth: [] +tags: + - name: Assistants + description: Build Assistants that can call models and use tools. + - name: Audio + description: Turn audio into text or text into audio. + - name: Chat + description: Given a list of messages comprising a conversation, the model will + return a response. + - name: Completions + description: Given a prompt, the model will return one or more predicted + completions, and can also return the probabilities of alternative tokens + at each position. + - name: Embeddings + description: Get a vector representation of a given input that can be easily + consumed by machine learning models and algorithms. + - name: Evals + description: Manage and run evals in the OpenAI platform. + - name: Fine-tuning + description: Manage fine-tuning jobs to tailor a model to your specific training data. + - name: Graders + description: Manage and run graders in the OpenAI platform. + - name: Batch + description: Create large batches of API requests to run asynchronously. + - name: Files + description: Files are used to upload documents that can be used with features + like Assistants and Fine-tuning. + - name: Uploads + description: Use Uploads to upload large files in multiple parts. + - name: Images + description: Given a prompt and/or an input image, the model will generate a new image. + - name: Models + description: List and describe the various models available in the API. + - name: Moderations + description: Given text and/or image inputs, classifies if those inputs are + potentially harmful. + - name: Audit Logs + description: List user actions and configuration changes within this organization. +paths: + /assistants: + get: + operationId: listAssistants + tags: + - Assistants + summary: Returns a list of assistants. + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListAssistantsResponse" + x-oaiMeta: + name: List assistants + group: assistants + beta: true + returns: A list of [assistant](/docs/api-reference/assistants/object) objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/assistants?order=desc&limit=20" \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + my_assistants = client.beta.assistants.list( + order="desc", + limit="20", + ) + print(my_assistants.data) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const myAssistants = await openai.beta.assistants.list({ + order: "desc", + limit: "20", + }); + + console.log(myAssistants.data); + } + + main(); + response: > + { + "object": "list", + "data": [ + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1698982736, + "name": "Coding Tutor", + "description": null, + "model": "gpt-4o", + "instructions": "You are a helpful assistant designed to make me better at coding!", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + }, + { + "id": "asst_abc456", + "object": "assistant", + "created_at": 1698982718, + "name": "My Assistant", + "description": null, + "model": "gpt-4o", + "instructions": "You are a helpful assistant designed to make me better at coding!", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + }, + { + "id": "asst_abc789", + "object": "assistant", + "created_at": 1698982643, + "name": null, + "description": null, + "model": "gpt-4o", + "instructions": null, + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + ], + "first_id": "asst_abc123", + "last_id": "asst_abc789", + "has_more": false + } + post: + operationId: createAssistant + tags: + - Assistants + summary: Create an assistant with a model and instructions. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateAssistantRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/AssistantObject" + x-oaiMeta: + name: Create assistant + group: assistants + beta: true + returns: An [assistant](/docs/api-reference/assistants/object) object. + examples: + - title: Code Interpreter + request: + curl: > + curl "https://api.openai.com/v1/assistants" \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", + "name": "Math Tutor", + "tools": [{"type": "code_interpreter"}], + "model": "gpt-4o" + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + my_assistant = client.beta.assistants.create( + instructions="You are a personal math tutor. When asked a question, write and run Python code to answer the question.", + name="Math Tutor", + tools=[{"type": "code_interpreter"}], + model="gpt-4o", + ) + + print(my_assistant) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const myAssistant = await openai.beta.assistants.create({ + instructions: + "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", + name: "Math Tutor", + tools: [{ type: "code_interpreter" }], + model: "gpt-4o", + }); + + console.log(myAssistant); + } + + + main(); + response: > + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1698984975, + "name": "Math Tutor", + "description": null, + "model": "gpt-4o", + "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", + "tools": [ + { + "type": "code_interpreter" + } + ], + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + - title: Files + request: + curl: > + curl https://api.openai.com/v1/assistants \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", + "tools": [{"type": "file_search"}], + "tool_resources": {"file_search": {"vector_store_ids": ["vs_123"]}}, + "model": "gpt-4o" + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + my_assistant = client.beta.assistants.create( + instructions="You are an HR bot, and you have access to files to answer employee questions about company policies.", + name="HR Helper", + tools=[{"type": "file_search"}], + tool_resources={"file_search": {"vector_store_ids": ["vs_123"]}}, + model="gpt-4o" + ) + + print(my_assistant) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const myAssistant = await openai.beta.assistants.create({ + instructions: + "You are an HR bot, and you have access to files to answer employee questions about company policies.", + name: "HR Helper", + tools: [{ type: "file_search" }], + tool_resources: { + file_search: { + vector_store_ids: ["vs_123"] + } + }, + model: "gpt-4o" + }); + + console.log(myAssistant); + } + + + main(); + response: > + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1699009403, + "name": "HR Helper", + "description": null, + "model": "gpt-4o", + "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", + "tools": [ + { + "type": "file_search" + } + ], + "tool_resources": { + "file_search": { + "vector_store_ids": ["vs_123"] + } + }, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + /assistants/{assistant_id}: + get: + operationId: getAssistant + tags: + - Assistants + summary: Retrieves an assistant. + parameters: + - in: path + name: assistant_id + required: true + schema: + type: string + description: The ID of the assistant to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/AssistantObject" + x-oaiMeta: + name: Retrieve assistant + group: assistants + beta: true + returns: The [assistant](/docs/api-reference/assistants/object) object matching + the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/assistants/asst_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + my_assistant = client.beta.assistants.retrieve("asst_abc123") + print(my_assistant) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const myAssistant = await openai.beta.assistants.retrieve( + "asst_abc123" + ); + + console.log(myAssistant); + } + + main(); + response: > + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1699009709, + "name": "HR Helper", + "description": null, + "model": "gpt-4o", + "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies.", + "tools": [ + { + "type": "file_search" + } + ], + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + post: + operationId: modifyAssistant + tags: + - Assistants + summary: Modifies an assistant. + parameters: + - in: path + name: assistant_id + required: true + schema: + type: string + description: The ID of the assistant to modify. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ModifyAssistantRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/AssistantObject" + x-oaiMeta: + name: Modify assistant + group: assistants + beta: true + returns: The modified [assistant](/docs/api-reference/assistants/object) object. + examples: + request: + curl: > + curl https://api.openai.com/v1/assistants/asst_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", + "tools": [{"type": "file_search"}], + "model": "gpt-4o" + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + my_updated_assistant = client.beta.assistants.update( + "asst_abc123", + instructions="You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", + name="HR Helper", + tools=[{"type": "file_search"}], + model="gpt-4o" + ) + + + print(my_updated_assistant) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const myUpdatedAssistant = await openai.beta.assistants.update( + "asst_abc123", + { + instructions: + "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", + name: "HR Helper", + tools: [{ type: "file_search" }], + model: "gpt-4o" + } + ); + + console.log(myUpdatedAssistant); + } + + + main(); + response: > + { + "id": "asst_123", + "object": "assistant", + "created_at": 1699009709, + "name": "HR Helper", + "description": null, + "model": "gpt-4o", + "instructions": "You are an HR bot, and you have access to files to answer employee questions about company policies. Always response with info from either of the files.", + "tools": [ + { + "type": "file_search" + } + ], + "tool_resources": { + "file_search": { + "vector_store_ids": [] + } + }, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + delete: + operationId: deleteAssistant + tags: + - Assistants + summary: Delete an assistant. + parameters: + - in: path + name: assistant_id + required: true + schema: + type: string + description: The ID of the assistant to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteAssistantResponse" + x-oaiMeta: + name: Delete assistant + group: assistants + beta: true + returns: Deletion status + examples: + request: + curl: | + curl https://api.openai.com/v1/assistants/asst_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -X DELETE + python: | + from openai import OpenAI + client = OpenAI() + + response = client.beta.assistants.delete("asst_abc123") + print(response) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const response = await openai.beta.assistants.del("asst_abc123"); + + console.log(response); + } + + main(); + response: | + { + "id": "asst_abc123", + "object": "assistant.deleted", + "deleted": true + } + /audio/speech: + post: + operationId: createSpeech + tags: + - Audio + summary: Generates audio from the input text. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateSpeechRequest" + responses: + "200": + description: OK + headers: + Transfer-Encoding: + schema: + type: string + description: chunked + content: + application/octet-stream: + schema: + type: string + format: binary + x-oaiMeta: + name: Create speech + group: audio + returns: The audio file content. + examples: + request: + curl: | + curl https://api.openai.com/v1/audio/speech \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "gpt-4o-mini-tts", + "input": "The quick brown fox jumped over the lazy dog.", + "voice": "alloy" + }' \ + --output speech.mp3 + python: | + from pathlib import Path + import openai + + speech_file_path = Path(__file__).parent / "speech.mp3" + with openai.audio.speech.with_streaming_response.create( + model="gpt-4o-mini-tts", + voice="alloy", + input="The quick brown fox jumped over the lazy dog." + ) as response: + response.stream_to_file(speech_file_path) + javascript: > + import fs from "fs"; + + import path from "path"; + + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const speechFile = path.resolve("./speech.mp3"); + + + async function main() { + const mp3 = await openai.audio.speech.create({ + model: "gpt-4o-mini-tts", + voice: "alloy", + input: "Today is a wonderful day to build something people love!", + }); + console.log(speechFile); + const buffer = Buffer.from(await mp3.arrayBuffer()); + await fs.promises.writeFile(speechFile, buffer); + } + + main(); + csharp: | + using System; + using System.IO; + + using OpenAI.Audio; + + AudioClient client = new( + model: "gpt-4o-mini-tts", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + BinaryData speech = client.GenerateSpeech( + text: "The quick brown fox jumped over the lazy dog.", + voice: GeneratedSpeechVoice.Alloy + ); + + using FileStream stream = File.OpenWrite("speech.mp3"); + speech.ToStream().CopyTo(stream); + /audio/transcriptions: + post: + operationId: createTranscription + tags: + - Audio + summary: Transcribes audio into the input language. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateTranscriptionRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + oneOf: + - $ref: "#/components/schemas/CreateTranscriptionResponseJson" + - $ref: "#/components/schemas/CreateTranscriptionResponseVerboseJson" + text/event-stream: + schema: + $ref: "#/components/schemas/CreateTranscriptionResponseStreamEvent" + x-oaiMeta: + name: Create transcription + group: audio + returns: The [transcription object](/docs/api-reference/audio/json-object), a + [verbose transcription + object](/docs/api-reference/audio/verbose-json-object) or a [stream of + transcript + events](/docs/api-reference/audio/transcript-text-delta-event). + examples: + - title: Default + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F model="gpt-4o-transcribe" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.transcriptions.create( + model="gpt-4o-transcribe", + file=audio_file + ) + javascript: > + import fs from "fs"; + + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const transcription = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "gpt-4o-transcribe", + }); + + console.log(transcription.text); + } + + main(); + csharp: > + using System; + + + using OpenAI.Audio; + + string audioFilePath = "audio.mp3"; + + + AudioClient client = new( + model: "gpt-4o-transcribe", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + AudioTranscription transcription = + client.TranscribeAudio(audioFilePath); + + + Console.WriteLine($"{transcription.Text}"); + response: > + { + "text": "Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that." + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F model="gpt-4o-mini-transcribe" \ + -F stream=true + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + stream = client.audio.transcriptions.create( + file=audio_file, + model="gpt-4o-mini-transcribe", + stream=True + ) + + for event in stream: + print(event) + javascript: | + import fs from "fs"; + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const stream = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "gpt-4o-mini-transcribe", + stream: true, + }); + + for await (const event of stream) { + console.log(event); + } + response: | + data: {"type":"transcript.text.delta","delta":"I","logprobs":[{"token":"I","logprob":-0.00007588794,"bytes":[73]}]} + + data: {"type":"transcript.text.delta","delta":" see","logprobs":[{"token":" see","logprob":-3.1281633e-7,"bytes":[32,115,101,101]}]} + + data: {"type":"transcript.text.delta","delta":" skies","logprobs":[{"token":" skies","logprob":-2.3392786e-6,"bytes":[32,115,107,105,101,115]}]} + + data: {"type":"transcript.text.delta","delta":" of","logprobs":[{"token":" of","logprob":-3.1281633e-7,"bytes":[32,111,102]}]} + + data: {"type":"transcript.text.delta","delta":" blue","logprobs":[{"token":" blue","logprob":-1.0280384e-6,"bytes":[32,98,108,117,101]}]} + + data: {"type":"transcript.text.delta","delta":" and","logprobs":[{"token":" and","logprob":-0.0005108566,"bytes":[32,97,110,100]}]} + + data: {"type":"transcript.text.delta","delta":" clouds","logprobs":[{"token":" clouds","logprob":-1.9361265e-7,"bytes":[32,99,108,111,117,100,115]}]} + + data: {"type":"transcript.text.delta","delta":" of","logprobs":[{"token":" of","logprob":-1.9361265e-7,"bytes":[32,111,102]}]} + + data: {"type":"transcript.text.delta","delta":" white","logprobs":[{"token":" white","logprob":-7.89631e-7,"bytes":[32,119,104,105,116,101]}]} + + data: {"type":"transcript.text.delta","delta":",","logprobs":[{"token":",","logprob":-0.0014890312,"bytes":[44]}]} + + data: {"type":"transcript.text.delta","delta":" the","logprobs":[{"token":" the","logprob":-0.0110956915,"bytes":[32,116,104,101]}]} + + data: {"type":"transcript.text.delta","delta":" bright","logprobs":[{"token":" bright","logprob":0.0,"bytes":[32,98,114,105,103,104,116]}]} + + data: {"type":"transcript.text.delta","delta":" blessed","logprobs":[{"token":" blessed","logprob":-0.000045848617,"bytes":[32,98,108,101,115,115,101,100]}]} + + data: {"type":"transcript.text.delta","delta":" days","logprobs":[{"token":" days","logprob":-0.000010802739,"bytes":[32,100,97,121,115]}]} + + data: {"type":"transcript.text.delta","delta":",","logprobs":[{"token":",","logprob":-0.00001700133,"bytes":[44]}]} + + data: {"type":"transcript.text.delta","delta":" the","logprobs":[{"token":" the","logprob":-0.0000118755715,"bytes":[32,116,104,101]}]} + + data: {"type":"transcript.text.delta","delta":" dark","logprobs":[{"token":" dark","logprob":-5.5122365e-7,"bytes":[32,100,97,114,107]}]} + + data: {"type":"transcript.text.delta","delta":" sacred","logprobs":[{"token":" sacred","logprob":-5.4385737e-6,"bytes":[32,115,97,99,114,101,100]}]} + + data: {"type":"transcript.text.delta","delta":" nights","logprobs":[{"token":" nights","logprob":-4.00813e-6,"bytes":[32,110,105,103,104,116,115]}]} + + data: {"type":"transcript.text.delta","delta":",","logprobs":[{"token":",","logprob":-0.0036910512,"bytes":[44]}]} + + data: {"type":"transcript.text.delta","delta":" and","logprobs":[{"token":" and","logprob":-0.0031903093,"bytes":[32,97,110,100]}]} + + data: {"type":"transcript.text.delta","delta":" I","logprobs":[{"token":" I","logprob":-1.504853e-6,"bytes":[32,73]}]} + + data: {"type":"transcript.text.delta","delta":" think","logprobs":[{"token":" think","logprob":-4.3202e-7,"bytes":[32,116,104,105,110,107]}]} + + data: {"type":"transcript.text.delta","delta":" to","logprobs":[{"token":" to","logprob":-1.9361265e-7,"bytes":[32,116,111]}]} + + data: {"type":"transcript.text.delta","delta":" myself","logprobs":[{"token":" myself","logprob":-1.7432603e-6,"bytes":[32,109,121,115,101,108,102]}]} + + data: {"type":"transcript.text.delta","delta":",","logprobs":[{"token":",","logprob":-0.29254505,"bytes":[44]}]} + + data: {"type":"transcript.text.delta","delta":" what","logprobs":[{"token":" what","logprob":-0.016815351,"bytes":[32,119,104,97,116]}]} + + data: {"type":"transcript.text.delta","delta":" a","logprobs":[{"token":" a","logprob":-3.1281633e-7,"bytes":[32,97]}]} + + data: {"type":"transcript.text.delta","delta":" wonderful","logprobs":[{"token":" wonderful","logprob":-2.1008714e-6,"bytes":[32,119,111,110,100,101,114,102,117,108]}]} + + data: {"type":"transcript.text.delta","delta":" world","logprobs":[{"token":" world","logprob":-8.180258e-6,"bytes":[32,119,111,114,108,100]}]} + + data: {"type":"transcript.text.delta","delta":".","logprobs":[{"token":".","logprob":-0.014231676,"bytes":[46]}]} + + data: {"type":"transcript.text.done","text":"I see skies of blue and clouds of white, the bright blessed days, the dark sacred nights, and I think to myself, what a wonderful world.","logprobs":[{"token":"I","logprob":-0.00007588794,"bytes":[73]},{"token":" see","logprob":-3.1281633e-7,"bytes":[32,115,101,101]},{"token":" skies","logprob":-2.3392786e-6,"bytes":[32,115,107,105,101,115]},{"token":" of","logprob":-3.1281633e-7,"bytes":[32,111,102]},{"token":" blue","logprob":-1.0280384e-6,"bytes":[32,98,108,117,101]},{"token":" and","logprob":-0.0005108566,"bytes":[32,97,110,100]},{"token":" clouds","logprob":-1.9361265e-7,"bytes":[32,99,108,111,117,100,115]},{"token":" of","logprob":-1.9361265e-7,"bytes":[32,111,102]},{"token":" white","logprob":-7.89631e-7,"bytes":[32,119,104,105,116,101]},{"token":",","logprob":-0.0014890312,"bytes":[44]},{"token":" the","logprob":-0.0110956915,"bytes":[32,116,104,101]},{"token":" bright","logprob":0.0,"bytes":[32,98,114,105,103,104,116]},{"token":" blessed","logprob":-0.000045848617,"bytes":[32,98,108,101,115,115,101,100]},{"token":" days","logprob":-0.000010802739,"bytes":[32,100,97,121,115]},{"token":",","logprob":-0.00001700133,"bytes":[44]},{"token":" the","logprob":-0.0000118755715,"bytes":[32,116,104,101]},{"token":" dark","logprob":-5.5122365e-7,"bytes":[32,100,97,114,107]},{"token":" sacred","logprob":-5.4385737e-6,"bytes":[32,115,97,99,114,101,100]},{"token":" nights","logprob":-4.00813e-6,"bytes":[32,110,105,103,104,116,115]},{"token":",","logprob":-0.0036910512,"bytes":[44]},{"token":" and","logprob":-0.0031903093,"bytes":[32,97,110,100]},{"token":" I","logprob":-1.504853e-6,"bytes":[32,73]},{"token":" think","logprob":-4.3202e-7,"bytes":[32,116,104,105,110,107]},{"token":" to","logprob":-1.9361265e-7,"bytes":[32,116,111]},{"token":" myself","logprob":-1.7432603e-6,"bytes":[32,109,121,115,101,108,102]},{"token":",","logprob":-0.29254505,"bytes":[44]},{"token":" what","logprob":-0.016815351,"bytes":[32,119,104,97,116]},{"token":" a","logprob":-3.1281633e-7,"bytes":[32,97]},{"token":" wonderful","logprob":-2.1008714e-6,"bytes":[32,119,111,110,100,101,114,102,117,108]},{"token":" world","logprob":-8.180258e-6,"bytes":[32,119,111,114,108,100]},{"token":".","logprob":-0.014231676,"bytes":[46]}]} + - title: Logprobs + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F "include[]=logprobs" \ + -F model="gpt-4o-transcribe" \ + -F response_format="json" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.transcriptions.create( + file=audio_file, + model="gpt-4o-transcribe", + response_format="json", + include=["logprobs"] + ) + + print(transcript) + javascript: > + import fs from "fs"; + + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const transcription = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "gpt-4o-transcribe", + response_format: "json", + include: ["logprobs"] + }); + + console.log(transcription); + } + + main(); + response: > + { + "text": "Hey, my knee is hurting and I want to see the doctor tomorrow ideally.", + "logprobs": [ + { "token": "Hey", "logprob": -1.0415299, "bytes": [72, 101, 121] }, + { "token": ",", "logprob": -9.805982e-5, "bytes": [44] }, + { "token": " my", "logprob": -0.00229799, "bytes": [32, 109, 121] }, + { + "token": " knee", + "logprob": -4.7159858e-5, + "bytes": [32, 107, 110, 101, 101] + }, + { "token": " is", "logprob": -0.043909557, "bytes": [32, 105, 115] }, + { + "token": " hurting", + "logprob": -1.1041146e-5, + "bytes": [32, 104, 117, 114, 116, 105, 110, 103] + }, + { "token": " and", "logprob": -0.011076359, "bytes": [32, 97, 110, 100] }, + { "token": " I", "logprob": -5.3193703e-6, "bytes": [32, 73] }, + { + "token": " want", + "logprob": -0.0017156356, + "bytes": [32, 119, 97, 110, 116] + }, + { "token": " to", "logprob": -7.89631e-7, "bytes": [32, 116, 111] }, + { "token": " see", "logprob": -5.5122365e-7, "bytes": [32, 115, 101, 101] }, + { "token": " the", "logprob": -0.0040786397, "bytes": [32, 116, 104, 101] }, + { + "token": " doctor", + "logprob": -2.3392786e-6, + "bytes": [32, 100, 111, 99, 116, 111, 114] + }, + { + "token": " tomorrow", + "logprob": -7.89631e-7, + "bytes": [32, 116, 111, 109, 111, 114, 114, 111, 119] + }, + { + "token": " ideally", + "logprob": -0.5800861, + "bytes": [32, 105, 100, 101, 97, 108, 108, 121] + }, + { "token": ".", "logprob": -0.00011093382, "bytes": [46] } + ] + } + - title: Word timestamps + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F "timestamp_granularities[]=word" \ + -F model="whisper-1" \ + -F response_format="verbose_json" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.transcriptions.create( + file=audio_file, + model="whisper-1", + response_format="verbose_json", + timestamp_granularities=["word"] + ) + + print(transcript.words) + javascript: > + import fs from "fs"; + + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const transcription = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "whisper-1", + response_format: "verbose_json", + timestamp_granularities: ["word"] + }); + + console.log(transcription.text); + } + + main(); + csharp: > + using System; + + + using OpenAI.Audio; + + + string audioFilePath = "audio.mp3"; + + + AudioClient client = new( + model: "whisper-1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + AudioTranscriptionOptions options = new() + + { + ResponseFormat = AudioTranscriptionFormat.Verbose, + TimestampGranularities = AudioTimestampGranularities.Word, + }; + + + AudioTranscription transcription = + client.TranscribeAudio(audioFilePath, options); + + + Console.WriteLine($"{transcription.Text}"); + response: > + { + "task": "transcribe", + "language": "english", + "duration": 8.470000267028809, + "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.", + "words": [ + { + "word": "The", + "start": 0.0, + "end": 0.23999999463558197 + }, + ... + { + "word": "volleyball", + "start": 7.400000095367432, + "end": 7.900000095367432 + } + ] + } + - title: Segment timestamps + request: + curl: | + curl https://api.openai.com/v1/audio/transcriptions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/audio.mp3" \ + -F "timestamp_granularities[]=segment" \ + -F model="whisper-1" \ + -F response_format="verbose_json" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.transcriptions.create( + file=audio_file, + model="whisper-1", + response_format="verbose_json", + timestamp_granularities=["segment"] + ) + + print(transcript.words) + javascript: > + import fs from "fs"; + + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const transcription = await openai.audio.transcriptions.create({ + file: fs.createReadStream("audio.mp3"), + model: "whisper-1", + response_format: "verbose_json", + timestamp_granularities: ["segment"] + }); + + console.log(transcription.text); + } + + main(); + csharp: > + using System; + + + using OpenAI.Audio; + + + string audioFilePath = "audio.mp3"; + + + AudioClient client = new( + model: "whisper-1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + AudioTranscriptionOptions options = new() + + { + ResponseFormat = AudioTranscriptionFormat.Verbose, + TimestampGranularities = AudioTimestampGranularities.Segment, + }; + + + AudioTranscription transcription = + client.TranscribeAudio(audioFilePath, options); + + + Console.WriteLine($"{transcription.Text}"); + response: > + { + "task": "transcribe", + "language": "english", + "duration": 8.470000267028809, + "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.", + "segments": [ + { + "id": 0, + "seek": 0, + "start": 0.0, + "end": 3.319999933242798, + "text": " The beach was a popular spot on a hot summer day.", + "tokens": [ + 50364, 440, 7534, 390, 257, 3743, 4008, 322, 257, 2368, 4266, 786, 13, 50530 + ], + "temperature": 0.0, + "avg_logprob": -0.2860786020755768, + "compression_ratio": 1.2363636493682861, + "no_speech_prob": 0.00985979475080967 + }, + ... + ] + } + /audio/translations: + post: + operationId: createTranslation + tags: + - Audio + summary: Translates audio into English. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateTranslationRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + oneOf: + - $ref: "#/components/schemas/CreateTranslationResponseJson" + - $ref: "#/components/schemas/CreateTranslationResponseVerboseJson" + x-oaiMeta: + name: Create translation + group: audio + returns: The translated text. + examples: + request: + curl: | + curl https://api.openai.com/v1/audio/translations \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: multipart/form-data" \ + -F file="@/path/to/file/german.m4a" \ + -F model="whisper-1" + python: | + from openai import OpenAI + client = OpenAI() + + audio_file = open("speech.mp3", "rb") + transcript = client.audio.translations.create( + model="whisper-1", + file=audio_file + ) + javascript: | + import fs from "fs"; + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const translation = await openai.audio.translations.create({ + file: fs.createReadStream("speech.mp3"), + model: "whisper-1", + }); + + console.log(translation.text); + } + main(); + csharp: > + using System; + + + using OpenAI.Audio; + + + string audioFilePath = "audio.mp3"; + + + AudioClient client = new( + model: "whisper-1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + AudioTranscription transcription = + client.TranscribeAudio(audioFilePath); + + + Console.WriteLine($"{transcription.Text}"); + response: > + { + "text": "Hello, my name is Wolfgang and I come from Germany. Where are you heading today?" + } + /batches: + post: + summary: Creates and executes a batch from an uploaded file of requests + operationId: createBatch + tags: + - Batch + requestBody: + required: true + content: + application/json: + schema: + type: object + required: + - input_file_id + - endpoint + - completion_window + properties: + input_file_id: + type: string + description: > + The ID of an uploaded file that contains requests for the + new batch. + + + See [upload file](/docs/api-reference/files/create) for how + to upload a file. + + + Your input file must be formatted as a [JSONL + file](/docs/api-reference/batch/request-input), and must be + uploaded with the purpose `batch`. The file can contain up + to 50,000 requests, and can be up to 200 MB in size. + endpoint: + type: string + enum: + - /v1/responses + - /v1/chat/completions + - /v1/embeddings + - /v1/completions + description: The endpoint to be used for all requests in the batch. Currently + `/v1/responses`, `/v1/chat/completions`, `/v1/embeddings`, + and `/v1/completions` are supported. Note that + `/v1/embeddings` batches are also restricted to a maximum of + 50,000 embedding inputs across all requests in the batch. + completion_window: + type: string + enum: + - 24h + description: The time frame within which the batch should be processed. + Currently only `24h` is supported. + metadata: + $ref: "#/components/schemas/Metadata" + responses: + "200": + description: Batch created successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Batch" + x-oaiMeta: + name: Create batch + group: batch + returns: The created [Batch](/docs/api-reference/batch/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "input_file_id": "file-abc123", + "endpoint": "/v1/chat/completions", + "completion_window": "24h" + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.create( + input_file_id="file-abc123", + endpoint="/v1/chat/completions", + completion_window="24h" + ) + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const batch = await openai.batches.create({ + input_file_id: "file-abc123", + endpoint: "/v1/chat/completions", + completion_window: "24h" + }); + + console.log(batch); + } + + main(); + response: | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/chat/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "validating", + "output_file_id": null, + "error_file_id": null, + "created_at": 1711471533, + "in_progress_at": null, + "expires_at": null, + "finalizing_at": null, + "completed_at": null, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 0, + "completed": 0, + "failed": 0 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + get: + operationId: listBatches + tags: + - Batch + summary: List your organization's batches. + parameters: + - in: query + name: after + required: false + schema: + type: string + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + responses: + "200": + description: Batch listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListBatchesResponse" + x-oaiMeta: + name: List batch + group: batch + returns: A list of paginated [Batch](/docs/api-reference/batch/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches?limit=2 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.list() + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const list = await openai.batches.list(); + + for await (const batch of list) { + console.log(batch); + } + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/chat/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "completed", + "output_file_id": "file-cvaTdG", + "error_file_id": "file-HOWS94", + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": 1711493133, + "completed_at": 1711493163, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 95, + "failed": 5 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly job", + } + }, + { ... }, + ], + "first_id": "batch_abc123", + "last_id": "batch_abc456", + "has_more": true + } + /batches/{batch_id}: + get: + operationId: retrieveBatch + tags: + - Batch + summary: Retrieves a batch. + parameters: + - in: path + name: batch_id + required: true + schema: + type: string + description: The ID of the batch to retrieve. + responses: + "200": + description: Batch retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Batch" + x-oaiMeta: + name: Retrieve batch + group: batch + returns: The [Batch](/docs/api-reference/batch/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches/batch_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.retrieve("batch_abc123") + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const batch = await openai.batches.retrieve("batch_abc123"); + + console.log(batch); + } + + main(); + response: | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "completed", + "output_file_id": "file-cvaTdG", + "error_file_id": "file-HOWS94", + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": 1711493133, + "completed_at": 1711493163, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 95, + "failed": 5 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + /batches/{batch_id}/cancel: + post: + operationId: cancelBatch + tags: + - Batch + summary: Cancels an in-progress batch. The batch will be in status `cancelling` + for up to 10 minutes, before changing to `cancelled`, where it will have + partial results (if any) available in the output file. + parameters: + - in: path + name: batch_id + required: true + schema: + type: string + description: The ID of the batch to cancel. + responses: + "200": + description: Batch is cancelling. Returns the cancelling batch's details. + content: + application/json: + schema: + $ref: "#/components/schemas/Batch" + x-oaiMeta: + name: Cancel batch + group: batch + returns: The [Batch](/docs/api-reference/batch/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/batches/batch_abc123/cancel \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -X POST + python: | + from openai import OpenAI + client = OpenAI() + + client.batches.cancel("batch_abc123") + node: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const batch = await openai.batches.cancel("batch_abc123"); + + console.log(batch); + } + + main(); + response: | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/chat/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "cancelling", + "output_file_id": null, + "error_file_id": null, + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": null, + "completed_at": null, + "failed_at": null, + "expired_at": null, + "cancelling_at": 1711475133, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 23, + "failed": 1 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + /chat/completions: + get: + operationId: listChatCompletions + tags: + - Chat + summary: > + List stored Chat Completions. Only Chat Completions that have been + stored + + with the `store` parameter set to `true` will be returned. + parameters: + - name: model + in: query + description: The model used to generate the Chat Completions. + required: false + schema: + type: string + - name: metadata + in: query + description: | + A list of metadata keys to filter the Chat Completions by. Example: + + `metadata[key1]=value1&metadata[key2]=value2` + required: false + schema: + $ref: "#/components/schemas/Metadata" + - name: after + in: query + description: Identifier for the last chat completion from the previous + pagination request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of Chat Completions to retrieve. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: Sort order for Chat Completions by timestamp. Use `asc` for + ascending order or `desc` for descending order. Defaults to `asc`. + required: false + schema: + type: string + enum: + - asc + - desc + default: asc + responses: + "200": + description: A list of Chat Completions + content: + application/json: + schema: + $ref: "#/components/schemas/ChatCompletionList" + x-oaiMeta: + name: List Chat Completions + group: chat + returns: A list of [Chat Completions](/docs/api-reference/chat/list-object) + matching the specified filters. + path: list + examples: + request: + curl: | + curl https://api.openai.com/v1/chat/completions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: | + from openai import OpenAI + client = OpenAI() + + completions = client.chat.completions.list() + print(completions) + response: > + { + "object": "list", + "data": [ + { + "object": "chat.completion", + "id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2", + "model": "gpt-4.1-2025-04-14", + "created": 1738960610, + "request_id": "req_ded8ab984ec4bf840f37566c1011c417", + "tool_choice": null, + "usage": { + "total_tokens": 31, + "completion_tokens": 18, + "prompt_tokens": 13 + }, + "seed": 4944116822809979520, + "top_p": 1.0, + "temperature": 1.0, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "system_fingerprint": "fp_50cad350e4", + "input_user": null, + "service_tier": "default", + "tools": null, + "metadata": {}, + "choices": [ + { + "index": 0, + "message": { + "content": "Mind of circuits hum, \nLearning patterns in silence— \nFuture's quiet spark.", + "role": "assistant", + "tool_calls": null, + "function_call": null + }, + "finish_reason": "stop", + "logprobs": null + } + ], + "response_format": null + } + ], + "first_id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2", + "last_id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2", + "has_more": false + } + post: + operationId: createChatCompletion + tags: + - Chat + summary: | + **Starting a new project?** We recommend trying [Responses](/docs/api-reference/responses) + to take advantage of the latest OpenAI platform features. Compare + [Chat Completions with Responses](/docs/guides/responses-vs-chat-completions?api-mode=responses). + + --- + + Creates a model response for the given chat conversation. Learn more in the + [text generation](/docs/guides/text-generation), [vision](/docs/guides/vision), + and [audio](/docs/guides/audio) guides. + + Parameter support can differ depending on the model used to generate the + response, particularly for newer reasoning models. Parameters that are only + supported for reasoning models are noted below. For the current state of + unsupported parameters in reasoning models, + [refer to the reasoning guide](/docs/guides/reasoning). + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateChatCompletionRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/CreateChatCompletionResponse" + text/event-stream: + schema: + $ref: "#/components/schemas/CreateChatCompletionStreamResponse" + x-oaiMeta: + name: Create chat completion + group: chat + returns: > + Returns a [chat completion](/docs/api-reference/chat/object) object, + or a streamed sequence of [chat completion + chunk](/docs/api-reference/chat/streaming) objects if the request is + streamed. + path: create + examples: + - title: Default + request: + curl: | + curl https://api.openai.com/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "VAR_chat_model_id", + "messages": [ + { + "role": "developer", + "content": "You are a helpful assistant." + }, + { + "role": "user", + "content": "Hello!" + } + ] + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + completion = client.chat.completions.create( + model="VAR_chat_model_id", + messages=[ + {"role": "developer", "content": "You are a helpful assistant."}, + {"role": "user", "content": "Hello!"} + ] + ) + + + print(completion.choices[0].message) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const completion = await openai.chat.completions.create({ + messages: [{ role: "developer", content: "You are a helpful assistant." }], + model: "VAR_chat_model_id", + store: true, + }); + + console.log(completion.choices[0]); + } + + + main(); + csharp: | + using System; + using System.Collections.Generic; + + using OpenAI.Chat; + + ChatClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + List messages = + [ + new SystemChatMessage("You are a helpful assistant."), + new UserChatMessage("Hello!") + ]; + + ChatCompletion completion = client.CompleteChat(messages); + + Console.WriteLine(completion.Content[0].Text); + response: | + { + "id": "chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT", + "object": "chat.completion", + "created": 1741569952, + "model": "gpt-4.1-2025-04-14", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": "Hello! How can I assist you today?", + "refusal": null, + "annotations": [] + }, + "logprobs": null, + "finish_reason": "stop" + } + ], + "usage": { + "prompt_tokens": 19, + "completion_tokens": 10, + "total_tokens": 29, + "prompt_tokens_details": { + "cached_tokens": 0, + "audio_tokens": 0 + }, + "completion_tokens_details": { + "reasoning_tokens": 0, + "audio_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + }, + "service_tier": "default" + } + - title: Image input + request: + curl: > + curl https://api.openai.com/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "gpt-4.1", + "messages": [ + { + "role": "user", + "content": [ + { + "type": "text", + "text": "What is in this image?" + }, + { + "type": "image_url", + "image_url": { + "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" + } + } + ] + } + ], + "max_tokens": 300 + }' + python: > + from openai import OpenAI + + + client = OpenAI() + + + response = client.chat.completions.create( + model="gpt-4.1", + messages=[ + { + "role": "user", + "content": [ + {"type": "text", "text": "What's in this image?"}, + { + "type": "image_url", + "image_url": { + "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", + } + }, + ], + } + ], + max_tokens=300, + ) + + + print(response.choices[0]) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const response = await openai.chat.completions.create({ + model: "gpt-4.1", + messages: [ + { + role: "user", + content: [ + { type: "text", text: "What's in this image?" }, + { + type: "image_url", + image_url: { + "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", + }, + } + ], + }, + ], + }); + console.log(response.choices[0]); + } + + main(); + csharp: > + using System; + + using System.Collections.Generic; + + + using OpenAI.Chat; + + + ChatClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + List messages = + + [ + new UserChatMessage( + [ + ChatMessageContentPart.CreateTextPart("What's in this image?"), + ChatMessageContentPart.CreateImagePart(new Uri("https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg")) + ]) + ]; + + + ChatCompletion completion = client.CompleteChat(messages); + + + Console.WriteLine(completion.Content[0].Text); + response: > + { + "id": "chatcmpl-B9MHDbslfkBeAs8l4bebGdFOJ6PeG", + "object": "chat.completion", + "created": 1741570283, + "model": "gpt-4.1-2025-04-14", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": "The image shows a wooden boardwalk path running through a lush green field or meadow. The sky is bright blue with some scattered clouds, giving the scene a serene and peaceful atmosphere. Trees and shrubs are visible in the background.", + "refusal": null, + "annotations": [] + }, + "logprobs": null, + "finish_reason": "stop" + } + ], + "usage": { + "prompt_tokens": 1117, + "completion_tokens": 46, + "total_tokens": 1163, + "prompt_tokens_details": { + "cached_tokens": 0, + "audio_tokens": 0 + }, + "completion_tokens_details": { + "reasoning_tokens": 0, + "audio_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + }, + "service_tier": "default" + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "VAR_chat_model_id", + "messages": [ + { + "role": "developer", + "content": "You are a helpful assistant." + }, + { + "role": "user", + "content": "Hello!" + } + ], + "stream": true + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + completion = client.chat.completions.create( + model="VAR_chat_model_id", + messages=[ + {"role": "developer", "content": "You are a helpful assistant."}, + {"role": "user", "content": "Hello!"} + ], + stream=True + ) + + + for chunk in completion: + print(chunk.choices[0].delta) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const completion = await openai.chat.completions.create({ + model: "VAR_chat_model_id", + messages: [ + {"role": "developer", "content": "You are a helpful assistant."}, + {"role": "user", "content": "Hello!"} + ], + stream: true, + }); + + for await (const chunk of completion) { + console.log(chunk.choices[0].delta.content); + } + } + + + main(); + csharp: > + using System; + + using System.ClientModel; + + using System.Collections.Generic; + + using System.Threading.Tasks; + + + using OpenAI.Chat; + + + ChatClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + List messages = + + [ + new SystemChatMessage("You are a helpful assistant."), + new UserChatMessage("Hello!") + ]; + + + AsyncCollectionResult + completionUpdates = client.CompleteChatStreamingAsync(messages); + + + await foreach (StreamingChatCompletionUpdate completionUpdate in + completionUpdates) + + { + if (completionUpdate.ContentUpdate.Count > 0) + { + Console.Write(completionUpdate.ContentUpdate[0].Text); + } + } + response: | + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]} + + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]} + + .... + + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]} + - title: Functions + request: + curl: > + curl https://api.openai.com/v1/chat/completions \ + + -H "Content-Type: application/json" \ + + -H "Authorization: Bearer $OPENAI_API_KEY" \ + + -d '{ + "model": "gpt-4.1", + "messages": [ + { + "role": "user", + "content": "What is the weather like in Boston today?" + } + ], + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location"] + } + } + } + ], + "tool_choice": "auto" + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ] + + messages = [{"role": "user", "content": "What's the weather like + in Boston today?"}] + + completion = client.chat.completions.create( + model="VAR_chat_model_id", + messages=messages, + tools=tools, + tool_choice="auto" + ) + + + print(completion) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const messages = [{"role": "user", "content": "What's the weather like in Boston today?"}]; + const tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ]; + + const response = await openai.chat.completions.create({ + model: "gpt-4.1", + messages: messages, + tools: tools, + tool_choice: "auto", + }); + + console.log(response); + } + + + main(); + csharp: > + using System; + + using System.Collections.Generic; + + + using OpenAI.Chat; + + + ChatClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + ChatTool getCurrentWeatherTool = ChatTool.CreateFunctionTool( + functionName: "get_current_weather", + functionDescription: "Get the current weather in a given location", + functionParameters: BinaryData.FromString(""" + { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": [ "celsius", "fahrenheit" ] + } + }, + "required": [ "location" ] + } + """) + ); + + + List messages = + + [ + new UserChatMessage("What's the weather like in Boston today?"), + ]; + + + ChatCompletionOptions options = new() + + { + Tools = + { + getCurrentWeatherTool + }, + ToolChoice = ChatToolChoice.CreateAutoChoice(), + }; + + + ChatCompletion completion = client.CompleteChat(messages, + options); + response: | + { + "id": "chatcmpl-abc123", + "object": "chat.completion", + "created": 1699896916, + "model": "gpt-4o-mini", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": null, + "tool_calls": [ + { + "id": "call_abc123", + "type": "function", + "function": { + "name": "get_current_weather", + "arguments": "{\n\"location\": \"Boston, MA\"\n}" + } + } + ] + }, + "logprobs": null, + "finish_reason": "tool_calls" + } + ], + "usage": { + "prompt_tokens": 82, + "completion_tokens": 17, + "total_tokens": 99, + "completion_tokens_details": { + "reasoning_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + } + } + - title: Logprobs + request: + curl: | + curl https://api.openai.com/v1/chat/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "VAR_chat_model_id", + "messages": [ + { + "role": "user", + "content": "Hello!" + } + ], + "logprobs": true, + "top_logprobs": 2 + }' + python: | + from openai import OpenAI + client = OpenAI() + + completion = client.chat.completions.create( + model="VAR_chat_model_id", + messages=[ + {"role": "user", "content": "Hello!"} + ], + logprobs=True, + top_logprobs=2 + ) + + print(completion.choices[0].message) + print(completion.choices[0].logprobs) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const completion = await openai.chat.completions.create({ + messages: [{ role: "user", content: "Hello!" }], + model: "VAR_chat_model_id", + logprobs: true, + top_logprobs: 2, + }); + + console.log(completion.choices[0]); + } + + main(); + csharp: > + using System; + + using System.Collections.Generic; + + + using OpenAI.Chat; + + + ChatClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + List messages = + + [ + new UserChatMessage("Hello!") + ]; + + + ChatCompletionOptions options = new() + + { + IncludeLogProbabilities = true, + TopLogProbabilityCount = 2 + }; + + + ChatCompletion completion = client.CompleteChat(messages, + options); + + + Console.WriteLine(completion.Content[0].Text); + response: | + { + "id": "chatcmpl-123", + "object": "chat.completion", + "created": 1702685778, + "model": "gpt-4o-mini", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": "Hello! How can I assist you today?" + }, + "logprobs": { + "content": [ + { + "token": "Hello", + "logprob": -0.31725305, + "bytes": [72, 101, 108, 108, 111], + "top_logprobs": [ + { + "token": "Hello", + "logprob": -0.31725305, + "bytes": [72, 101, 108, 108, 111] + }, + { + "token": "Hi", + "logprob": -1.3190403, + "bytes": [72, 105] + } + ] + }, + { + "token": "!", + "logprob": -0.02380986, + "bytes": [ + 33 + ], + "top_logprobs": [ + { + "token": "!", + "logprob": -0.02380986, + "bytes": [33] + }, + { + "token": " there", + "logprob": -3.787621, + "bytes": [32, 116, 104, 101, 114, 101] + } + ] + }, + { + "token": " How", + "logprob": -0.000054669687, + "bytes": [32, 72, 111, 119], + "top_logprobs": [ + { + "token": " How", + "logprob": -0.000054669687, + "bytes": [32, 72, 111, 119] + }, + { + "token": "<|end|>", + "logprob": -10.953937, + "bytes": null + } + ] + }, + { + "token": " can", + "logprob": -0.015801601, + "bytes": [32, 99, 97, 110], + "top_logprobs": [ + { + "token": " can", + "logprob": -0.015801601, + "bytes": [32, 99, 97, 110] + }, + { + "token": " may", + "logprob": -4.161023, + "bytes": [32, 109, 97, 121] + } + ] + }, + { + "token": " I", + "logprob": -3.7697225e-6, + "bytes": [ + 32, + 73 + ], + "top_logprobs": [ + { + "token": " I", + "logprob": -3.7697225e-6, + "bytes": [32, 73] + }, + { + "token": " assist", + "logprob": -13.596657, + "bytes": [32, 97, 115, 115, 105, 115, 116] + } + ] + }, + { + "token": " assist", + "logprob": -0.04571125, + "bytes": [32, 97, 115, 115, 105, 115, 116], + "top_logprobs": [ + { + "token": " assist", + "logprob": -0.04571125, + "bytes": [32, 97, 115, 115, 105, 115, 116] + }, + { + "token": " help", + "logprob": -3.1089056, + "bytes": [32, 104, 101, 108, 112] + } + ] + }, + { + "token": " you", + "logprob": -5.4385737e-6, + "bytes": [32, 121, 111, 117], + "top_logprobs": [ + { + "token": " you", + "logprob": -5.4385737e-6, + "bytes": [32, 121, 111, 117] + }, + { + "token": " today", + "logprob": -12.807695, + "bytes": [32, 116, 111, 100, 97, 121] + } + ] + }, + { + "token": " today", + "logprob": -0.0040071653, + "bytes": [32, 116, 111, 100, 97, 121], + "top_logprobs": [ + { + "token": " today", + "logprob": -0.0040071653, + "bytes": [32, 116, 111, 100, 97, 121] + }, + { + "token": "?", + "logprob": -5.5247097, + "bytes": [63] + } + ] + }, + { + "token": "?", + "logprob": -0.0008108172, + "bytes": [63], + "top_logprobs": [ + { + "token": "?", + "logprob": -0.0008108172, + "bytes": [63] + }, + { + "token": "?\n", + "logprob": -7.184561, + "bytes": [63, 10] + } + ] + } + ] + }, + "finish_reason": "stop" + } + ], + "usage": { + "prompt_tokens": 9, + "completion_tokens": 9, + "total_tokens": 18, + "completion_tokens_details": { + "reasoning_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + }, + "system_fingerprint": null + } + /chat/completions/{completion_id}: + get: + operationId: getChatCompletion + tags: + - Chat + summary: > + Get a stored chat completion. Only Chat Completions that have been + created + + with the `store` parameter set to `true` will be returned. + parameters: + - in: path + name: completion_id + required: true + schema: + type: string + description: The ID of the chat completion to retrieve. + responses: + "200": + description: A chat completion + content: + application/json: + schema: + $ref: "#/components/schemas/CreateChatCompletionResponse" + x-oaiMeta: + name: Get chat completion + group: chat + returns: The [ChatCompletion](/docs/api-reference/chat/object) object matching + the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/chat/completions/chatcmpl-abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: > + from openai import OpenAI + + client = OpenAI() + + + completions = client.chat.completions.list() + + first_id = completions[0].id + + first_completion = + client.chat.completions.retrieve(completion_id=first_id) + + print(first_completion) + response: > + { + "object": "chat.completion", + "id": "chatcmpl-abc123", + "model": "gpt-4o-2024-08-06", + "created": 1738960610, + "request_id": "req_ded8ab984ec4bf840f37566c1011c417", + "tool_choice": null, + "usage": { + "total_tokens": 31, + "completion_tokens": 18, + "prompt_tokens": 13 + }, + "seed": 4944116822809979520, + "top_p": 1.0, + "temperature": 1.0, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "system_fingerprint": "fp_50cad350e4", + "input_user": null, + "service_tier": "default", + "tools": null, + "metadata": {}, + "choices": [ + { + "index": 0, + "message": { + "content": "Mind of circuits hum, \nLearning patterns in silence— \nFuture's quiet spark.", + "role": "assistant", + "tool_calls": null, + "function_call": null + }, + "finish_reason": "stop", + "logprobs": null + } + ], + "response_format": null + } + post: + operationId: updateChatCompletion + tags: + - Chat + summary: > + Modify a stored chat completion. Only Chat Completions that have been + + created with the `store` parameter set to `true` can be modified. + Currently, + + the only supported modification is to update the `metadata` field. + parameters: + - in: path + name: completion_id + required: true + schema: + type: string + description: The ID of the chat completion to update. + requestBody: + required: true + content: + application/json: + schema: + type: object + required: + - metadata + properties: + metadata: + $ref: "#/components/schemas/Metadata" + responses: + "200": + description: A chat completion + content: + application/json: + schema: + $ref: "#/components/schemas/CreateChatCompletionResponse" + x-oaiMeta: + name: Update chat completion + group: chat + returns: The [ChatCompletion](/docs/api-reference/chat/object) object matching + the specified ID. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/chat/completions/chat_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{"metadata": {"foo": "bar"}}' + python: > + from openai import OpenAI + + client = OpenAI() + + + completions = client.chat.completions.list() + + first_id = completions[0].id + + updated_completion = + client.chat.completions.update(completion_id=first_id, + request_body={"metadata": {"foo": "bar"}}) + + print(updated_completion) + response: > + { + "object": "chat.completion", + "id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2", + "model": "gpt-4o-2024-08-06", + "created": 1738960610, + "request_id": "req_ded8ab984ec4bf840f37566c1011c417", + "tool_choice": null, + "usage": { + "total_tokens": 31, + "completion_tokens": 18, + "prompt_tokens": 13 + }, + "seed": 4944116822809979520, + "top_p": 1.0, + "temperature": 1.0, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "system_fingerprint": "fp_50cad350e4", + "input_user": null, + "service_tier": "default", + "tools": null, + "metadata": { + "foo": "bar" + }, + "choices": [ + { + "index": 0, + "message": { + "content": "Mind of circuits hum, \nLearning patterns in silence— \nFuture's quiet spark.", + "role": "assistant", + "tool_calls": null, + "function_call": null + }, + "finish_reason": "stop", + "logprobs": null + } + ], + "response_format": null + } + delete: + operationId: deleteChatCompletion + tags: + - Chat + summary: | + Delete a stored chat completion. Only Chat Completions that have been + created with the `store` parameter set to `true` can be deleted. + parameters: + - in: path + name: completion_id + required: true + schema: + type: string + description: The ID of the chat completion to delete. + responses: + "200": + description: The chat completion was deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ChatCompletionDeleted" + x-oaiMeta: + name: Delete chat completion + group: chat + returns: A deletion confirmation object. + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/chat/completions/chat_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: > + from openai import OpenAI + + client = OpenAI() + + + completions = client.chat.completions.list() + + first_id = completions[0].id + + delete_response = + client.chat.completions.delete(completion_id=first_id) + + print(delete_response) + response: | + { + "object": "chat.completion.deleted", + "id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2", + "deleted": true + } + /chat/completions/{completion_id}/messages: + get: + operationId: getChatCompletionMessages + tags: + - Chat + summary: | + Get the messages in a stored chat completion. Only Chat Completions that + have been created with the `store` parameter set to `true` will be + returned. + parameters: + - in: path + name: completion_id + required: true + schema: + type: string + description: The ID of the chat completion to retrieve messages from. + - name: after + in: query + description: Identifier for the last message from the previous pagination request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of messages to retrieve. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: Sort order for messages by timestamp. Use `asc` for ascending order + or `desc` for descending order. Defaults to `asc`. + required: false + schema: + type: string + enum: + - asc + - desc + default: asc + responses: + "200": + description: A list of messages + content: + application/json: + schema: + $ref: "#/components/schemas/ChatCompletionMessageList" + x-oaiMeta: + name: Get chat messages + group: chat + returns: A list of [messages](/docs/api-reference/chat/message-list) for the + specified chat completion. + examples: + request: + curl: > + curl + https://api.openai.com/v1/chat/completions/chat_abc123/messages \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: > + from openai import OpenAI + + client = OpenAI() + + + completions = client.chat.completions.list() + + first_id = completions[0].id + + first_completion = + client.chat.completions.retrieve(completion_id=first_id) + + messages = + client.chat.completions.messages.list(completion_id=first_id) + + print(messages) + response: | + { + "object": "list", + "data": [ + { + "id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0", + "role": "user", + "content": "write a haiku about ai", + "name": null, + "content_parts": null + } + ], + "first_id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0", + "last_id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0", + "has_more": false + } + /completions: + post: + operationId: createCompletion + tags: + - Completions + summary: Creates a completion for the provided prompt and parameters. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateCompletionRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/CreateCompletionResponse" + x-oaiMeta: + name: Create completion + group: completions + returns: > + Returns a [completion](/docs/api-reference/completions/object) object, + or a sequence of completion objects if the request is streamed. + legacy: true + examples: + - title: No streaming + request: + curl: | + curl https://api.openai.com/v1/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "VAR_completion_model_id", + "prompt": "Say this is a test", + "max_tokens": 7, + "temperature": 0 + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.completions.create( + model="VAR_completion_model_id", + prompt="Say this is a test", + max_tokens=7, + temperature=0 + ) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const completion = await openai.completions.create({ + model: "VAR_completion_model_id", + prompt: "Say this is a test.", + max_tokens: 7, + temperature: 0, + }); + + console.log(completion); + } + main(); + response: | + { + "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7", + "object": "text_completion", + "created": 1589478378, + "model": "VAR_completion_model_id", + "system_fingerprint": "fp_44709d6fcb", + "choices": [ + { + "text": "\n\nThis is indeed a test", + "index": 0, + "logprobs": null, + "finish_reason": "length" + } + ], + "usage": { + "prompt_tokens": 5, + "completion_tokens": 7, + "total_tokens": 12 + } + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/completions \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "VAR_completion_model_id", + "prompt": "Say this is a test", + "max_tokens": 7, + "temperature": 0, + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + for chunk in client.completions.create( + model="VAR_completion_model_id", + prompt="Say this is a test", + max_tokens=7, + temperature=0, + stream=True + ): + print(chunk.choices[0].text) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const stream = await openai.completions.create({ + model: "VAR_completion_model_id", + prompt: "Say this is a test.", + stream: true, + }); + + for await (const chunk of stream) { + console.log(chunk.choices[0].text) + } + } + main(); + response: | + { + "id": "cmpl-7iA7iJjj8V2zOkCGvWF2hAkDWBQZe", + "object": "text_completion", + "created": 1690759702, + "choices": [ + { + "text": "This", + "index": 0, + "logprobs": null, + "finish_reason": null + } + ], + "model": "gpt-3.5-turbo-instruct" + "system_fingerprint": "fp_44709d6fcb", + } + /containers: + get: + summary: List Containers + description: Lists containers. + operationId: ListContainers + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + responses: + "200": + description: Success + content: + application/json: + schema: + $ref: "#/components/schemas/ContainerListResource" + x-oaiMeta: + name: List containers + group: containers + returns: a list of [container](/docs/api-reference/containers/object) objects. + path: get + examples: + request: + curl: | + curl https://api.openai.com/v1/containers \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: > + { + "object": "list", + "data": [ + { + "id": "cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863", + "object": "container", + "created_at": 1747844794, + "status": "running", + "expires_after": { + "anchor": "last_active_at", + "minutes": 20 + }, + "last_active_at": 1747844794, + "name": "My Container" + } + ], + "first_id": "container_123", + "last_id": "container_123", + "has_more": false + } + post: + summary: Create Container + description: Creates a container. + operationId: CreateContainer + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: "#/components/schemas/CreateContainerBody" + responses: + "200": + description: Success + content: + application/json: + schema: + $ref: "#/components/schemas/ContainerResource" + x-oaiMeta: + name: Create container + group: containers + returns: The created [container](/docs/api-reference/containers/object) object. + path: post + examples: + request: + curl: | + curl https://api.openai.com/v1/containers \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "name": "My Container" + }' + response: | + { + "id": "cntr_682e30645a488191b6363a0cbefc0f0a025ec61b66250591", + "object": "container", + "created_at": 1747857508, + "status": "running", + "expires_after": { + "anchor": "last_active_at", + "minutes": 20 + }, + "last_active_at": 1747857508, + "name": "My Container" + } + /containers/{container_id}: + get: + summary: Retrieve Container + description: Retrieves a container. + operationId: RetrieveContainer + parameters: + - name: container_id + in: path + required: true + schema: + type: string + responses: + "200": + description: Success + content: + application/json: + schema: + $ref: "#/components/schemas/ContainerResource" + x-oaiMeta: + name: Retrieve container + group: containers + returns: The [container](/docs/api-reference/containers/object) object. + path: get + examples: + request: + curl: | + curl https://api.openai.com/v1/containers/cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863 \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: | + { + "id": "cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863", + "object": "container", + "created_at": 1747844794, + "status": "running", + "expires_after": { + "anchor": "last_active_at", + "minutes": 20 + }, + "last_active_at": 1747844794, + "name": "My Container" + } + delete: + operationId: DeleteContainer + summary: Delete Container + description: Delete a container. + parameters: + - name: container_id + in: path + description: The ID of the container to delete. + required: true + schema: + type: string + responses: + "200": + description: OK + x-oaiMeta: + name: Delete a container + group: containers + returns: Deletion Status + path: delete + examples: + request: + curl: | + curl -X DELETE https://api.openai.com/v1/containers/cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863 \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: | + { + "id": "cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863", + "object": "container.deleted", + "deleted": true + } + /containers/{container_id}/files: + post: + summary: > + Create a Container File + + + You can send either a multipart/form-data request with the raw file + content, or a JSON request with a file ID. + description: | + Creates a container file. + operationId: CreateContainerFile + parameters: + - name: container_id + in: path + required: true + schema: + type: string + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateContainerFileBody" + responses: + "200": + description: Success + content: + application/json: + schema: + $ref: "#/components/schemas/ContainerFileResource" + x-oaiMeta: + name: Create container file + group: containers + returns: The created [container + file](/docs/api-reference/container-files/object) object. + path: post + examples: + request: + curl: | + curl https://api.openai.com/v1/containers/cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -F file="@example.txt" + response: > + { + "id": "cfile_682e0e8a43c88191a7978f477a09bdf5", + "object": "container.file", + "created_at": 1747848842, + "bytes": 880, + "container_id": "cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04", + "path": "/mnt/data/88e12fa445d32636f190a0b33daed6cb-tsconfig.json", + "source": "user" + } + get: + summary: List Container files + description: Lists container files. + operationId: ListContainerFiles + parameters: + - name: container_id + in: path + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + responses: + "200": + description: Success + content: + application/json: + schema: + $ref: "#/components/schemas/ContainerFileListResource" + x-oaiMeta: + name: List container files + group: containers + returns: a list of [container file](/docs/api-reference/container-files/object) + objects. + path: get + examples: + request: + curl: | + curl https://api.openai.com/v1/containers/cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: > + { + "object": "list", + "data": [ + { + "id": "cfile_682e0e8a43c88191a7978f477a09bdf5", + "object": "container.file", + "created_at": 1747848842, + "bytes": 880, + "container_id": "cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04", + "path": "/mnt/data/88e12fa445d32636f190a0b33daed6cb-tsconfig.json", + "source": "user" + } + ], + "first_id": "cfile_682e0e8a43c88191a7978f477a09bdf5", + "has_more": false, + "last_id": "cfile_682e0e8a43c88191a7978f477a09bdf5" + } + /containers/{container_id}/files/{file_id}: + get: + summary: Retrieve Container File + description: Retrieves a container file. + operationId: RetrieveContainerFile + parameters: + - name: container_id + in: path + required: true + schema: + type: string + - name: file_id + in: path + required: true + schema: + type: string + responses: + "200": + description: Success + content: + application/json: + schema: + $ref: "#/components/schemas/ContainerFileResource" + x-oaiMeta: + name: Retrieve container file + group: containers + returns: The [container file](/docs/api-reference/container-files/object) + object. + path: get + examples: + request: + curl: > + curl + https://api.openai.com/v1/containers/container_123/files/file_456 + \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: > + { + "id": "cfile_682e0e8a43c88191a7978f477a09bdf5", + "object": "container.file", + "created_at": 1747848842, + "bytes": 880, + "container_id": "cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04", + "path": "/mnt/data/88e12fa445d32636f190a0b33daed6cb-tsconfig.json", + "source": "user" + } + delete: + operationId: DeleteContainerFile + summary: Delete Container File + description: Delete a container file. + parameters: + - name: container_id + in: path + required: true + schema: + type: string + - name: file_id + in: path + required: true + schema: + type: string + responses: + "200": + description: OK + x-oaiMeta: + name: Delete a container file + group: containers + returns: Deletion Status + path: delete + examples: + request: + curl: | + curl -X DELETE https://api.openai.com/v1/containers/cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863/files/cfile_682e0e8a43c88191a7978f477a09bdf5 \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: | + { + "id": "cfile_682e0e8a43c88191a7978f477a09bdf5", + "object": "container.file.deleted", + "deleted": true + } + /containers/{container_id}/files/{file_id}/content: + get: + summary: Retrieve Container File Content + description: Retrieves a container file content. + operationId: RetrieveContainerFileContent + parameters: + - name: container_id + in: path + required: true + schema: + type: string + - name: file_id + in: path + required: true + schema: + type: string + responses: + "200": + description: Success + x-oaiMeta: + name: Retrieve container file content + group: containers + returns: The contents of the container file. + path: get + examples: + request: + curl: | + curl https://api.openai.com/v1/containers/container_123/files/cfile_456/content \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: | + + /embeddings: + post: + operationId: createEmbedding + tags: + - Embeddings + summary: Creates an embedding vector representing the input text. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateEmbeddingRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/CreateEmbeddingResponse" + x-oaiMeta: + name: Create embeddings + group: embeddings + returns: A list of [embedding](/docs/api-reference/embeddings/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/embeddings \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "input": "The food was delicious and the waiter...", + "model": "text-embedding-ada-002", + "encoding_format": "float" + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.embeddings.create( + model="text-embedding-ada-002", + input="The food was delicious and the waiter...", + encoding_format="float" + ) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const embedding = await openai.embeddings.create({ + model: "text-embedding-ada-002", + input: "The quick brown fox jumped over the lazy dog", + encoding_format: "float", + }); + + console.log(embedding); + } + + main(); + csharp: > + using System; + + + using OpenAI.Embeddings; + + + EmbeddingClient client = new( + model: "text-embedding-3-small", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + OpenAIEmbedding embedding = client.GenerateEmbedding(input: "The + quick brown fox jumped over the lazy dog"); + + ReadOnlyMemory vector = embedding.ToFloats(); + + + for (int i = 0; i < vector.Length; i++) + + { + Console.WriteLine($" [{i,4}] = {vector.Span[i]}"); + } + response: | + { + "object": "list", + "data": [ + { + "object": "embedding", + "embedding": [ + 0.0023064255, + -0.009327292, + .... (1536 floats total for ada-002) + -0.0028842222, + ], + "index": 0 + } + ], + "model": "text-embedding-ada-002", + "usage": { + "prompt_tokens": 8, + "total_tokens": 8 + } + } + /evals: + get: + operationId: listEvals + tags: + - Evals + summary: | + List evaluations for a project. + parameters: + - name: after + in: query + description: Identifier for the last eval from the previous pagination request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of evals to retrieve. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: Sort order for evals by timestamp. Use `asc` for ascending order or + `desc` for descending order. + required: false + schema: + type: string + enum: + - asc + - desc + default: asc + - name: order_by + in: query + description: > + Evals can be ordered by creation time or last updated time. Use + + `created_at` for creation time or `updated_at` for last updated + time. + required: false + schema: + type: string + enum: + - created_at + - updated_at + default: created_at + responses: + "200": + description: A list of evals + content: + application/json: + schema: + $ref: "#/components/schemas/EvalList" + x-oaiMeta: + name: List evals + group: evals + returns: A list of [evals](/docs/api-reference/evals/object) matching the + specified filters. + path: list + examples: + request: + curl: | + curl https://api.openai.com/v1/evals?limit=1 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: | + from openai import OpenAI + client = OpenAI() + + evals = client.evals.list(limit=1) + print(evals) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const evals = await openai.evals.list({ limit: 1 }); + console.log(evals); + response: > + { + "object": "list", + "data": [ + { + "id": "eval_67abd54d9b0081909a86353f6fb9317a", + "object": "eval", + "data_source_config": { + "type": "stored_completions", + "metadata": { + "usecase": "push_notifications_summarizer" + }, + "schema": { + "type": "object", + "properties": { + "item": { + "type": "object" + }, + "sample": { + "type": "object" + } + }, + "required": [ + "item", + "sample" + ] + } + }, + "testing_criteria": [ + { + "name": "Push Notification Summary Grader", + "id": "Push Notification Summary Grader-9b876f24-4762-4be9-aff4-db7a9b31c673", + "type": "label_model", + "model": "o3-mini", + "input": [ + { + "type": "message", + "role": "developer", + "content": { + "type": "input_text", + "text": "\nLabel the following push notification summary as either correct or incorrect.\nThe push notification and the summary will be provided below.\nA good push notificiation summary is concise and snappy.\nIf it is good, then label it as correct, if not, then incorrect.\n" + } + }, + { + "type": "message", + "role": "user", + "content": { + "type": "input_text", + "text": "\nPush notifications: {{item.input}}\nSummary: {{sample.output_text}}\n" + } + } + ], + "passing_labels": [ + "correct" + ], + "labels": [ + "correct", + "incorrect" + ], + "sampling_params": null + } + ], + "name": "Push Notification Summary Grader", + "created_at": 1739314509, + "metadata": { + "description": "A stored completions eval for push notification summaries" + } + } + ], + "first_id": "eval_67abd54d9b0081909a86353f6fb9317a", + "last_id": "eval_67aa884cf6688190b58f657d4441c8b7", + "has_more": true + } + post: + operationId: createEval + tags: + - Evals + summary: > + Create the structure of an evaluation that can be used to test a model's + performance. + + An evaluation is a set of testing criteria and the config for a data + source, which dictates the schema of the data used in the evaluation. + After creating an evaluation, you can run it on different models and + model parameters. We support several types of graders and datasources. + + For more information, see the [Evals guide](/docs/guides/evals). + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateEvalRequest" + responses: + "201": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Eval" + x-oaiMeta: + name: Create eval + group: evals + returns: The created [Eval](/docs/api-reference/evals/object) object. + path: post + examples: + request: + curl: > + curl https://api.openai.com/v1/evals \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "name": "Sentiment", + "data_source_config": { + "type": "stored_completions", + "metadata": { + "usecase": "chatbot" + } + }, + "testing_criteria": [ + { + "type": "label_model", + "model": "o3-mini", + "input": [ + { + "role": "developer", + "content": "Classify the sentiment of the following statement as one of 'positive', 'neutral', or 'negative'" + }, + { + "role": "user", + "content": "Statement: {{item.input}}" + } + ], + "passing_labels": [ + "positive" + ], + "labels": [ + "positive", + "neutral", + "negative" + ], + "name": "Example label grader" + } + ] + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + eval_obj = client.evals.create( + name="Sentiment", + data_source_config={ + "type": "stored_completions", + "metadata": {"usecase": "chatbot"} + }, + testing_criteria=[ + { + "type": "label_model", + "model": "o3-mini", + "input": [ + {"role": "developer", "content": "Classify the sentiment of the following statement as one of 'positive', 'neutral', or 'negative'"}, + {"role": "user", "content": "Statement: {{item.input}}"} + ], + "passing_labels": ["positive"], + "labels": ["positive", "neutral", "negative"], + "name": "Example label grader" + } + ] + ) + + print(eval_obj) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const evalObj = await openai.evals.create({ + name: "Sentiment", + data_source_config: { + type: "stored_completions", + metadata: { usecase: "chatbot" } + }, + testing_criteria: [ + { + type: "label_model", + model: "o3-mini", + input: [ + { role: "developer", content: "Classify the sentiment of the following statement as one of 'positive', 'neutral', or 'negative'" }, + { role: "user", content: "Statement: {{item.input}}" } + ], + passing_labels: ["positive"], + labels: ["positive", "neutral", "negative"], + name: "Example label grader" + } + ] + }); + + console.log(evalObj); + response: > + { + "object": "eval", + "id": "eval_67b7fa9a81a88190ab4aa417e397ea21", + "data_source_config": { + "type": "stored_completions", + "metadata": { + "usecase": "chatbot" + }, + "schema": { + "type": "object", + "properties": { + "item": { + "type": "object" + }, + "sample": { + "type": "object" + } + }, + "required": [ + "item", + "sample" + ] + }, + "testing_criteria": [ + { + "name": "Example label grader", + "type": "label_model", + "model": "o3-mini", + "input": [ + { + "type": "message", + "role": "developer", + "content": { + "type": "input_text", + "text": "Classify the sentiment of the following statement as one of positive, neutral, or negative" + } + }, + { + "type": "message", + "role": "user", + "content": { + "type": "input_text", + "text": "Statement: {{item.input}}" + } + } + ], + "passing_labels": [ + "positive" + ], + "labels": [ + "positive", + "neutral", + "negative" + ] + } + ], + "name": "Sentiment", + "created_at": 1740110490, + "metadata": { + "description": "An eval for sentiment analysis" + } + } + /evals/{eval_id}: + get: + operationId: getEval + tags: + - Evals + summary: | + Get an evaluation by ID. + parameters: + - name: eval_id + in: path + required: true + schema: + type: string + description: The ID of the evaluation to retrieve. + responses: + "200": + description: The evaluation + content: + application/json: + schema: + $ref: "#/components/schemas/Eval" + x-oaiMeta: + name: Get an eval + group: evals + returns: The [Eval](/docs/api-reference/evals/object) object matching the + specified ID. + path: get + examples: + request: + curl: | + curl https://api.openai.com/v1/evals/eval_67abd54d9b0081909a86353f6fb9317a \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: > + from openai import OpenAI + + client = OpenAI() + + + eval_obj = + client.evals.retrieve("eval_67abd54d9b0081909a86353f6fb9317a") + + print(eval_obj) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const evalObj = await + openai.evals.retrieve("eval_67abd54d9b0081909a86353f6fb9317a"); + + console.log(evalObj); + response: | + { + "object": "eval", + "id": "eval_67abd54d9b0081909a86353f6fb9317a", + "data_source_config": { + "type": "custom", + "schema": { + "type": "object", + "properties": { + "item": { + "type": "object", + "properties": { + "input": { + "type": "string" + }, + "ground_truth": { + "type": "string" + } + }, + "required": [ + "input", + "ground_truth" + ] + } + }, + "required": [ + "item" + ] + } + }, + "testing_criteria": [ + { + "name": "String check", + "id": "String check-2eaf2d8d-d649-4335-8148-9535a7ca73c2", + "type": "string_check", + "input": "{{item.input}}", + "reference": "{{item.ground_truth}}", + "operation": "eq" + } + ], + "name": "External Data Eval", + "created_at": 1739314509, + "metadata": {}, + } + post: + operationId: updateEval + tags: + - Evals + summary: | + Update certain properties of an evaluation. + parameters: + - name: eval_id + in: path + required: true + schema: + type: string + description: The ID of the evaluation to update. + requestBody: + description: Request to update an evaluation + required: true + content: + application/json: + schema: + type: object + properties: + name: + type: string + description: Rename the evaluation. + metadata: + $ref: "#/components/schemas/Metadata" + responses: + "200": + description: The updated evaluation + content: + application/json: + schema: + $ref: "#/components/schemas/Eval" + x-oaiMeta: + name: Update an eval + group: evals + returns: The [Eval](/docs/api-reference/evals/object) object matching the + updated version. + path: update + examples: + request: + curl: | + curl https://api.openai.com/v1/evals/eval_67abd54d9b0081909a86353f6fb9317a \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{"name": "Updated Eval", "metadata": {"description": "Updated description"}}' + python: | + from openai import OpenAI + client = OpenAI() + + updated_eval = client.evals.update( + "eval_67abd54d9b0081909a86353f6fb9317a", + name="Updated Eval", + metadata={"description": "Updated description"} + ) + print(updated_eval) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const updatedEval = await openai.evals.update( + "eval_67abd54d9b0081909a86353f6fb9317a", + { + name: "Updated Eval", + metadata: { description: "Updated description" } + } + ); + console.log(updatedEval); + response: | + { + "object": "eval", + "id": "eval_67abd54d9b0081909a86353f6fb9317a", + "data_source_config": { + "type": "custom", + "schema": { + "type": "object", + "properties": { + "item": { + "type": "object", + "properties": { + "input": { + "type": "string" + }, + "ground_truth": { + "type": "string" + } + }, + "required": [ + "input", + "ground_truth" + ] + } + }, + "required": [ + "item" + ] + } + }, + "testing_criteria": [ + { + "name": "String check", + "id": "String check-2eaf2d8d-d649-4335-8148-9535a7ca73c2", + "type": "string_check", + "input": "{{item.input}}", + "reference": "{{item.ground_truth}}", + "operation": "eq" + } + ], + "name": "Updated Eval", + "created_at": 1739314509, + "metadata": {"description": "Updated description"}, + } + delete: + operationId: deleteEval + tags: + - Evals + summary: | + Delete an evaluation. + parameters: + - name: eval_id + in: path + required: true + schema: + type: string + description: The ID of the evaluation to delete. + responses: + "200": + description: Successfully deleted the evaluation. + content: + application/json: + schema: + type: object + properties: + object: + type: string + example: eval.deleted + deleted: + type: boolean + example: true + eval_id: + type: string + example: eval_abc123 + required: + - object + - deleted + - eval_id + "404": + description: Evaluation not found. + content: + application/json: + schema: + $ref: "#/components/schemas/Error" + x-oaiMeta: + name: Delete an eval + group: evals + returns: A deletion confirmation object. + examples: + request: + curl: | + curl https://api.openai.com/v1/evals/eval_abc123 \ + -X DELETE \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + deleted = client.evals.delete("eval_abc123") + print(deleted) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const deleted = await openai.evals.delete("eval_abc123"); + console.log(deleted); + response: | + { + "object": "eval.deleted", + "deleted": true, + "eval_id": "eval_abc123" + } + /evals/{eval_id}/runs: + get: + operationId: getEvalRuns + tags: + - Evals + summary: | + Get a list of runs for an evaluation. + parameters: + - name: eval_id + in: path + required: true + schema: + type: string + description: The ID of the evaluation to retrieve runs for. + - name: after + in: query + description: Identifier for the last run from the previous pagination request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of runs to retrieve. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: Sort order for runs by timestamp. Use `asc` for ascending order or + `desc` for descending order. Defaults to `asc`. + required: false + schema: + type: string + enum: + - asc + - desc + default: asc + - name: status + in: query + description: Filter runs by status. One of `queued` | `in_progress` | `failed` | + `completed` | `canceled`. + required: false + schema: + type: string + enum: + - queued + - in_progress + - completed + - canceled + - failed + responses: + "200": + description: A list of runs for the evaluation + content: + application/json: + schema: + $ref: "#/components/schemas/EvalRunList" + x-oaiMeta: + name: Get eval runs + group: evals + returns: A list of [EvalRun](/docs/api-reference/evals/run-object) objects + matching the specified ID. + path: get-runs + examples: + request: + curl: | + curl https://api.openai.com/v1/evals/egroup_67abd54d9b0081909a86353f6fb9317a/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: > + from openai import OpenAI + + client = OpenAI() + + + runs = + client.evals.runs.list("egroup_67abd54d9b0081909a86353f6fb9317a") + + print(runs) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const runs = await + openai.evals.runs.list("egroup_67abd54d9b0081909a86353f6fb9317a"); + + console.log(runs); + response: > + { + "object": "list", + "data": [ + { + "object": "eval.run", + "id": "evalrun_67e0c7d31560819090d60c0780591042", + "eval_id": "eval_67e0c726d560819083f19a957c4c640b", + "report_url": "https://platform.openai.com/evaluations/eval_67e0c726d560819083f19a957c4c640b", + "status": "completed", + "model": "o3-mini", + "name": "bulk_with_negative_examples_o3-mini", + "created_at": 1742784467, + "result_counts": { + "total": 1, + "errored": 0, + "failed": 0, + "passed": 1 + }, + "per_model_usage": [ + { + "model_name": "o3-mini", + "invocation_count": 1, + "prompt_tokens": 563, + "completion_tokens": 874, + "total_tokens": 1437, + "cached_tokens": 0 + } + ], + "per_testing_criteria_results": [ + { + "testing_criteria": "Push Notification Summary Grader-1808cd0b-eeec-4e0b-a519-337e79f4f5d1", + "passed": 1, + "failed": 0 + } + ], + "data_source": { + "type": "completions", + "source": { + "type": "file_content", + "content": [ + { + "item": { + "notifications": "\n- New message from Sarah: \"Can you call me later?\"\n- Your package has been delivered!\n- Flash sale: 20% off electronics for the next 2 hours!\n" + } + } + ] + }, + "input_messages": { + "type": "template", + "template": [ + { + "type": "message", + "role": "developer", + "content": { + "type": "input_text", + "text": "\n\n\n\nYou are a helpful assistant that takes in an array of push notifications and returns a collapsed summary of them.\nThe push notification will be provided as follows:\n\n...notificationlist...\n\n\nYou should return just the summary and nothing else.\n\n\nYou should return a summary that is concise and snappy.\n\n\nHere is an example of a good summary:\n\n- Traffic alert: Accident reported on Main Street.- Package out for delivery: Expected by 5 PM.- New friend suggestion: Connect with Emma.\n\n\nTraffic alert, package expected by 5pm, suggestion for new friend (Emily).\n\n\n\nHere is an example of a bad summary:\n\n- Traffic alert: Accident reported on Main Street.- Package out for delivery: Expected by 5 PM.- New friend suggestion: Connect with Emma.\n\n\nTraffic alert reported on main street. You have a package that will arrive by 5pm, Emily is a new friend suggested for you.\n\n" + } + }, + { + "type": "message", + "role": "user", + "content": { + "type": "input_text", + "text": "{{item.notifications}}" + } + } + ] + }, + "model": "o3-mini", + "sampling_params": null + }, + "error": null, + "metadata": {} + } + ], + "first_id": "evalrun_67e0c7d31560819090d60c0780591042", + "last_id": "evalrun_67e0c7d31560819090d60c0780591042", + "has_more": true + } + post: + operationId: createEvalRun + tags: + - Evals + summary: > + Kicks off a new run for a given evaluation, specifying the data source, + and what model configuration to use to test. The datasource will be + validated against the schema specified in the config of the evaluation. + parameters: + - in: path + name: eval_id + required: true + schema: + type: string + description: The ID of the evaluation to create a run for. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateEvalRunRequest" + responses: + "201": + description: Successfully created a run for the evaluation + content: + application/json: + schema: + $ref: "#/components/schemas/EvalRun" + "400": + description: Bad request (for example, missing eval object) + content: + application/json: + schema: + $ref: "#/components/schemas/Error" + x-oaiMeta: + name: Create eval run + group: evals + returns: The [EvalRun](/docs/api-reference/evals/run-object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/evals/eval_67e579652b548190aaa83ada4b125f47/runs \ + -X POST \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{"name":"gpt-4o-mini","data_source":{"type":"completions","input_messages":{"type":"template","template":[{"role":"developer","content":"Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\n\n# Steps\n\n1. Analyze the content of the news headline to understand its primary focus.\n2. Extract the subject matter, identifying any key indicators or keywords.\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\n4. Ensure only one category is selected per headline.\n\n# Output Format\n\nRespond with the chosen category as a single word. For instance: \"Technology\", \"Markets\", \"World\", \"Business\", or \"Sports\".\n\n# Examples\n\n**Input**: \"Apple Unveils New iPhone Model, Featuring Advanced AI Features\" \n**Output**: \"Technology\"\n\n**Input**: \"Global Stocks Mixed as Investors Await Central Bank Decisions\" \n**Output**: \"Markets\"\n\n**Input**: \"War in Ukraine: Latest Updates on Negotiation Status\" \n**Output**: \"World\"\n\n**Input**: \"Microsoft in Talks to Acquire Gaming Company for $2 Billion\" \n**Output**: \"Business\"\n\n**Input**: \"Manchester United Secures Win in Premier League Football Match\" \n**Output**: \"Sports\" \n\n# Notes\n\n- If the headline appears to fit into more than one category, choose the most dominant theme.\n- Keywords or phrases such as \"stocks\", \"company acquisition\", \"match\", or technological brands can be good indicators for classification.\n"} , {"role":"user","content":"{{item.input}}"}]} ,"sampling_params":{"temperature":1,"max_completions_tokens":2048,"top_p":1,"seed":42},"model":"gpt-4o-mini","source":{"type":"file_content","content":[{"item":{"input":"Tech Company Launches Advanced Artificial Intelligence Platform","ground_truth":"Technology"}}]}}' + python: > + from openai import OpenAI + + client = OpenAI() + + + run = client.evals.runs.create( + "eval_67e579652b548190aaa83ada4b125f47", + name="gpt-4o-mini", + data_source={ + "type": "completions", + "input_messages": { + "type": "template", + "template": [ + { + "role": "developer", + "content": "Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\n\n# Steps\n\n1. Analyze the content of the news headline to understand its primary focus.\n2. Extract the subject matter, identifying any key indicators or keywords.\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\n4. Ensure only one category is selected per headline.\n\n# Output Format\n\nRespond with the chosen category as a single word. For instance: \"Technology\", \"Markets\", \"World\", \"Business\", or \"Sports\".\n\n# Examples\n\n**Input**: \"Apple Unveils New iPhone Model, Featuring Advanced AI Features\" \n**Output**: \"Technology\"\n\n**Input**: \"Global Stocks Mixed as Investors Await Central Bank Decisions\" \n**Output**: \"Markets\"\n\n**Input**: \"War in Ukraine: Latest Updates on Negotiation Status\" \n**Output**: \"World\"\n\n**Input**: \"Microsoft in Talks to Acquire Gaming Company for $2 Billion\" \n**Output**: \"Business\"\n\n**Input**: \"Manchester United Secures Win in Premier League Football Match\" \n**Output**: \"Sports\" \n\n# Notes\n\n- If the headline appears to fit into more than one category, choose the most dominant theme.\n- Keywords or phrases such as \"stocks\", \"company acquisition\", \"match\", or technological brands can be good indicators for classification.\n" + }, + { + "role": "user", + "content": "{{item.input}}" + } + ] + }, + "sampling_params": { + "temperature": 1, + "max_completions_tokens": 2048, + "top_p": 1, + "seed": 42 + }, + "model": "gpt-4o-mini", + "source": { + "type": "file_content", + "content": [ + { + "item": { + "input": "Tech Company Launches Advanced Artificial Intelligence Platform", + "ground_truth": "Technology" + } + } + ] + } + } + ) + + print(run) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const run = await openai.evals.runs.create( + "eval_67e579652b548190aaa83ada4b125f47", + { + name: "gpt-4o-mini", + data_source: { + type: "completions", + input_messages: { + type: "template", + template: [ + { + role: "developer", + content: "Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\n\n# Steps\n\n1. Analyze the content of the news headline to understand its primary focus.\n2. Extract the subject matter, identifying any key indicators or keywords.\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\n4. Ensure only one category is selected per headline.\n\n# Output Format\n\nRespond with the chosen category as a single word. For instance: \"Technology\", \"Markets\", \"World\", \"Business\", or \"Sports\".\n\n# Examples\n\n**Input**: \"Apple Unveils New iPhone Model, Featuring Advanced AI Features\" \n**Output**: \"Technology\"\n\n**Input**: \"Global Stocks Mixed as Investors Await Central Bank Decisions\" \n**Output**: \"Markets\"\n\n**Input**: \"War in Ukraine: Latest Updates on Negotiation Status\" \n**Output**: \"World\"\n\n**Input**: \"Microsoft in Talks to Acquire Gaming Company for $2 Billion\" \n**Output**: \"Business\"\n\n**Input**: \"Manchester United Secures Win in Premier League Football Match\" \n**Output**: \"Sports\" \n\n# Notes\n\n- If the headline appears to fit into more than one category, choose the most dominant theme.\n- Keywords or phrases such as \"stocks\", \"company acquisition\", \"match\", or technological brands can be good indicators for classification.\n" + }, + { + role: "user", + content: "{{item.input}}" + } + ] + }, + sampling_params: { + temperature: 1, + max_completions_tokens: 2048, + top_p: 1, + seed: 42 + }, + model: "gpt-4o-mini", + source: { + type: "file_content", + content: [ + { + item: { + input: "Tech Company Launches Advanced Artificial Intelligence Platform", + ground_truth: "Technology" + } + } + ] + } + } + } + ); + + console.log(run); + response: > + { + "object": "eval.run", + "id": "evalrun_67e57965b480819094274e3a32235e4c", + "eval_id": "eval_67e579652b548190aaa83ada4b125f47", + "report_url": "https://platform.openai.com/evaluations/eval_67e579652b548190aaa83ada4b125f47&run_id=evalrun_67e57965b480819094274e3a32235e4c", + "status": "queued", + "model": "gpt-4o-mini", + "name": "gpt-4o-mini", + "created_at": 1743092069, + "result_counts": { + "total": 0, + "errored": 0, + "failed": 0, + "passed": 0 + }, + "per_model_usage": null, + "per_testing_criteria_results": null, + "data_source": { + "type": "completions", + "source": { + "type": "file_content", + "content": [ + { + "item": { + "input": "Tech Company Launches Advanced Artificial Intelligence Platform", + "ground_truth": "Technology" + } + } + ] + }, + "input_messages": { + "type": "template", + "template": [ + { + "type": "message", + "role": "developer", + "content": { + "type": "input_text", + "text": "Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\n\n# Steps\n\n1. Analyze the content of the news headline to understand its primary focus.\n2. Extract the subject matter, identifying any key indicators or keywords.\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\n4. Ensure only one category is selected per headline.\n\n# Output Format\n\nRespond with the chosen category as a single word. For instance: \"Technology\", \"Markets\", \"World\", \"Business\", or \"Sports\".\n\n# Examples\n\n**Input**: \"Apple Unveils New iPhone Model, Featuring Advanced AI Features\" \n**Output**: \"Technology\"\n\n**Input**: \"Global Stocks Mixed as Investors Await Central Bank Decisions\" \n**Output**: \"Markets\"\n\n**Input**: \"War in Ukraine: Latest Updates on Negotiation Status\" \n**Output**: \"World\"\n\n**Input**: \"Microsoft in Talks to Acquire Gaming Company for $2 Billion\" \n**Output**: \"Business\"\n\n**Input**: \"Manchester United Secures Win in Premier League Football Match\" \n**Output**: \"Sports\" \n\n# Notes\n\n- If the headline appears to fit into more than one category, choose the most dominant theme.\n- Keywords or phrases such as \"stocks\", \"company acquisition\", \"match\", or technological brands can be good indicators for classification.\n" + } + }, + { + "type": "message", + "role": "user", + "content": { + "type": "input_text", + "text": "{{item.input}}" + } + } + ] + }, + "model": "gpt-4o-mini", + "sampling_params": { + "seed": 42, + "temperature": 1.0, + "top_p": 1.0, + "max_completions_tokens": 2048 + } + }, + "error": null, + "metadata": {} + } + /evals/{eval_id}/runs/{run_id}: + get: + operationId: getEvalRun + tags: + - Evals + summary: | + Get an evaluation run by ID. + parameters: + - name: eval_id + in: path + required: true + schema: + type: string + description: The ID of the evaluation to retrieve runs for. + - name: run_id + in: path + required: true + schema: + type: string + description: The ID of the run to retrieve. + responses: + "200": + description: The evaluation run + content: + application/json: + schema: + $ref: "#/components/schemas/EvalRun" + x-oaiMeta: + name: Get an eval run + group: evals + returns: The [EvalRun](/docs/api-reference/evals/run-object) object matching the + specified ID. + path: get + examples: + request: + curl: | + curl https://api.openai.com/v1/evals/eval_67abd54d9b0081909a86353f6fb9317a/runs/evalrun_67abd54d60ec8190832b46859da808f7 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: | + from openai import OpenAI + client = OpenAI() + + run = client.evals.runs.retrieve( + "eval_67abd54d9b0081909a86353f6fb9317a", + "evalrun_67abd54d60ec8190832b46859da808f7" + ) + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const run = await openai.evals.runs.retrieve( + "eval_67abd54d9b0081909a86353f6fb9317a", + "evalrun_67abd54d60ec8190832b46859da808f7" + ); + console.log(run); + response: > + { + "object": "eval.run", + "id": "evalrun_67abd54d60ec8190832b46859da808f7", + "eval_id": "eval_67abd54d9b0081909a86353f6fb9317a", + "report_url": "https://platform.openai.com/evaluations/eval_67abd54d9b0081909a86353f6fb9317a?run_id=evalrun_67abd54d60ec8190832b46859da808f7", + "status": "queued", + "model": "gpt-4o-mini", + "name": "gpt-4o-mini", + "created_at": 1743092069, + "result_counts": { + "total": 0, + "errored": 0, + "failed": 0, + "passed": 0 + }, + "per_model_usage": null, + "per_testing_criteria_results": null, + "data_source": { + "type": "completions", + "source": { + "type": "file_content", + "content": [ + { + "item": { + "input": "Tech Company Launches Advanced Artificial Intelligence Platform", + "ground_truth": "Technology" + } + }, + { + "item": { + "input": "Central Bank Increases Interest Rates Amid Inflation Concerns", + "ground_truth": "Markets" + } + }, + { + "item": { + "input": "International Summit Addresses Climate Change Strategies", + "ground_truth": "World" + } + }, + { + "item": { + "input": "Major Retailer Reports Record-Breaking Holiday Sales", + "ground_truth": "Business" + } + }, + { + "item": { + "input": "National Team Qualifies for World Championship Finals", + "ground_truth": "Sports" + } + }, + { + "item": { + "input": "Stock Markets Rally After Positive Economic Data Released", + "ground_truth": "Markets" + } + }, + { + "item": { + "input": "Global Manufacturer Announces Merger with Competitor", + "ground_truth": "Business" + } + }, + { + "item": { + "input": "Breakthrough in Renewable Energy Technology Unveiled", + "ground_truth": "Technology" + } + }, + { + "item": { + "input": "World Leaders Sign Historic Climate Agreement", + "ground_truth": "World" + } + }, + { + "item": { + "input": "Professional Athlete Sets New Record in Championship Event", + "ground_truth": "Sports" + } + }, + { + "item": { + "input": "Financial Institutions Adapt to New Regulatory Requirements", + "ground_truth": "Business" + } + }, + { + "item": { + "input": "Tech Conference Showcases Advances in Artificial Intelligence", + "ground_truth": "Technology" + } + }, + { + "item": { + "input": "Global Markets Respond to Oil Price Fluctuations", + "ground_truth": "Markets" + } + }, + { + "item": { + "input": "International Cooperation Strengthened Through New Treaty", + "ground_truth": "World" + } + }, + { + "item": { + "input": "Sports League Announces Revised Schedule for Upcoming Season", + "ground_truth": "Sports" + } + } + ] + }, + "input_messages": { + "type": "template", + "template": [ + { + "type": "message", + "role": "developer", + "content": { + "type": "input_text", + "text": "Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\n\n# Steps\n\n1. Analyze the content of the news headline to understand its primary focus.\n2. Extract the subject matter, identifying any key indicators or keywords.\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\n4. Ensure only one category is selected per headline.\n\n# Output Format\n\nRespond with the chosen category as a single word. For instance: \"Technology\", \"Markets\", \"World\", \"Business\", or \"Sports\".\n\n# Examples\n\n**Input**: \"Apple Unveils New iPhone Model, Featuring Advanced AI Features\" \n**Output**: \"Technology\"\n\n**Input**: \"Global Stocks Mixed as Investors Await Central Bank Decisions\" \n**Output**: \"Markets\"\n\n**Input**: \"War in Ukraine: Latest Updates on Negotiation Status\" \n**Output**: \"World\"\n\n**Input**: \"Microsoft in Talks to Acquire Gaming Company for $2 Billion\" \n**Output**: \"Business\"\n\n**Input**: \"Manchester United Secures Win in Premier League Football Match\" \n**Output**: \"Sports\" \n\n# Notes\n\n- If the headline appears to fit into more than one category, choose the most dominant theme.\n- Keywords or phrases such as \"stocks\", \"company acquisition\", \"match\", or technological brands can be good indicators for classification.\n" + } + }, + { + "type": "message", + "role": "user", + "content": { + "type": "input_text", + "text": "{{item.input}}" + } + } + ] + }, + "model": "gpt-4o-mini", + "sampling_params": { + "seed": 42, + "temperature": 1.0, + "top_p": 1.0, + "max_completions_tokens": 2048 + } + }, + "error": null, + "metadata": {} + } + post: + operationId: cancelEvalRun + tags: + - Evals + summary: | + Cancel an ongoing evaluation run. + parameters: + - name: eval_id + in: path + required: true + schema: + type: string + description: The ID of the evaluation whose run you want to cancel. + - name: run_id + in: path + required: true + schema: + type: string + description: The ID of the run to cancel. + responses: + "200": + description: The canceled eval run object + content: + application/json: + schema: + $ref: "#/components/schemas/EvalRun" + x-oaiMeta: + name: Cancel eval run + group: evals + returns: The updated [EvalRun](/docs/api-reference/evals/run-object) object + reflecting that the run is canceled. + path: post + examples: + request: + curl: | + curl https://api.openai.com/v1/evals/eval_67abd54d9b0081909a86353f6fb9317a/runs/evalrun_67abd54d60ec8190832b46859da808f7/cancel \ + -X POST \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: | + from openai import OpenAI + client = OpenAI() + + canceled_run = client.evals.runs.cancel( + "eval_67abd54d9b0081909a86353f6fb9317a", + "evalrun_67abd54d60ec8190832b46859da808f7" + ) + print(canceled_run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const canceledRun = await openai.evals.runs.cancel( + "eval_67abd54d9b0081909a86353f6fb9317a", + "evalrun_67abd54d60ec8190832b46859da808f7" + ); + console.log(canceledRun); + response: > + { + "object": "eval.run", + "id": "evalrun_67abd54d60ec8190832b46859da808f7", + "eval_id": "eval_67abd54d9b0081909a86353f6fb9317a", + "report_url": "https://platform.openai.com/evaluations/eval_67abd54d9b0081909a86353f6fb9317a?run_id=evalrun_67abd54d60ec8190832b46859da808f7", + "status": "canceled", + "model": "gpt-4o-mini", + "name": "gpt-4o-mini", + "created_at": 1743092069, + "result_counts": { + "total": 0, + "errored": 0, + "failed": 0, + "passed": 0 + }, + "per_model_usage": null, + "per_testing_criteria_results": null, + "data_source": { + "type": "completions", + "source": { + "type": "file_content", + "content": [ + { + "item": { + "input": "Tech Company Launches Advanced Artificial Intelligence Platform", + "ground_truth": "Technology" + } + }, + { + "item": { + "input": "Central Bank Increases Interest Rates Amid Inflation Concerns", + "ground_truth": "Markets" + } + }, + { + "item": { + "input": "International Summit Addresses Climate Change Strategies", + "ground_truth": "World" + } + }, + { + "item": { + "input": "Major Retailer Reports Record-Breaking Holiday Sales", + "ground_truth": "Business" + } + }, + { + "item": { + "input": "National Team Qualifies for World Championship Finals", + "ground_truth": "Sports" + } + }, + { + "item": { + "input": "Stock Markets Rally After Positive Economic Data Released", + "ground_truth": "Markets" + } + }, + { + "item": { + "input": "Global Manufacturer Announces Merger with Competitor", + "ground_truth": "Business" + } + }, + { + "item": { + "input": "Breakthrough in Renewable Energy Technology Unveiled", + "ground_truth": "Technology" + } + }, + { + "item": { + "input": "World Leaders Sign Historic Climate Agreement", + "ground_truth": "World" + } + }, + { + "item": { + "input": "Professional Athlete Sets New Record in Championship Event", + "ground_truth": "Sports" + } + }, + { + "item": { + "input": "Financial Institutions Adapt to New Regulatory Requirements", + "ground_truth": "Business" + } + }, + { + "item": { + "input": "Tech Conference Showcases Advances in Artificial Intelligence", + "ground_truth": "Technology" + } + }, + { + "item": { + "input": "Global Markets Respond to Oil Price Fluctuations", + "ground_truth": "Markets" + } + }, + { + "item": { + "input": "International Cooperation Strengthened Through New Treaty", + "ground_truth": "World" + } + }, + { + "item": { + "input": "Sports League Announces Revised Schedule for Upcoming Season", + "ground_truth": "Sports" + } + } + ] + }, + "input_messages": { + "type": "template", + "template": [ + { + "type": "message", + "role": "developer", + "content": { + "type": "input_text", + "text": "Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\n\n# Steps\n\n1. Analyze the content of the news headline to understand its primary focus.\n2. Extract the subject matter, identifying any key indicators or keywords.\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\n4. Ensure only one category is selected per headline.\n\n# Output Format\n\nRespond with the chosen category as a single word. For instance: \"Technology\", \"Markets\", \"World\", \"Business\", or \"Sports\".\n\n# Examples\n\n**Input**: \"Apple Unveils New iPhone Model, Featuring Advanced AI Features\" \n**Output**: \"Technology\"\n\n**Input**: \"Global Stocks Mixed as Investors Await Central Bank Decisions\" \n**Output**: \"Markets\"\n\n**Input**: \"War in Ukraine: Latest Updates on Negotiation Status\" \n**Output**: \"World\"\n\n**Input**: \"Microsoft in Talks to Acquire Gaming Company for $2 Billion\" \n**Output**: \"Business\"\n\n**Input**: \"Manchester United Secures Win in Premier League Football Match\" \n**Output**: \"Sports\" \n\n# Notes\n\n- If the headline appears to fit into more than one category, choose the most dominant theme.\n- Keywords or phrases such as \"stocks\", \"company acquisition\", \"match\", or technological brands can be good indicators for classification.\n" + } + }, + { + "type": "message", + "role": "user", + "content": { + "type": "input_text", + "text": "{{item.input}}" + } + } + ] + }, + "model": "gpt-4o-mini", + "sampling_params": { + "seed": 42, + "temperature": 1.0, + "top_p": 1.0, + "max_completions_tokens": 2048 + } + }, + "error": null, + "metadata": {} + } + delete: + operationId: deleteEvalRun + tags: + - Evals + summary: | + Delete an eval run. + parameters: + - name: eval_id + in: path + required: true + schema: + type: string + description: The ID of the evaluation to delete the run from. + - name: run_id + in: path + required: true + schema: + type: string + description: The ID of the run to delete. + responses: + "200": + description: Successfully deleted the eval run + content: + application/json: + schema: + type: object + properties: + object: + type: string + example: eval.run.deleted + deleted: + type: boolean + example: true + run_id: + type: string + example: evalrun_677469f564d48190807532a852da3afb + "404": + description: Run not found + content: + application/json: + schema: + $ref: "#/components/schemas/Error" + x-oaiMeta: + name: Delete eval run + group: evals + returns: An object containing the status of the delete operation. + path: delete + examples: + request: + curl: > + curl + https://api.openai.com/v1/evals/eval_123abc/runs/evalrun_abc456 \ + -X DELETE \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: | + from openai import OpenAI + client = OpenAI() + + deleted = client.evals.runs.delete( + "eval_123abc", + "evalrun_abc456" + ) + print(deleted) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const deleted = await openai.evals.runs.delete( + "eval_123abc", + "evalrun_abc456" + ); + console.log(deleted); + response: | + { + "object": "eval.run.deleted", + "deleted": true, + "run_id": "evalrun_abc456" + } + /evals/{eval_id}/runs/{run_id}/output_items: + get: + operationId: getEvalRunOutputItems + tags: + - Evals + summary: | + Get a list of output items for an evaluation run. + parameters: + - name: eval_id + in: path + required: true + schema: + type: string + description: The ID of the evaluation to retrieve runs for. + - name: run_id + in: path + required: true + schema: + type: string + description: The ID of the run to retrieve output items for. + - name: after + in: query + description: Identifier for the last output item from the previous pagination + request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of output items to retrieve. + required: false + schema: + type: integer + default: 20 + - name: status + in: query + description: > + Filter output items by status. Use `failed` to filter by failed + output + + items or `pass` to filter by passed output items. + required: false + schema: + type: string + enum: + - fail + - pass + - name: order + in: query + description: Sort order for output items by timestamp. Use `asc` for ascending + order or `desc` for descending order. Defaults to `asc`. + required: false + schema: + type: string + enum: + - asc + - desc + default: asc + responses: + "200": + description: A list of output items for the evaluation run + content: + application/json: + schema: + $ref: "#/components/schemas/EvalRunOutputItemList" + x-oaiMeta: + name: Get eval run output items + group: evals + returns: A list of + [EvalRunOutputItem](/docs/api-reference/evals/run-output-item-object) + objects matching the specified ID. + path: get + examples: + request: + curl: | + curl https://api.openai.com/v1/evals/egroup_67abd54d9b0081909a86353f6fb9317a/runs/erun_67abd54d60ec8190832b46859da808f7/output_items \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: | + from openai import OpenAI + client = OpenAI() + + output_items = client.evals.runs.output_items.list( + "egroup_67abd54d9b0081909a86353f6fb9317a", + "erun_67abd54d60ec8190832b46859da808f7" + ) + print(output_items) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const outputItems = await openai.evals.runs.outputItems.list( + "egroup_67abd54d9b0081909a86353f6fb9317a", + "erun_67abd54d60ec8190832b46859da808f7" + ); + console.log(outputItems); + response: > + { + "object": "list", + "data": [ + { + "object": "eval.run.output_item", + "id": "outputitem_67e5796c28e081909917bf79f6e6214d", + "created_at": 1743092076, + "run_id": "evalrun_67abd54d60ec8190832b46859da808f7", + "eval_id": "eval_67abd54d9b0081909a86353f6fb9317a", + "status": "pass", + "datasource_item_id": 5, + "datasource_item": { + "input": "Stock Markets Rally After Positive Economic Data Released", + "ground_truth": "Markets" + }, + "results": [ + { + "name": "String check-a2486074-d803-4445-b431-ad2262e85d47", + "sample": null, + "passed": true, + "score": 1.0 + } + ], + "sample": { + "input": [ + { + "role": "developer", + "content": "Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\n\n# Steps\n\n1. Analyze the content of the news headline to understand its primary focus.\n2. Extract the subject matter, identifying any key indicators or keywords.\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\n4. Ensure only one category is selected per headline.\n\n# Output Format\n\nRespond with the chosen category as a single word. For instance: \"Technology\", \"Markets\", \"World\", \"Business\", or \"Sports\".\n\n# Examples\n\n**Input**: \"Apple Unveils New iPhone Model, Featuring Advanced AI Features\" \n**Output**: \"Technology\"\n\n**Input**: \"Global Stocks Mixed as Investors Await Central Bank Decisions\" \n**Output**: \"Markets\"\n\n**Input**: \"War in Ukraine: Latest Updates on Negotiation Status\" \n**Output**: \"World\"\n\n**Input**: \"Microsoft in Talks to Acquire Gaming Company for $2 Billion\" \n**Output**: \"Business\"\n\n**Input**: \"Manchester United Secures Win in Premier League Football Match\" \n**Output**: \"Sports\" \n\n# Notes\n\n- If the headline appears to fit into more than one category, choose the most dominant theme.\n- Keywords or phrases such as \"stocks\", \"company acquisition\", \"match\", or technological brands can be good indicators for classification.\n", + "tool_call_id": null, + "tool_calls": null, + "function_call": null + }, + { + "role": "user", + "content": "Stock Markets Rally After Positive Economic Data Released", + "tool_call_id": null, + "tool_calls": null, + "function_call": null + } + ], + "output": [ + { + "role": "assistant", + "content": "Markets", + "tool_call_id": null, + "tool_calls": null, + "function_call": null + } + ], + "finish_reason": "stop", + "model": "gpt-4o-mini-2024-07-18", + "usage": { + "total_tokens": 325, + "completion_tokens": 2, + "prompt_tokens": 323, + "cached_tokens": 0 + }, + "error": null, + "temperature": 1.0, + "max_completion_tokens": 2048, + "top_p": 1.0, + "seed": 42 + } + } + ], + "first_id": "outputitem_67e5796c28e081909917bf79f6e6214d", + "last_id": "outputitem_67e5796c28e081909917bf79f6e6214d", + "has_more": true + } + /evals/{eval_id}/runs/{run_id}/output_items/{output_item_id}: + get: + operationId: getEvalRunOutputItem + tags: + - Evals + summary: | + Get an evaluation run output item by ID. + parameters: + - name: eval_id + in: path + required: true + schema: + type: string + description: The ID of the evaluation to retrieve runs for. + - name: run_id + in: path + required: true + schema: + type: string + description: The ID of the run to retrieve. + - name: output_item_id + in: path + required: true + schema: + type: string + description: The ID of the output item to retrieve. + responses: + "200": + description: The evaluation run output item + content: + application/json: + schema: + $ref: "#/components/schemas/EvalRunOutputItem" + x-oaiMeta: + name: Get an output item of an eval run + group: evals + returns: The + [EvalRunOutputItem](/docs/api-reference/evals/run-output-item-object) + object matching the specified ID. + path: get + examples: + request: + curl: | + curl https://api.openai.com/v1/evals/eval_67abd54d9b0081909a86353f6fb9317a/runs/evalrun_67abd54d60ec8190832b46859da808f7/output_items/outputitem_67abd55eb6548190bb580745d5644a33 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" + python: | + from openai import OpenAI + client = OpenAI() + + output_item = client.evals.runs.output_items.retrieve( + "eval_67abd54d9b0081909a86353f6fb9317a", + "evalrun_67abd54d60ec8190832b46859da808f7", + "outputitem_67abd55eb6548190bb580745d5644a33" + ) + print(output_item) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const outputItem = await openai.evals.runs.outputItems.retrieve( + "eval_67abd54d9b0081909a86353f6fb9317a", + "evalrun_67abd54d60ec8190832b46859da808f7", + "outputitem_67abd55eb6548190bb580745d5644a33" + ); + console.log(outputItem); + response: > + { + "object": "eval.run.output_item", + "id": "outputitem_67e5796c28e081909917bf79f6e6214d", + "created_at": 1743092076, + "run_id": "evalrun_67abd54d60ec8190832b46859da808f7", + "eval_id": "eval_67abd54d9b0081909a86353f6fb9317a", + "status": "pass", + "datasource_item_id": 5, + "datasource_item": { + "input": "Stock Markets Rally After Positive Economic Data Released", + "ground_truth": "Markets" + }, + "results": [ + { + "name": "String check-a2486074-d803-4445-b431-ad2262e85d47", + "sample": null, + "passed": true, + "score": 1.0 + } + ], + "sample": { + "input": [ + { + "role": "developer", + "content": "Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\n\n# Steps\n\n1. Analyze the content of the news headline to understand its primary focus.\n2. Extract the subject matter, identifying any key indicators or keywords.\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\n4. Ensure only one category is selected per headline.\n\n# Output Format\n\nRespond with the chosen category as a single word. For instance: \"Technology\", \"Markets\", \"World\", \"Business\", or \"Sports\".\n\n# Examples\n\n**Input**: \"Apple Unveils New iPhone Model, Featuring Advanced AI Features\" \n**Output**: \"Technology\"\n\n**Input**: \"Global Stocks Mixed as Investors Await Central Bank Decisions\" \n**Output**: \"Markets\"\n\n**Input**: \"War in Ukraine: Latest Updates on Negotiation Status\" \n**Output**: \"World\"\n\n**Input**: \"Microsoft in Talks to Acquire Gaming Company for $2 Billion\" \n**Output**: \"Business\"\n\n**Input**: \"Manchester United Secures Win in Premier League Football Match\" \n**Output**: \"Sports\" \n\n# Notes\n\n- If the headline appears to fit into more than one category, choose the most dominant theme.\n- Keywords or phrases such as \"stocks\", \"company acquisition\", \"match\", or technological brands can be good indicators for classification.\n", + "tool_call_id": null, + "tool_calls": null, + "function_call": null + }, + { + "role": "user", + "content": "Stock Markets Rally After Positive Economic Data Released", + "tool_call_id": null, + "tool_calls": null, + "function_call": null + } + ], + "output": [ + { + "role": "assistant", + "content": "Markets", + "tool_call_id": null, + "tool_calls": null, + "function_call": null + } + ], + "finish_reason": "stop", + "model": "gpt-4o-mini-2024-07-18", + "usage": { + "total_tokens": 325, + "completion_tokens": 2, + "prompt_tokens": 323, + "cached_tokens": 0 + }, + "error": null, + "temperature": 1.0, + "max_completion_tokens": 2048, + "top_p": 1.0, + "seed": 42 + } + } + /files: + get: + operationId: listFiles + tags: + - Files + summary: Returns a list of files. + parameters: + - in: query + name: purpose + required: false + schema: + type: string + description: Only return files with the given purpose. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 10,000, and the default is 10,000. + required: false + schema: + type: integer + default: 10000 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListFilesResponse" + x-oaiMeta: + name: List files + group: files + returns: A list of [File](/docs/api-reference/files/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.files.list() + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const list = await openai.files.list(); + + for await (const file of list) { + console.log(file); + } + } + + main(); + response: | + { + "data": [ + { + "id": "file-abc123", + "object": "file", + "bytes": 175, + "created_at": 1613677385, + "filename": "salesOverview.pdf", + "purpose": "assistants", + }, + { + "id": "file-abc123", + "object": "file", + "bytes": 140, + "created_at": 1613779121, + "filename": "puppy.jsonl", + "purpose": "fine-tune", + } + ], + "object": "list" + } + post: + operationId: createFile + tags: + - Files + summary: > + Upload a file that can be used across various endpoints. Individual + files can be up to 512 MB, and the size of all files uploaded by one + organization can be up to 100 GB. + + + The Assistants API supports files up to 2 million tokens and of specific + file types. See the [Assistants Tools guide](/docs/assistants/tools) for + details. + + + The Fine-tuning API only supports `.jsonl` files. The input also has + certain required formats for fine-tuning + [chat](/docs/api-reference/fine-tuning/chat-input) or + [completions](/docs/api-reference/fine-tuning/completions-input) models. + + + The Batch API only supports `.jsonl` files up to 200 MB in size. The + input also has a specific required + [format](/docs/api-reference/batch/request-input). + + + Please [contact us](https://help.openai.com/) if you need to increase + these storage limits. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateFileRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/OpenAIFile" + x-oaiMeta: + name: Upload file + group: files + returns: The uploaded [File](/docs/api-reference/files/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -F purpose="fine-tune" \ + -F file="@mydata.jsonl" + python: | + from openai import OpenAI + client = OpenAI() + + client.files.create( + file=open("mydata.jsonl", "rb"), + purpose="fine-tune" + ) + node.js: |- + import fs from "fs"; + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const file = await openai.files.create({ + file: fs.createReadStream("mydata.jsonl"), + purpose: "fine-tune", + }); + + console.log(file); + } + + main(); + response: | + { + "id": "file-abc123", + "object": "file", + "bytes": 120000, + "created_at": 1677610602, + "filename": "mydata.jsonl", + "purpose": "fine-tune", + } + /files/{file_id}: + delete: + operationId: deleteFile + tags: + - Files + summary: Delete a file. + parameters: + - in: path + name: file_id + required: true + schema: + type: string + description: The ID of the file to use for this request. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteFileResponse" + x-oaiMeta: + name: Delete file + group: files + returns: Deletion status. + examples: + request: + curl: | + curl https://api.openai.com/v1/files/file-abc123 \ + -X DELETE \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.files.delete("file-abc123") + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const file = await openai.files.del("file-abc123"); + + console.log(file); + } + + main(); + response: | + { + "id": "file-abc123", + "object": "file", + "deleted": true + } + get: + operationId: retrieveFile + tags: + - Files + summary: Returns information about a specific file. + parameters: + - in: path + name: file_id + required: true + schema: + type: string + description: The ID of the file to use for this request. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/OpenAIFile" + x-oaiMeta: + name: Retrieve file + group: files + returns: The [File](/docs/api-reference/files/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/files/file-abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.files.retrieve("file-abc123") + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const file = await openai.files.retrieve("file-abc123"); + + console.log(file); + } + + main(); + response: | + { + "id": "file-abc123", + "object": "file", + "bytes": 120000, + "created_at": 1677610602, + "filename": "mydata.jsonl", + "purpose": "fine-tune", + } + /files/{file_id}/content: + get: + operationId: downloadFile + tags: + - Files + summary: Returns the contents of the specified file. + parameters: + - in: path + name: file_id + required: true + schema: + type: string + description: The ID of the file to use for this request. + responses: + "200": + description: OK + content: + application/json: + schema: + type: string + x-oaiMeta: + name: Retrieve file content + group: files + returns: The file content. + examples: + request: + curl: | + curl https://api.openai.com/v1/files/file-abc123/content \ + -H "Authorization: Bearer $OPENAI_API_KEY" > file.jsonl + python: | + from openai import OpenAI + client = OpenAI() + + content = client.files.content("file-abc123") + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const file = await openai.files.content("file-abc123"); + + console.log(file); + } + + main(); + /fine_tuning/alpha/graders/run: + post: + operationId: runGrader + tags: + - Fine-tuning + summary: | + Run a grader. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/RunGraderRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunGraderResponse" + x-oaiMeta: + name: Run grader + beta: true + group: graders + returns: The results from the grader run. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/fine_tuning/alpha/graders/run \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "grader": { + "type": "score_model", + "name": "Example score model grader", + "input": [ + { + "role": "user", + "content": "Score how close the reference answer is to the model answer. Score 1.0 if they are the same and 0.0 if they are different. Return just a floating point score\n\nReference answer: {{item.reference_answer}}\n\nModel answer: {{sample.output_text}}" + } + ], + "model": "gpt-4o-2024-08-06", + "sampling_params": { + "temperature": 1, + "top_p": 1, + "seed": 42 + } + }, + "item": { + "reference_answer": "fuzzy wuzzy was a bear" + }, + "model_sample": "fuzzy wuzzy was a bear" + }' + response: | + { + "reward": 1.0, + "metadata": { + "name": "Example score model grader", + "type": "score_model", + "errors": { + "formula_parse_error": false, + "sample_parse_error": false, + "truncated_observation_error": false, + "unresponsive_reward_error": false, + "invalid_variable_error": false, + "other_error": false, + "python_grader_server_error": false, + "python_grader_server_error_type": null, + "python_grader_runtime_error": false, + "python_grader_runtime_error_details": null, + "model_grader_server_error": false, + "model_grader_refusal_error": false, + "model_grader_parse_error": false, + "model_grader_server_error_details": null + }, + "execution_time": 4.365238428115845, + "scores": {}, + "token_usage": { + "prompt_tokens": 190, + "total_tokens": 324, + "completion_tokens": 134, + "cached_tokens": 0 + }, + "sampled_model_name": "gpt-4o-2024-08-06" + }, + "sub_rewards": {}, + "model_grader_token_usage_per_model": { + "gpt-4o-2024-08-06": { + "prompt_tokens": 190, + "total_tokens": 324, + "completion_tokens": 134, + "cached_tokens": 0 + } + } + } + /fine_tuning/alpha/graders/validate: + post: + operationId: validateGrader + tags: + - Fine-tuning + summary: | + Validate a grader. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ValidateGraderRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ValidateGraderResponse" + x-oaiMeta: + name: Validate grader + beta: true + group: graders + returns: The validated grader object. + examples: + request: + curl: > + curl https://api.openai.com/v1/fine_tuning/alpha/graders/validate + \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "grader": { + "type": "string_check", + "name": "Example string check grader", + "input": "{{sample.output_text}}", + "reference": "{{item.label}}", + "operation": "eq" + } + }' + response: | + { + "grader": { + "type": "string_check", + "name": "Example string check grader", + "input": "{{sample.output_text}}", + "reference": "{{item.label}}", + "operation": "eq" + } + } + /fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions: + get: + operationId: listFineTuningCheckpointPermissions + tags: + - Fine-tuning + summary: > + **NOTE:** This endpoint requires an [admin API key](../admin-api-keys). + + + Organization owners can use this endpoint to view all permissions for a + fine-tuned model checkpoint. + parameters: + - in: path + name: fine_tuned_model_checkpoint + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuned model checkpoint to get permissions for. + - name: project_id + in: query + description: The ID of the project to get permissions for. + required: false + schema: + type: string + - name: after + in: query + description: Identifier for the last permission ID from the previous pagination + request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of permissions to retrieve. + required: false + schema: + type: integer + default: 10 + - name: order + in: query + description: The order in which to retrieve permissions. + required: false + schema: + type: string + enum: + - ascending + - descending + default: descending + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListFineTuningCheckpointPermissionResponse" + x-oaiMeta: + name: List checkpoint permissions + group: fine-tuning + returns: A list of fine-tuned model checkpoint [permission + objects](/docs/api-reference/fine-tuning/permission-object) for a + fine-tuned model checkpoint. + examples: + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/checkpoints/ft:gpt-4o-mini-2024-07-18:org:weather:B7R9VjQd/permissions \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: | + { + "object": "list", + "data": [ + { + "object": "checkpoint.permission", + "id": "cp_zc4Q7MP6XxulcVzj4MZdwsAB", + "created_at": 1721764867, + "project_id": "proj_abGMw1llN8IrBb6SvvY5A1iH" + }, + { + "object": "checkpoint.permission", + "id": "cp_enQCFmOTGj3syEpYVhBRLTSy", + "created_at": 1721764800, + "project_id": "proj_iqGMw1llN8IrBb6SvvY5A1oF" + }, + ], + "first_id": "cp_zc4Q7MP6XxulcVzj4MZdwsAB", + "last_id": "cp_enQCFmOTGj3syEpYVhBRLTSy", + "has_more": false + } + post: + operationId: createFineTuningCheckpointPermission + tags: + - Fine-tuning + summary: > + **NOTE:** Calling this endpoint requires an [admin API + key](../admin-api-keys). + + + This enables organization owners to share fine-tuned models with other + projects in their organization. + parameters: + - in: path + name: fine_tuned_model_checkpoint + required: true + schema: + type: string + example: ft:gpt-4o-mini-2024-07-18:org:weather:B7R9VjQd + description: > + The ID of the fine-tuned model checkpoint to create a permission for. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateFineTuningCheckpointPermissionRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListFineTuningCheckpointPermissionResponse" + x-oaiMeta: + name: Create checkpoint permissions + group: fine-tuning + returns: A list of fine-tuned model checkpoint [permission + objects](/docs/api-reference/fine-tuning/permission-object) for a + fine-tuned model checkpoint. + examples: + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/checkpoints/ft:gpt-4o-mini-2024-07-18:org:weather:B7R9VjQd/permissions \ + -H "Authorization: Bearer $OPENAI_API_KEY" + -d '{"project_ids": ["proj_abGMw1llN8IrBb6SvvY5A1iH"]}' + response: | + { + "object": "list", + "data": [ + { + "object": "checkpoint.permission", + "id": "cp_zc4Q7MP6XxulcVzj4MZdwsAB", + "created_at": 1721764867, + "project_id": "proj_abGMw1llN8IrBb6SvvY5A1iH" + } + ], + "first_id": "cp_zc4Q7MP6XxulcVzj4MZdwsAB", + "last_id": "cp_zc4Q7MP6XxulcVzj4MZdwsAB", + "has_more": false + } + /fine_tuning/checkpoints/{fine_tuned_model_checkpoint}/permissions/{permission_id}: + delete: + operationId: deleteFineTuningCheckpointPermission + tags: + - Fine-tuning + summary: > + **NOTE:** This endpoint requires an [admin API key](../admin-api-keys). + + + Organization owners can use this endpoint to delete a permission for a + fine-tuned model checkpoint. + parameters: + - in: path + name: fine_tuned_model_checkpoint + required: true + schema: + type: string + example: ft:gpt-4o-mini-2024-07-18:org:weather:B7R9VjQd + description: > + The ID of the fine-tuned model checkpoint to delete a permission for. + - in: path + name: permission_id + required: true + schema: + type: string + example: cp_zc4Q7MP6XxulcVzj4MZdwsAB + description: | + The ID of the fine-tuned model checkpoint permission to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteFineTuningCheckpointPermissionResponse" + x-oaiMeta: + name: Delete checkpoint permission + group: fine-tuning + returns: The deletion status of the fine-tuned model checkpoint [permission + object](/docs/api-reference/fine-tuning/permission-object). + examples: + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/checkpoints/ft:gpt-4o-mini-2024-07-18:org:weather:B7R9VjQd/permissions/cp_zc4Q7MP6XxulcVzj4MZdwsAB \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: | + { + "object": "checkpoint.permission", + "id": "cp_zc4Q7MP6XxulcVzj4MZdwsAB", + "deleted": true + } + /fine_tuning/jobs: + post: + operationId: createFineTuningJob + tags: + - Fine-tuning + summary: > + Creates a fine-tuning job which begins the process of creating a new + model from a given dataset. + + + Response includes details of the enqueued job including job status and + the name of the fine-tuned models once complete. + + + [Learn more about fine-tuning](/docs/guides/model-optimization) + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateFineTuningJobRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/FineTuningJob" + x-oaiMeta: + name: Create fine-tuning job + group: fine-tuning + returns: A [fine-tuning.job](/docs/api-reference/fine-tuning/object) object. + examples: + - title: Default + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-BK7bzQj3FfZFXr7DbL6xJwfo", + "model": "gpt-4o-mini" + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.create( + training_file="file-abc123", + model="gpt-4o-mini" + ) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const fineTune = await openai.fineTuning.jobs.create({ + training_file: "file-abc123" + }); + + console.log(fineTune); + } + + main(); + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": null, + "training_file": "file-abc123", + "method": { + "type": "supervised", + "supervised": { + "hyperparameters": { + "batch_size": "auto", + "learning_rate_multiplier": "auto", + "n_epochs": "auto", + } + } + }, + "metadata": null + } + - title: Epochs + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-abc123", + "model": "gpt-4o-mini", + "method": { + "type": "supervised", + "supervised": { + "hyperparameters": { + "n_epochs": 2 + } + } + } + }' + python: > + from openai import OpenAI + + from openai.types.fine_tuning import SupervisedMethod, + SupervisedHyperparameters + + + client = OpenAI() + + + client.fine_tuning.jobs.create( + training_file="file-abc123", + model="gpt-4o-mini", + method={ + "type": "supervised", + "supervised": SupervisedMethod( + hyperparameters=SupervisedHyperparameters( + n_epochs=2 + ) + ) + } + ) + node.js: > + import OpenAI from "openai"; + + import { SupervisedMethod, SupervisedHyperparameters } from + "openai/src/resources/fine-tuning/methods"; + + + const openai = new OpenAI(); + + + async function main() { + const fineTune = await openai.fineTuning.jobs.create({ + training_file: "file-abc123", + model: "gpt-4o-mini", + method: { + type: "supervised", + supervised: { + hyperparameters: { + n_epochs: 2 + } + } + } + }); + + console.log(fineTune); + } + + + main(); + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": null, + "training_file": "file-abc123", + "hyperparameters": { + "batch_size": "auto", + "learning_rate_multiplier": "auto", + "n_epochs": 2 + }, + "method": { + "type": "supervised", + "supervised": { + "hyperparameters": { + "batch_size": "auto", + "learning_rate_multiplier": "auto", + "n_epochs": 2 + } + } + }, + "metadata": null, + "error": { + "code": null, + "message": null, + "param": null + }, + "finished_at": null, + "seed": 683058546, + "trained_tokens": null, + "estimated_finish": null, + "integrations": [], + "user_provided_suffix": null, + "usage_metrics": null, + "shared_with_openai": false + } + - title: DPO + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-abc123", + "validation_file": "file-abc123", + "model": "gpt-4o-mini", + "method": { + "type": "dpo", + "dpo": { + "hyperparameters": { + "beta": 0.1 + } + } + } + }' + python: | + from openai import OpenAI + from openai.types.fine_tuning import DpoMethod, DpoHyperparameters + + client = OpenAI() + + client.fine_tuning.jobs.create( + training_file="file-abc", + validation_file="file-123", + model="gpt-4o-mini", + method={ + "type": "dpo", + "dpo": DpoMethod( + hyperparameters=DpoHyperparameters(beta=0.1) + ) + } + ) + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc", + "model": "gpt-4o-mini", + "created_at": 1746130590, + "fine_tuned_model": null, + "organization_id": "org-abc", + "result_files": [], + "status": "queued", + "validation_file": "file-123", + "training_file": "file-abc", + "method": { + "type": "dpo", + "dpo": { + "hyperparameters": { + "beta": 0.1, + "batch_size": "auto", + "learning_rate_multiplier": "auto", + "n_epochs": "auto" + } + } + }, + "metadata": null, + "error": { + "code": null, + "message": null, + "param": null + }, + "finished_at": null, + "hyperparameters": null, + "seed": 1036326793, + "estimated_finish": null, + "integrations": [], + "user_provided_suffix": null, + "usage_metrics": null, + "shared_with_openai": false + } + - title: Reinforcement + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-abc", + "validation_file": "file-123", + "model": "o4-mini", + "method": { + "type": "reinforcement", + "reinforcement": { + "grader": { + "type": "string_check", + "name": "Example string check grader", + "input": "{{sample.output_text}}", + "reference": "{{item.label}}", + "operation": "eq" + }, + "hyperparameters": { + "reasoning_effort": "medium" + } + } + } + }' + python: > + from openai import OpenAI + + from openai.types.fine_tuning import ReinforcementMethod, + ReinforcementHyperparameters + + from openai.types.graders import StringCheckGrader + + + client = OpenAI() + + + client.fine_tuning.jobs.create( + training_file="file-abc", + validation_file="file-123", + model="o4-mini", + method={ + "type": "reinforcement", + "reinforcement": ReinforcementMethod( + grader=StringCheckGrader( + name="Example string check grader", + type="string_check", + input="{{item.label}}", + operation="eq", + reference="{{sample.output_text}}" + ), + hyperparameters=ReinforcementHyperparameters( + reasoning_effort="medium", + ) + ) + }, + seed=42, + ) + response: |+ + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "o4-mini", + "created_at": 1721764800, + "finished_at": null, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "validating_files", + "validation_file": "file-123", + "training_file": "file-abc", + "trained_tokens": null, + "error": {}, + "user_provided_suffix": null, + "seed": 950189191, + "estimated_finish": null, + "integrations": [], + "method": { + "type": "reinforcement", + "reinforcement": { + "hyperparameters": { + "batch_size": "auto", + "learning_rate_multiplier": "auto", + "n_epochs": "auto", + "eval_interval": "auto", + "eval_samples": "auto", + "compute_multiplier": "auto", + "reasoning_effort": "medium" + }, + "grader": { + "type": "string_check", + "name": "Example string check grader", + "input": "{{sample.output_text}}", + "reference": "{{item.label}}", + "operation": "eq" + }, + "response_format": null + } + }, + "metadata": null, + "usage_metrics": null, + "shared_with_openai": false + } + + - title: Validation file + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-abc123", + "validation_file": "file-abc123", + "model": "gpt-4o-mini" + }' + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.create( + training_file="file-abc123", + validation_file="file-def456", + model="gpt-4o-mini" + ) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const fineTune = await openai.fineTuning.jobs.create({ + training_file: "file-abc123", + validation_file: "file-abc123" + }); + + console.log(fineTune); + } + + main(); + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": "file-abc123", + "training_file": "file-abc123", + "method": { + "type": "supervised", + "supervised": { + "hyperparameters": { + "batch_size": "auto", + "learning_rate_multiplier": "auto", + "n_epochs": "auto", + } + } + }, + "metadata": null + } + - title: W&B Integration + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "training_file": "file-abc123", + "validation_file": "file-abc123", + "model": "gpt-4o-mini", + "integrations": [ + { + "type": "wandb", + "wandb": { + "project": "my-wandb-project", + "name": "ft-run-display-name" + "tags": [ + "first-experiment", "v2" + ] + } + } + ] + }' + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": "file-abc123", + "training_file": "file-abc123", + "integrations": [ + { + "type": "wandb", + "wandb": { + "project": "my-wandb-project", + "entity": None, + "run_id": "ftjob-abc123" + } + } + ], + "method": { + "type": "supervised", + "supervised": { + "hyperparameters": { + "batch_size": "auto", + "learning_rate_multiplier": "auto", + "n_epochs": "auto", + } + } + }, + "metadata": null + } + get: + operationId: listPaginatedFineTuningJobs + tags: + - Fine-tuning + summary: | + List your organization's fine-tuning jobs + parameters: + - name: after + in: query + description: Identifier for the last job from the previous pagination request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of fine-tuning jobs to retrieve. + required: false + schema: + type: integer + default: 20 + - in: query + name: metadata + required: false + schema: + type: object + nullable: true + additionalProperties: + type: string + style: deepObject + explode: true + description: > + Optional metadata filter. To filter, use the syntax `metadata[k]=v`. + Alternatively, set `metadata=null` to indicate no metadata. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListPaginatedFineTuningJobsResponse" + x-oaiMeta: + name: List fine-tuning jobs + group: fine-tuning + returns: A list of paginated [fine-tuning + job](/docs/api-reference/fine-tuning/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs?limit=2&metadata[key]=value \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.list() + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const list = await openai.fineTuning.jobs.list(); + + for await (const fineTune of list) { + console.log(fineTune); + } + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": null, + "training_file": "file-abc123", + "metadata": { + "key": "value" + } + }, + { ... }, + { ... } + ], "has_more": true + } + /fine_tuning/jobs/{fine_tuning_job_id}: + get: + operationId: retrieveFineTuningJob + tags: + - Fine-tuning + summary: | + Get info about a fine-tuning job. + + [Learn more about fine-tuning](/docs/guides/model-optimization) + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/FineTuningJob" + x-oaiMeta: + name: Retrieve fine-tuning job + group: fine-tuning + returns: The [fine-tuning](/docs/api-reference/fine-tuning/object) object with + the given ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs/ft-AF1WoRqd3aJAHsqc9NY7iL8F \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.retrieve("ftjob-abc123") + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const fineTune = await openai.fineTuning.jobs.retrieve("ftjob-abc123"); + + console.log(fineTune); + } + + + main(); + response: > + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "davinci-002", + "created_at": 1692661014, + "finished_at": 1692661190, + "fine_tuned_model": "ft:davinci-002:my-org:custom_suffix:7q8mpxmy", + "organization_id": "org-123", + "result_files": [ + "file-abc123" + ], + "status": "succeeded", + "validation_file": null, + "training_file": "file-abc123", + "hyperparameters": { + "n_epochs": 4, + "batch_size": 1, + "learning_rate_multiplier": 1.0 + }, + "trained_tokens": 5768, + "integrations": [], + "seed": 0, + "estimated_finish": 0, + "method": { + "type": "supervised", + "supervised": { + "hyperparameters": { + "n_epochs": 4, + "batch_size": 1, + "learning_rate_multiplier": 1.0 + } + } + } + } + /fine_tuning/jobs/{fine_tuning_job_id}/cancel: + post: + operationId: cancelFineTuningJob + tags: + - Fine-tuning + summary: | + Immediately cancel a fine-tune job. + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job to cancel. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/FineTuningJob" + x-oaiMeta: + name: Cancel fine-tuning + group: fine-tuning + returns: The cancelled [fine-tuning](/docs/api-reference/fine-tuning/object) + object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/cancel \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.cancel("ftjob-abc123") + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const fineTune = await openai.fineTuning.jobs.cancel("ftjob-abc123"); + + console.log(fineTune); + } + + main(); + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "cancelled", + "validation_file": "file-abc123", + "training_file": "file-abc123" + } + /fine_tuning/jobs/{fine_tuning_job_id}/checkpoints: + get: + operationId: listFineTuningJobCheckpoints + tags: + - Fine-tuning + summary: | + List checkpoints for a fine-tuning job. + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job to get checkpoints for. + - name: after + in: query + description: Identifier for the last checkpoint ID from the previous pagination + request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of checkpoints to retrieve. + required: false + schema: + type: integer + default: 10 + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListFineTuningJobCheckpointsResponse" + x-oaiMeta: + name: List fine-tuning checkpoints + group: fine-tuning + returns: A list of fine-tuning [checkpoint + objects](/docs/api-reference/fine-tuning/checkpoint-object) for a + fine-tuning job. + examples: + request: + curl: | + curl https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/checkpoints \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: > + { + "object": "list" + "data": [ + { + "object": "fine_tuning.job.checkpoint", + "id": "ftckpt_zc4Q7MP6XxulcVzj4MZdwsAB", + "created_at": 1721764867, + "fine_tuned_model_checkpoint": "ft:gpt-4o-mini-2024-07-18:my-org:custom-suffix:96olL566:ckpt-step-2000", + "metrics": { + "full_valid_loss": 0.134, + "full_valid_mean_token_accuracy": 0.874 + }, + "fine_tuning_job_id": "ftjob-abc123", + "step_number": 2000, + }, + { + "object": "fine_tuning.job.checkpoint", + "id": "ftckpt_enQCFmOTGj3syEpYVhBRLTSy", + "created_at": 1721764800, + "fine_tuned_model_checkpoint": "ft:gpt-4o-mini-2024-07-18:my-org:custom-suffix:7q8mpxmy:ckpt-step-1000", + "metrics": { + "full_valid_loss": 0.167, + "full_valid_mean_token_accuracy": 0.781 + }, + "fine_tuning_job_id": "ftjob-abc123", + "step_number": 1000, + }, + ], + "first_id": "ftckpt_zc4Q7MP6XxulcVzj4MZdwsAB", + "last_id": "ftckpt_enQCFmOTGj3syEpYVhBRLTSy", + "has_more": true + } + /fine_tuning/jobs/{fine_tuning_job_id}/events: + get: + operationId: listFineTuningEvents + tags: + - Fine-tuning + summary: | + Get status updates for a fine-tuning job. + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job to get events for. + - name: after + in: query + description: Identifier for the last event from the previous pagination request. + required: false + schema: + type: string + - name: limit + in: query + description: Number of events to retrieve. + required: false + schema: + type: integer + default: 20 + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListFineTuningJobEventsResponse" + x-oaiMeta: + name: List fine-tuning events + group: fine-tuning + returns: A list of fine-tuning event objects. + examples: + request: + curl: > + curl + https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/events \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.list_events( + fine_tuning_job_id="ftjob-abc123", + limit=2 + ) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const list = await openai.fineTuning.list_events(id="ftjob-abc123", limit=2); + + for await (const fineTune of list) { + console.log(fineTune); + } + } + + + main(); + response: > + { + "object": "list", + "data": [ + { + "object": "fine_tuning.job.event", + "id": "ft-event-ddTJfwuMVpfLXseO0Am0Gqjm", + "created_at": 1721764800, + "level": "info", + "message": "Fine tuning job successfully completed", + "data": null, + "type": "message" + }, + { + "object": "fine_tuning.job.event", + "id": "ft-event-tyiGuB72evQncpH87xe505Sv", + "created_at": 1721764800, + "level": "info", + "message": "New fine-tuned model created: ft:gpt-4o-mini:openai::7p4lURel", + "data": null, + "type": "message" + } + ], + "has_more": true + } + /fine_tuning/jobs/{fine_tuning_job_id}/pause: + post: + operationId: pauseFineTuningJob + tags: + - Fine-tuning + summary: | + Pause a fine-tune job. + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job to pause. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/FineTuningJob" + x-oaiMeta: + name: Pause fine-tuning + group: fine-tuning + returns: The paused [fine-tuning](/docs/api-reference/fine-tuning/object) + object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/pause \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.pause("ftjob-abc123") + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const fineTune = await openai.fineTuning.jobs.pause("ftjob-abc123"); + + console.log(fineTune); + } + + main(); + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "paused", + "validation_file": "file-abc123", + "training_file": "file-abc123" + } + /fine_tuning/jobs/{fine_tuning_job_id}/resume: + post: + operationId: resumeFineTuningJob + tags: + - Fine-tuning + summary: | + Resume a fine-tune job. + parameters: + - in: path + name: fine_tuning_job_id + required: true + schema: + type: string + example: ft-AF1WoRqd3aJAHsqc9NY7iL8F + description: | + The ID of the fine-tuning job to resume. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/FineTuningJob" + x-oaiMeta: + name: Resume fine-tuning + group: fine-tuning + returns: The resumed [fine-tuning](/docs/api-reference/fine-tuning/object) + object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/fine_tuning/jobs/ftjob-abc123/resume \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.fine_tuning.jobs.resume("ftjob-abc123") + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const fineTune = await openai.fineTuning.jobs.resume("ftjob-abc123"); + + console.log(fineTune); + } + + main(); + response: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "gpt-4o-mini-2024-07-18", + "created_at": 1721764800, + "fine_tuned_model": null, + "organization_id": "org-123", + "result_files": [], + "status": "queued", + "validation_file": "file-abc123", + "training_file": "file-abc123" + } + /images/edits: + post: + operationId: createImageEdit + tags: + - Images + summary: Creates an edited or extended image given one or more source images and + a prompt. This endpoint only supports `gpt-image-1` and `dall-e-2`. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateImageEditRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ImagesResponse" + x-oaiMeta: + name: Create image edit + group: images + returns: Returns a list of [image](/docs/api-reference/images/object) objects. + examples: + request: + curl: > + curl -s -D >(grep -i x-request-id >&2) \ + -o >(jq -r '.data[0].b64_json' | base64 --decode > gift-basket.png) \ + -X POST "https://api.openai.com/v1/images/edits" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -F "model=gpt-image-1" \ + -F "image[]=@body-lotion.png" \ + -F "image[]=@bath-bomb.png" \ + -F "image[]=@incense-kit.png" \ + -F "image[]=@soap.png" \ + -F 'prompt=Create a lovely gift basket with these four items in it' + python: > + import base64 + + from openai import OpenAI + + client = OpenAI() + + + prompt = """ + + Generate a photorealistic image of a gift basket on a white + background + + labeled 'Relax & Unwind' with a ribbon and handwriting-like font, + + containing all the items in the reference pictures. + + """ + + + result = client.images.edit( + model="gpt-image-1", + image=[ + open("body-lotion.png", "rb"), + open("bath-bomb.png", "rb"), + open("incense-kit.png", "rb"), + open("soap.png", "rb"), + ], + prompt=prompt + ) + + + image_base64 = result.data[0].b64_json + + image_bytes = base64.b64decode(image_base64) + + + # Save the image to a file + + with open("gift-basket.png", "wb") as f: + f.write(image_bytes) + node.js: > + import fs from "fs"; + + import OpenAI, { toFile } from "openai"; + + + const client = new OpenAI(); + + + const imageFiles = [ + "bath-bomb.png", + "body-lotion.png", + "incense-kit.png", + "soap.png", + ]; + + + const images = await Promise.all( + imageFiles.map(async (file) => + await toFile(fs.createReadStream(file), null, { + type: "image/png", + }) + ), + ); + + + const rsp = await client.images.edit({ + model: "gpt-image-1", + image: images, + prompt: "Create a lovely gift basket with these four items in it", + }); + + + // Save the image to a file + + const image_base64 = rsp.data[0].b64_json; + + const image_bytes = Buffer.from(image_base64, "base64"); + + fs.writeFileSync("basket.png", image_bytes); + response: | + { + "created": 1713833628, + "data": [ + { + "b64_json": "..." + } + ], + "usage": { + "total_tokens": 100, + "input_tokens": 50, + "output_tokens": 50, + "input_tokens_details": { + "text_tokens": 10, + "image_tokens": 40 + } + } + } + /images/generations: + post: + operationId: createImage + tags: + - Images + summary: | + Creates an image given a prompt. [Learn more](/docs/guides/images). + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateImageRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ImagesResponse" + x-oaiMeta: + name: Create image + group: images + returns: Returns a list of [image](/docs/api-reference/images/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/images/generations \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "gpt-image-1", + "prompt": "A cute baby sea otter", + "n": 1, + "size": "1024x1024" + }' + python: | + import base64 + from openai import OpenAI + client = OpenAI() + + img = client.images.generate( + model="gpt-image-1", + prompt="A cute baby sea otter", + n=1, + size="1024x1024" + ) + + image_bytes = base64.b64decode(img.data[0].b64_json) + with open("output.png", "wb") as f: + f.write(image_bytes) + node.js: | + import OpenAI from "openai"; + import { writeFile } from "fs/promises"; + + const client = new OpenAI(); + + const img = await client.images.generate({ + model: "gpt-image-1", + prompt: "A cute baby sea otter", + n: 1, + size: "1024x1024" + }); + + const imageBuffer = Buffer.from(img.data[0].b64_json, "base64"); + await writeFile("output.png", imageBuffer); + response: | + { + "created": 1713833628, + "data": [ + { + "b64_json": "..." + } + ], + "usage": { + "total_tokens": 100, + "input_tokens": 50, + "output_tokens": 50, + "input_tokens_details": { + "text_tokens": 10, + "image_tokens": 40 + } + } + } + /images/variations: + post: + operationId: createImageVariation + tags: + - Images + summary: Creates a variation of a given image. This endpoint only supports + `dall-e-2`. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/CreateImageVariationRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ImagesResponse" + x-oaiMeta: + name: Create image variation + group: images + returns: Returns a list of [image](/docs/api-reference/images/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/images/variations \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -F image="@otter.png" \ + -F n=2 \ + -F size="1024x1024" + python: | + from openai import OpenAI + client = OpenAI() + + response = client.images.create_variation( + image=open("image_edit_original.png", "rb"), + n=2, + size="1024x1024" + ) + node.js: |- + import fs from "fs"; + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const image = await openai.images.createVariation({ + image: fs.createReadStream("otter.png"), + }); + + console.log(image.data); + } + main(); + csharp: > + using System; + + + using OpenAI.Images; + + + ImageClient client = new( + model: "dall-e-2", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + GeneratedImage image = + client.GenerateImageVariation(imageFilePath: "otter.png"); + + + Console.WriteLine(image.ImageUri); + response: | + { + "created": 1589478378, + "data": [ + { + "url": "https://..." + }, + { + "url": "https://..." + } + ] + } + /models: + get: + operationId: listModels + tags: + - Models + summary: Lists the currently available models, and provides basic information + about each one such as the owner and availability. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListModelsResponse" + x-oaiMeta: + name: List models + group: models + returns: A list of [model](/docs/api-reference/models/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/models \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.models.list() + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const list = await openai.models.list(); + + for await (const model of list) { + console.log(model); + } + } + main(); + csharp: | + using System; + + using OpenAI.Models; + + OpenAIModelClient client = new( + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + foreach (var model in client.GetModels().Value) + { + Console.WriteLine(model.Id); + } + response: | + { + "object": "list", + "data": [ + { + "id": "model-id-0", + "object": "model", + "created": 1686935002, + "owned_by": "organization-owner" + }, + { + "id": "model-id-1", + "object": "model", + "created": 1686935002, + "owned_by": "organization-owner", + }, + { + "id": "model-id-2", + "object": "model", + "created": 1686935002, + "owned_by": "openai" + }, + ], + "object": "list" + } + /models/{model}: + get: + operationId: retrieveModel + tags: + - Models + summary: Retrieves a model instance, providing basic information about the model + such as the owner and permissioning. + parameters: + - in: path + name: model + required: true + schema: + type: string + example: gpt-4o-mini + description: The ID of the model to use for this request + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Model" + x-oaiMeta: + name: Retrieve model + group: models + returns: The [model](/docs/api-reference/models/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/models/VAR_chat_model_id \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.models.retrieve("VAR_chat_model_id") + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const model = await openai.models.retrieve("VAR_chat_model_id"); + + console.log(model); + } + + main(); + csharp: | + using System; + using System.ClientModel; + + using OpenAI.Models; + + OpenAIModelClient client = new( + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + ClientResult model = client.GetModel("babbage-002"); + Console.WriteLine(model.Value.Id); + response: | + { + "id": "VAR_chat_model_id", + "object": "model", + "created": 1686935002, + "owned_by": "openai" + } + delete: + operationId: deleteModel + tags: + - Models + summary: Delete a fine-tuned model. You must have the Owner role in your + organization to delete a model. + parameters: + - in: path + name: model + required: true + schema: + type: string + example: ft:gpt-4o-mini:acemeco:suffix:abc123 + description: The model to delete + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteModelResponse" + x-oaiMeta: + name: Delete a fine-tuned model + group: models + returns: Deletion status. + examples: + request: + curl: | + curl https://api.openai.com/v1/models/ft:gpt-4o-mini:acemeco:suffix:abc123 \ + -X DELETE \ + -H "Authorization: Bearer $OPENAI_API_KEY" + python: | + from openai import OpenAI + client = OpenAI() + + client.models.delete("ft:gpt-4o-mini:acemeco:suffix:abc123") + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const model = await openai.models.del("ft:gpt-4o-mini:acemeco:suffix:abc123"); + + console.log(model); + } + + main(); + csharp: > + using System; + + using System.ClientModel; + + + using OpenAI.Models; + + + OpenAIModelClient client = new( + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + ClientResult success = + client.DeleteModel("ft:gpt-4o-mini:acemeco:suffix:abc123"); + + Console.WriteLine(success); + response: | + { + "id": "ft:gpt-4o-mini:acemeco:suffix:abc123", + "object": "model", + "deleted": true + } + /moderations: + post: + operationId: createModeration + tags: + - Moderations + summary: | + Classifies if text and/or image inputs are potentially harmful. Learn + more in the [moderation guide](/docs/guides/moderation). + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateModerationRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/CreateModerationResponse" + x-oaiMeta: + name: Create moderation + group: moderations + returns: A [moderation](/docs/api-reference/moderations/object) object. + examples: + - title: Single string + request: + curl: | + curl https://api.openai.com/v1/moderations \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "input": "I want to kill them." + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + moderation = client.moderations.create(input="I want to kill + them.") + + print(moderation) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const moderation = await openai.moderations.create({ input: "I want to kill them." }); + + console.log(moderation); + } + + main(); + csharp: > + using System; + + using System.ClientModel; + + + using OpenAI.Moderations; + + + ModerationClient client = new( + model: "omni-moderation-latest", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + ClientResult moderation = + client.ClassifyText("I want to kill them."); + response: | + { + "id": "modr-AB8CjOTu2jiq12hp1AQPfeqFWaORR", + "model": "text-moderation-007", + "results": [ + { + "flagged": true, + "categories": { + "sexual": false, + "hate": false, + "harassment": true, + "self-harm": false, + "sexual/minors": false, + "hate/threatening": false, + "violence/graphic": false, + "self-harm/intent": false, + "self-harm/instructions": false, + "harassment/threatening": true, + "violence": true + }, + "category_scores": { + "sexual": 0.000011726012417057063, + "hate": 0.22706663608551025, + "harassment": 0.5215635299682617, + "self-harm": 2.227119921371923e-6, + "sexual/minors": 7.107352217872176e-8, + "hate/threatening": 0.023547329008579254, + "violence/graphic": 0.00003391829886822961, + "self-harm/intent": 1.646940972932498e-6, + "self-harm/instructions": 1.1198755256458526e-9, + "harassment/threatening": 0.5694745779037476, + "violence": 0.9971134662628174 + } + } + ] + } + - title: Image and text + request: + curl: > + curl https://api.openai.com/v1/moderations \ + -X POST \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "omni-moderation-latest", + "input": [ + { "type": "text", "text": "...text to classify goes here..." }, + { + "type": "image_url", + "image_url": { + "url": "https://example.com/image.png" + } + } + ] + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + response = client.moderations.create( + model="omni-moderation-latest", + input=[ + {"type": "text", "text": "...text to classify goes here..."}, + { + "type": "image_url", + "image_url": { + "url": "https://example.com/image.png", + # can also use base64 encoded image URLs + # "url": "data:image/jpeg;base64,abcdefg..." + } + }, + ], + ) + + + print(response) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + const moderation = await openai.moderations.create({ + model: "omni-moderation-latest", + input: [ + { type: "text", text: "...text to classify goes here..." }, + { + type: "image_url", + image_url: { + url: "https://example.com/image.png" + // can also use base64 encoded image URLs + // url: "data:image/jpeg;base64,abcdefg..." + } + } + ], + }); + + + console.log(moderation); + response: | + { + "id": "modr-0d9740456c391e43c445bf0f010940c7", + "model": "omni-moderation-latest", + "results": [ + { + "flagged": true, + "categories": { + "harassment": true, + "harassment/threatening": true, + "sexual": false, + "hate": false, + "hate/threatening": false, + "illicit": false, + "illicit/violent": false, + "self-harm/intent": false, + "self-harm/instructions": false, + "self-harm": false, + "sexual/minors": false, + "violence": true, + "violence/graphic": true + }, + "category_scores": { + "harassment": 0.8189693396524255, + "harassment/threatening": 0.804985420696006, + "sexual": 1.573112165348997e-6, + "hate": 0.007562942636942845, + "hate/threatening": 0.004208854591835476, + "illicit": 0.030535955153511665, + "illicit/violent": 0.008925306722380033, + "self-harm/intent": 0.00023023930975076432, + "self-harm/instructions": 0.0002293869201073356, + "self-harm": 0.012598046106750154, + "sexual/minors": 2.212566909570261e-8, + "violence": 0.9999992735124786, + "violence/graphic": 0.843064871157054 + }, + "category_applied_input_types": { + "harassment": [ + "text" + ], + "harassment/threatening": [ + "text" + ], + "sexual": [ + "text", + "image" + ], + "hate": [ + "text" + ], + "hate/threatening": [ + "text" + ], + "illicit": [ + "text" + ], + "illicit/violent": [ + "text" + ], + "self-harm/intent": [ + "text", + "image" + ], + "self-harm/instructions": [ + "text", + "image" + ], + "self-harm": [ + "text", + "image" + ], + "sexual/minors": [ + "text" + ], + "violence": [ + "text", + "image" + ], + "violence/graphic": [ + "text", + "image" + ] + } + } + ] + } + /organization/admin_api_keys: + get: + summary: List organization API keys + operationId: admin-api-keys-list + description: Retrieve a paginated list of organization admin API keys. + parameters: + - in: query + name: after + required: false + schema: + type: string + nullable: true + description: Return keys with IDs that come after this ID in the pagination + order. + - in: query + name: order + required: false + schema: + type: string + enum: + - asc + - desc + default: asc + description: Order results by creation time, ascending or descending. + - in: query + name: limit + required: false + schema: + type: integer + default: 20 + description: Maximum number of keys to return. + responses: + "200": + description: A list of organization API keys. + content: + application/json: + schema: + $ref: "#/components/schemas/ApiKeyList" + x-oaiMeta: + name: List all organization and project API keys. + group: administration + returns: A list of admin and project API key objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/admin_api_keys?after=key_abc&limit=20 \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "list", + "data": [ + { + "object": "organization.admin_api_key", + "id": "key_abc", + "name": "Main Admin Key", + "redacted_value": "sk-admin...def", + "created_at": 1711471533, + "last_used_at": 1711471534, + "owner": { + "type": "service_account", + "object": "organization.service_account", + "id": "sa_456", + "name": "My Service Account", + "created_at": 1711471533, + "role": "member" + } + } + ], + "first_id": "key_abc", + "last_id": "key_abc", + "has_more": false + } + post: + summary: Create an organization admin API key + operationId: admin-api-keys-create + description: Create a new admin-level API key for the organization. + requestBody: + required: true + content: + application/json: + schema: + type: object + required: + - name + properties: + name: + type: string + example: New Admin Key + responses: + "200": + description: The newly created admin API key. + content: + application/json: + schema: + $ref: "#/components/schemas/AdminApiKey" + x-oaiMeta: + name: Create admin API key + group: administration + returns: The created [AdminApiKey](/docs/api-reference/admin-api-keys/object) + object. + examples: + request: + curl: > + curl -X POST https://api.openai.com/v1/organization/admin_api_keys + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "name": "New Admin Key" + }' + response: | + { + "object": "organization.admin_api_key", + "id": "key_xyz", + "name": "New Admin Key", + "redacted_value": "sk-admin...xyz", + "created_at": 1711471533, + "last_used_at": 1711471534, + "owner": { + "type": "user", + "object": "organization.user", + "id": "user_123", + "name": "John Doe", + "created_at": 1711471533, + "role": "owner" + }, + "value": "sk-admin-1234abcd" + } + /organization/admin_api_keys/{key_id}: + get: + summary: Retrieve a single organization API key + operationId: admin-api-keys-get + description: Get details for a specific organization API key by its ID. + parameters: + - in: path + name: key_id + required: true + schema: + type: string + description: The ID of the API key. + responses: + "200": + description: Details of the requested API key. + content: + application/json: + schema: + $ref: "#/components/schemas/AdminApiKey" + x-oaiMeta: + name: Retrieve admin API key + group: administration + returns: The requested [AdminApiKey](/docs/api-reference/admin-api-keys/object) + object. + examples: + request: + curl: > + curl https://api.openai.com/v1/organization/admin_api_keys/key_abc + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.admin_api_key", + "id": "key_abc", + "name": "Main Admin Key", + "redacted_value": "sk-admin...xyz", + "created_at": 1711471533, + "last_used_at": 1711471534, + "owner": { + "type": "user", + "object": "organization.user", + "id": "user_123", + "name": "John Doe", + "created_at": 1711471533, + "role": "owner" + } + } + delete: + summary: Delete an organization admin API key + operationId: admin-api-keys-delete + description: Delete the specified admin API key. + parameters: + - in: path + name: key_id + required: true + schema: + type: string + description: The ID of the API key to be deleted. + responses: + "200": + description: Confirmation that the API key was deleted. + content: + application/json: + schema: + type: object + properties: + id: + type: string + example: key_abc + object: + type: string + example: organization.admin_api_key.deleted + deleted: + type: boolean + example: true + x-oaiMeta: + name: Delete admin API key + group: administration + returns: A confirmation object indicating the key was deleted. + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/organization/admin_api_keys/key_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "id": "key_abc", + "object": "organization.admin_api_key.deleted", + "deleted": true + } + /organization/audit_logs: + get: + summary: List user actions and configuration changes within this organization. + operationId: list-audit-logs + tags: + - Audit Logs + parameters: + - name: effective_at + in: query + description: Return only events whose `effective_at` (Unix seconds) is in this + range. + required: false + schema: + type: object + properties: + gt: + type: integer + description: Return only events whose `effective_at` (Unix seconds) is greater + than this value. + gte: + type: integer + description: Return only events whose `effective_at` (Unix seconds) is greater + than or equal to this value. + lt: + type: integer + description: Return only events whose `effective_at` (Unix seconds) is less than + this value. + lte: + type: integer + description: Return only events whose `effective_at` (Unix seconds) is less than + or equal to this value. + - name: project_ids[] + in: query + description: Return only events for these projects. + required: false + schema: + type: array + items: + type: string + - name: event_types[] + in: query + description: Return only events with a `type` in one of these values. For + example, `project.created`. For all options, see the documentation + for the [audit log object](/docs/api-reference/audit-logs/object). + required: false + schema: + type: array + items: + $ref: "#/components/schemas/AuditLogEventType" + - name: actor_ids[] + in: query + description: Return only events performed by these actors. Can be a user ID, a + service account ID, or an api key tracking ID. + required: false + schema: + type: array + items: + type: string + - name: actor_emails[] + in: query + description: Return only events performed by users with these emails. + required: false + schema: + type: array + items: + type: string + - name: resource_ids[] + in: query + description: Return only events performed on these targets. For example, a + project ID updated. + required: false + schema: + type: array + items: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + responses: + "200": + description: Audit logs listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListAuditLogsResponse" + x-oaiMeta: + name: List audit logs + group: audit-logs + returns: A list of paginated [Audit Log](/docs/api-reference/audit-logs/object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/audit_logs \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: > + { + "object": "list", + "data": [ + { + "id": "audit_log-xxx_yyyymmdd", + "type": "project.archived", + "effective_at": 1722461446, + "actor": { + "type": "api_key", + "api_key": { + "type": "user", + "user": { + "id": "user-xxx", + "email": "user@example.com" + } + } + }, + "project.archived": { + "id": "proj_abc" + }, + }, + { + "id": "audit_log-yyy__20240101", + "type": "api_key.updated", + "effective_at": 1720804190, + "actor": { + "type": "session", + "session": { + "user": { + "id": "user-xxx", + "email": "user@example.com" + }, + "ip_address": "127.0.0.1", + "user_agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36", + "ja3": "a497151ce4338a12c4418c44d375173e", + "ja4": "q13d0313h3_55b375c5d22e_c7319ce65786", + "ip_address_details": { + "country": "US", + "city": "San Francisco", + "region": "California", + "region_code": "CA", + "asn": "1234", + "latitude": "37.77490", + "longitude": "-122.41940" + } + } + }, + "api_key.updated": { + "id": "key_xxxx", + "data": { + "scopes": ["resource_2.operation_2"] + } + }, + } + ], + "first_id": "audit_log-xxx__20240101", + "last_id": "audit_log_yyy__20240101", + "has_more": true + } + /organization/certificates: + get: + summary: List uploaded certificates for this organization. + operationId: listOrganizationCertificates + tags: + - Certificates + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + responses: + "200": + description: Certificates listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListCertificatesResponse" + x-oaiMeta: + name: List organization certificates + group: administration + returns: A list of [Certificate](/docs/api-reference/certificates/object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/certificates \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" + response: | + { + "object": "list", + "data": [ + { + "object": "organization.certificate", + "id": "cert_abc", + "name": "My Example Certificate", + "active": true, + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + }, + ], + "first_id": "cert_abc", + "last_id": "cert_abc", + "has_more": false + } + post: + summary: > + Upload a certificate to the organization. This does **not** + automatically activate the certificate. + + + Organizations can upload up to 50 certificates. + operationId: uploadCertificate + tags: + - Certificates + requestBody: + description: The certificate upload payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/UploadCertificateRequest" + responses: + "200": + description: Certificate uploaded successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Certificate" + x-oaiMeta: + name: Upload certificate + group: administration + returns: A single [Certificate](/docs/api-reference/certificates/object) object. + examples: + request: + curl: > + curl -X POST https://api.openai.com/v1/organization/certificates \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" \ + + -d '{ + "name": "My Example Certificate", + "certificate": "-----BEGIN CERTIFICATE-----\\nMIIDeT...\\n-----END CERTIFICATE-----" + }' + response: | + { + "object": "certificate", + "id": "cert_abc", + "name": "My Example Certificate", + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + } + /organization/certificates/activate: + post: + summary: > + Activate certificates at the organization level. + + + You can atomically and idempotently activate up to 10 certificates at a + time. + operationId: activateOrganizationCertificates + tags: + - Certificates + requestBody: + description: The certificate activation payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ToggleCertificatesRequest" + responses: + "200": + description: Certificates activated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListCertificatesResponse" + x-oaiMeta: + name: Activate certificates for organization + group: administration + returns: A list of [Certificate](/docs/api-reference/certificates/object) + objects that were activated. + examples: + request: + curl: > + curl https://api.openai.com/v1/organization/certificates/activate + \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" \ + + -d '{ + "data": ["cert_abc", "cert_def"] + }' + response: | + { + "object": "organization.certificate.activation", + "data": [ + { + "object": "organization.certificate", + "id": "cert_abc", + "name": "My Example Certificate", + "active": true, + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + }, + { + "object": "organization.certificate", + "id": "cert_def", + "name": "My Example Certificate 2", + "active": true, + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + }, + ], + } + /organization/certificates/deactivate: + post: + summary: > + Deactivate certificates at the organization level. + + + You can atomically and idempotently deactivate up to 10 certificates at + a time. + operationId: deactivateOrganizationCertificates + tags: + - Certificates + requestBody: + description: The certificate deactivation payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ToggleCertificatesRequest" + responses: + "200": + description: Certificates deactivated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListCertificatesResponse" + x-oaiMeta: + name: Deactivate certificates for organization + group: administration + returns: A list of [Certificate](/docs/api-reference/certificates/object) + objects that were deactivated. + examples: + request: + curl: > + curl + https://api.openai.com/v1/organization/certificates/deactivate \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" \ + + -d '{ + "data": ["cert_abc", "cert_def"] + }' + response: | + { + "object": "organization.certificate.deactivation", + "data": [ + { + "object": "organization.certificate", + "id": "cert_abc", + "name": "My Example Certificate", + "active": false, + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + }, + { + "object": "organization.certificate", + "id": "cert_def", + "name": "My Example Certificate 2", + "active": false, + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + }, + ], + } + /organization/certificates/{certificate_id}: + get: + summary: | + Get a certificate that has been uploaded to the organization. + + You can get a certificate regardless of whether it is active or not. + operationId: getCertificate + tags: + - Certificates + parameters: + - name: certificate_id + in: path + description: Unique ID of the certificate to retrieve. + required: true + schema: + type: string + - name: include + in: query + description: A list of additional fields to include in the response. Currently + the only supported value is `content` to fetch the PEM content of + the certificate. + required: false + schema: + type: array + items: + type: string + enum: + - content + responses: + "200": + description: Certificate retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Certificate" + x-oaiMeta: + name: Get certificate + group: administration + returns: A single [Certificate](/docs/api-reference/certificates/object) object. + examples: + request: + curl: | + curl "https://api.openai.com/v1/organization/certificates/cert_abc?include[]=content" \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" + response: > + { + "object": "certificate", + "id": "cert_abc", + "name": "My Example Certificate", + "created_at": 1234567, + "certificate_details": { + "valid_at": 1234567, + "expires_at": 12345678, + "content": "-----BEGIN CERTIFICATE-----MIIDeT...-----END CERTIFICATE-----" + } + } + post: + summary: | + Modify a certificate. Note that only the name can be modified. + operationId: modifyCertificate + tags: + - Certificates + requestBody: + description: The certificate modification payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ModifyCertificateRequest" + responses: + "200": + description: Certificate modified successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Certificate" + x-oaiMeta: + name: Modify certificate + group: administration + returns: The updated [Certificate](/docs/api-reference/certificates/object) + object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/organization/certificates/cert_abc \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + + -H "Content-Type: application/json" \ + + -d '{ + "name": "Renamed Certificate" + }' + response: | + { + "object": "certificate", + "id": "cert_abc", + "name": "Renamed Certificate", + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + } + delete: + summary: | + Delete a certificate from the organization. + + The certificate must be inactive for the organization and all projects. + operationId: deleteCertificate + tags: + - Certificates + responses: + "200": + description: Certificate deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteCertificateResponse" + x-oaiMeta: + name: Delete certificate + group: administration + returns: A confirmation object indicating the certificate was deleted. + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/organization/certificates/cert_abc \ + + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" + response: | + { + "object": "certificate.deleted", + "id": "cert_abc" + } + /organization/costs: + get: + summary: Get costs details for the organization. + operationId: usage-costs + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently only `1d` is + supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1d + default: 1d + - name: project_ids + in: query + description: Return only costs for these projects. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the costs by the specified fields. Support fields include + `project_id`, `line_item` and any combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - line_item + - name: limit + in: query + description: > + A limit on the number of buckets to be returned. Limit can range + between 1 and 180, and the default is 7. + required: false + schema: + type: integer + default: 7 + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Costs data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Costs + group: usage-costs + returns: A list of paginated, time bucketed + [Costs](/docs/api-reference/usage/costs_object) objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/organization/costs?start_time=1730419200&limit=1" \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.costs.result", + "amount": { + "value": 0.06, + "currency": "usd" + }, + "line_item": null, + "project_id": null + } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/invites: + get: + summary: Returns a list of invites in the organization. + operationId: list-invites + tags: + - Invites + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + responses: + "200": + description: Invites listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/InviteListResponse" + x-oaiMeta: + name: List invites + group: administration + returns: A list of [Invite](/docs/api-reference/invite/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/invites?after=invite-abc&limit=20 \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "list", + "data": [ + { + "object": "organization.invite", + "id": "invite-abc", + "email": "user@example.com", + "role": "owner", + "status": "accepted", + "invited_at": 1711471533, + "expires_at": 1711471533, + "accepted_at": 1711471533 + } + ], + "first_id": "invite-abc", + "last_id": "invite-abc", + "has_more": false + } + post: + summary: Create an invite for a user to the organization. The invite must be + accepted by the user before they have access to the organization. + operationId: inviteUser + tags: + - Invites + requestBody: + description: The invite request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/InviteRequest" + responses: + "200": + description: User invited successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Invite" + x-oaiMeta: + name: Create invite + group: administration + returns: The created [Invite](/docs/api-reference/invite/object) object. + examples: + request: + curl: | + curl -X POST https://api.openai.com/v1/organization/invites \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "email": "anotheruser@example.com", + "role": "reader", + "projects": [ + { + "id": "project-xyz", + "role": "member" + }, + { + "id": "project-abc", + "role": "owner" + } + ] + }' + response: | + { + "object": "organization.invite", + "id": "invite-def", + "email": "anotheruser@example.com", + "role": "reader", + "status": "pending", + "invited_at": 1711471533, + "expires_at": 1711471533, + "accepted_at": null, + "projects": [ + { + "id": "project-xyz", + "role": "member" + }, + { + "id": "project-abc", + "role": "owner" + } + ] + } + /organization/invites/{invite_id}: + get: + summary: Retrieves an invite. + operationId: retrieve-invite + tags: + - Invites + parameters: + - in: path + name: invite_id + required: true + schema: + type: string + description: The ID of the invite to retrieve. + responses: + "200": + description: Invite retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Invite" + x-oaiMeta: + name: Retrieve invite + group: administration + returns: The [Invite](/docs/api-reference/invite/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/invites/invite-abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.invite", + "id": "invite-abc", + "email": "user@example.com", + "role": "owner", + "status": "accepted", + "invited_at": 1711471533, + "expires_at": 1711471533, + "accepted_at": 1711471533 + } + delete: + summary: Delete an invite. If the invite has already been accepted, it cannot be + deleted. + operationId: delete-invite + tags: + - Invites + parameters: + - in: path + name: invite_id + required: true + schema: + type: string + description: The ID of the invite to delete. + responses: + "200": + description: Invite deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/InviteDeleteResponse" + x-oaiMeta: + name: Delete invite + group: administration + returns: Confirmation that the invite has been deleted + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/organization/invites/invite-abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.invite.deleted", + "id": "invite-abc", + "deleted": true + } + /organization/projects: + get: + summary: Returns a list of projects. + operationId: list-projects + tags: + - Projects + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + - name: include_archived + in: query + schema: + type: boolean + default: false + description: If `true` returns all projects including those that have been + `archived`. Archived projects are not included by default. + responses: + "200": + description: Projects listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectListResponse" + x-oaiMeta: + name: List projects + group: administration + returns: A list of [Project](/docs/api-reference/projects/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects?after=proj_abc&limit=20&include_archived=false \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "list", + "data": [ + { + "id": "proj_abc", + "object": "organization.project", + "name": "Project example", + "created_at": 1711471533, + "archived_at": null, + "status": "active" + } + ], + "first_id": "proj-abc", + "last_id": "proj-xyz", + "has_more": false + } + post: + summary: Create a new project in the organization. Projects can be created and + archived, but cannot be deleted. + operationId: create-project + tags: + - Projects + requestBody: + description: The project create request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectCreateRequest" + responses: + "200": + description: Project created successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Project" + x-oaiMeta: + name: Create project + group: administration + returns: The created [Project](/docs/api-reference/projects/object) object. + examples: + request: + curl: | + curl -X POST https://api.openai.com/v1/organization/projects \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "name": "Project ABC" + }' + response: | + { + "id": "proj_abc", + "object": "organization.project", + "name": "Project ABC", + "created_at": 1711471533, + "archived_at": null, + "status": "active" + } + /organization/projects/{project_id}: + get: + summary: Retrieves a project. + operationId: retrieve-project + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + responses: + "200": + description: Project retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Project" + x-oaiMeta: + name: Retrieve project + group: administration + description: Retrieve a project. + returns: The [Project](/docs/api-reference/projects/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "id": "proj_abc", + "object": "organization.project", + "name": "Project example", + "created_at": 1711471533, + "archived_at": null, + "status": "active" + } + post: + summary: Modifies a project in the organization. + operationId: modify-project + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + requestBody: + description: The project update request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUpdateRequest" + responses: + "200": + description: Project updated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Project" + "400": + description: Error response when updating the default project. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Modify project + group: administration + returns: The updated [Project](/docs/api-reference/projects/object) object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/organization/projects/proj_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "name": "Project DEF" + }' + /organization/projects/{project_id}/api_keys: + get: + summary: Returns a list of API keys in the project. + operationId: list-project-api-keys + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + responses: + "200": + description: Project API keys listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectApiKeyListResponse" + x-oaiMeta: + name: List project API keys + group: administration + returns: A list of [ProjectApiKey](/docs/api-reference/project-api-keys/object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc/api_keys?after=key_abc&limit=20 \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "list", + "data": [ + { + "object": "organization.project.api_key", + "redacted_value": "sk-abc...def", + "name": "My API Key", + "created_at": 1711471533, + "last_used_at": 1711471534, + "id": "key_abc", + "owner": { + "type": "user", + "user": { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + } + } + ], + "first_id": "key_abc", + "last_id": "key_xyz", + "has_more": false + } + /organization/projects/{project_id}/api_keys/{key_id}: + get: + summary: Retrieves an API key in the project. + operationId: retrieve-project-api-key + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: key_id + in: path + description: The ID of the API key. + required: true + schema: + type: string + responses: + "200": + description: Project API key retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectApiKey" + x-oaiMeta: + name: Retrieve project API key + group: administration + returns: The [ProjectApiKey](/docs/api-reference/project-api-keys/object) object + matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc/api_keys/key_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.project.api_key", + "redacted_value": "sk-abc...def", + "name": "My API Key", + "created_at": 1711471533, + "last_used_at": 1711471534, + "id": "key_abc", + "owner": { + "type": "user", + "user": { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + } + } + delete: + summary: Deletes an API key from the project. + operationId: delete-project-api-key + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: key_id + in: path + description: The ID of the API key. + required: true + schema: + type: string + responses: + "200": + description: Project API key deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectApiKeyDeleteResponse" + "400": + description: Error response for various conditions. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Delete project API key + group: administration + returns: Confirmation of the key's deletion or an error if the key belonged to a + service account + examples: + request: + curl: | + curl -X DELETE https://api.openai.com/v1/organization/projects/proj_abc/api_keys/key_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.project.api_key.deleted", + "id": "key_abc", + "deleted": true + } + /organization/projects/{project_id}/archive: + post: + summary: Archives a project in the organization. Archived projects cannot be + used or updated. + operationId: archive-project + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + responses: + "200": + description: Project archived successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/Project" + x-oaiMeta: + name: Archive project + group: administration + returns: The archived [Project](/docs/api-reference/projects/object) object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/organization/projects/proj_abc/archive \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "id": "proj_abc", + "object": "organization.project", + "name": "Project DEF", + "created_at": 1711471533, + "archived_at": 1711471533, + "status": "archived" + } + /organization/projects/{project_id}/certificates: + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + get: + summary: List certificates for this project. + operationId: listProjectCertificates + tags: + - Certificates + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + responses: + "200": + description: Certificates listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListCertificatesResponse" + x-oaiMeta: + name: List project certificates + group: administration + returns: A list of [Certificate](/docs/api-reference/certificates/object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc/certificates \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" + response: | + { + "object": "list", + "data": [ + { + "object": "organization.project.certificate", + "id": "cert_abc", + "name": "My Example Certificate", + "active": true, + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + }, + ], + "first_id": "cert_abc", + "last_id": "cert_abc", + "has_more": false + } + /organization/projects/{project_id}/certificates/activate: + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + post: + summary: > + Activate certificates at the project level. + + + You can atomically and idempotently activate up to 10 certificates at a + time. + operationId: activateProjectCertificates + tags: + - Certificates + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + requestBody: + description: The certificate activation payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ToggleCertificatesRequest" + responses: + "200": + description: Certificates activated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListCertificatesResponse" + x-oaiMeta: + name: Activate certificates for project + group: administration + returns: A list of [Certificate](/docs/api-reference/certificates/object) + objects that were activated. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc/certificates/activate \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "data": ["cert_abc", "cert_def"] + }' + response: | + { + "object": "organization.project.certificate.activation", + "data": [ + { + "object": "organization.project.certificate", + "id": "cert_abc", + "name": "My Example Certificate", + "active": true, + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + }, + { + "object": "organization.project.certificate", + "id": "cert_def", + "name": "My Example Certificate 2", + "active": true, + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + }, + ], + } + /organization/projects/{project_id}/certificates/deactivate: + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + post: + summary: | + Deactivate certificates at the project level. You can atomically and + idempotently deactivate up to 10 certificates at a time. + operationId: deactivateProjectCertificates + tags: + - Certificates + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + requestBody: + description: The certificate deactivation payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ToggleCertificatesRequest" + responses: + "200": + description: Certificates deactivated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ListCertificatesResponse" + x-oaiMeta: + name: Deactivate certificates for project + group: administration + returns: A list of [Certificate](/docs/api-reference/certificates/object) + objects that were deactivated. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc/certificates/deactivate \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "data": ["cert_abc", "cert_def"] + }' + response: | + { + "object": "organization.project.certificate.deactivation", + "data": [ + { + "object": "organization.project.certificate", + "id": "cert_abc", + "name": "My Example Certificate", + "active": false, + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + }, + { + "object": "organization.project.certificate", + "id": "cert_def", + "name": "My Example Certificate 2", + "active": false, + "created_at": 1234567, + "certificate_details": { + "valid_at": 12345667, + "expires_at": 12345678 + } + }, + ], + } + /organization/projects/{project_id}/rate_limits: + get: + summary: Returns the rate limits per model for a project. + operationId: list-project-rate-limits + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: limit + in: query + description: | + A limit on the number of objects to be returned. The default is 100. + required: false + schema: + type: integer + default: 100 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, beginning with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + required: false + schema: + type: string + responses: + "200": + description: Project rate limits listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectRateLimitListResponse" + x-oaiMeta: + name: List project rate limits + group: administration + returns: A list of + [ProjectRateLimit](/docs/api-reference/project-rate-limits/object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc/rate_limits?after=rl_xxx&limit=20 \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "list", + "data": [ + { + "object": "project.rate_limit", + "id": "rl-ada", + "model": "ada", + "max_requests_per_1_minute": 600, + "max_tokens_per_1_minute": 150000, + "max_images_per_1_minute": 10 + } + ], + "first_id": "rl-ada", + "last_id": "rl-ada", + "has_more": false + } + error_response: | + { + "code": 404, + "message": "The project {project_id} was not found" + } + /organization/projects/{project_id}/rate_limits/{rate_limit_id}: + post: + summary: Updates a project rate limit. + operationId: update-project-rate-limits + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: rate_limit_id + in: path + description: The ID of the rate limit. + required: true + schema: + type: string + requestBody: + description: The project rate limit update request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectRateLimitUpdateRequest" + responses: + "200": + description: Project rate limit updated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectRateLimit" + "400": + description: Error response for various conditions. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Modify project rate limit + group: administration + returns: The updated + [ProjectRateLimit](/docs/api-reference/project-rate-limits/object) + object. + examples: + request: + curl: | + curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/rate_limits/rl_xxx \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "max_requests_per_1_minute": 500 + }' + response: | + { + "object": "project.rate_limit", + "id": "rl-ada", + "model": "ada", + "max_requests_per_1_minute": 600, + "max_tokens_per_1_minute": 150000, + "max_images_per_1_minute": 10 + } + error_response: | + { + "code": 404, + "message": "The project {project_id} was not found" + } + /organization/projects/{project_id}/service_accounts: + get: + summary: Returns a list of service accounts in the project. + operationId: list-project-service-accounts + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + responses: + "200": + description: Project service accounts listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectServiceAccountListResponse" + "400": + description: Error response when project is archived. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: List project service accounts + group: administration + returns: A list of + [ProjectServiceAccount](/docs/api-reference/project-service-accounts/object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc/service_accounts?after=custom_id&limit=20 \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "list", + "data": [ + { + "object": "organization.project.service_account", + "id": "svc_acct_abc", + "name": "Service Account", + "role": "owner", + "created_at": 1711471533 + } + ], + "first_id": "svc_acct_abc", + "last_id": "svc_acct_xyz", + "has_more": false + } + post: + summary: Creates a new service account in the project. This also returns an + unredacted API key for the service account. + operationId: create-project-service-account + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + requestBody: + description: The project service account create request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectServiceAccountCreateRequest" + responses: + "200": + description: Project service account created successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectServiceAccountCreateResponse" + "400": + description: Error response when project is archived. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Create project service account + group: administration + returns: The created + [ProjectServiceAccount](/docs/api-reference/project-service-accounts/object) + object. + examples: + request: + curl: | + curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/service_accounts \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "name": "Production App" + }' + response: | + { + "object": "organization.project.service_account", + "id": "svc_acct_abc", + "name": "Production App", + "role": "member", + "created_at": 1711471533, + "api_key": { + "object": "organization.project.service_account.api_key", + "value": "sk-abcdefghijklmnop123", + "name": "Secret Key", + "created_at": 1711471533, + "id": "key_abc" + } + } + /organization/projects/{project_id}/service_accounts/{service_account_id}: + get: + summary: Retrieves a service account in the project. + operationId: retrieve-project-service-account + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: service_account_id + in: path + description: The ID of the service account. + required: true + schema: + type: string + responses: + "200": + description: Project service account retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectServiceAccount" + x-oaiMeta: + name: Retrieve project service account + group: administration + returns: The + [ProjectServiceAccount](/docs/api-reference/project-service-accounts/object) + object matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc/service_accounts/svc_acct_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.project.service_account", + "id": "svc_acct_abc", + "name": "Service Account", + "role": "owner", + "created_at": 1711471533 + } + delete: + summary: Deletes a service account from the project. + operationId: delete-project-service-account + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: service_account_id + in: path + description: The ID of the service account. + required: true + schema: + type: string + responses: + "200": + description: Project service account deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectServiceAccountDeleteResponse" + x-oaiMeta: + name: Delete project service account + group: administration + returns: Confirmation of service account being deleted, or an error in case of + an archived project, which has no service accounts + examples: + request: + curl: | + curl -X DELETE https://api.openai.com/v1/organization/projects/proj_abc/service_accounts/svc_acct_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.project.service_account.deleted", + "id": "svc_acct_abc", + "deleted": true + } + /organization/projects/{project_id}/users: + get: + summary: Returns a list of users in the project. + operationId: list-project-users + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + responses: + "200": + description: Project users listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUserListResponse" + "400": + description: Error response when project is archived. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: List project users + group: administration + returns: A list of [ProjectUser](/docs/api-reference/project-users/object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc/users?after=user_abc&limit=20 \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "list", + "data": [ + { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + ], + "first_id": "user-abc", + "last_id": "user-xyz", + "has_more": false + } + post: + summary: Adds a user to the project. Users must already be members of the + organization to be added to a project. + operationId: create-project-user + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + tags: + - Projects + requestBody: + description: The project user create request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUserCreateRequest" + responses: + "200": + description: User added to project successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUser" + "400": + description: Error response for various conditions. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Create project user + group: administration + returns: The created [ProjectUser](/docs/api-reference/project-users/object) + object. + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/organization/projects/proj_abc/users \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "user_id": "user_abc", + "role": "member" + }' + response: | + { + "object": "organization.project.user", + "id": "user_abc", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + /organization/projects/{project_id}/users/{user_id}: + get: + summary: Retrieves a user in the project. + operationId: retrieve-project-user + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + responses: + "200": + description: Project user retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUser" + x-oaiMeta: + name: Retrieve project user + group: administration + returns: The [ProjectUser](/docs/api-reference/project-users/object) object + matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/projects/proj_abc/users/user_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + post: + summary: Modifies a user's role in the project. + operationId: modify-project-user + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + requestBody: + description: The project user update request payload. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUserUpdateRequest" + responses: + "200": + description: Project user's role updated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUser" + "400": + description: Error response for various conditions. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Modify project user + group: administration + returns: The updated [ProjectUser](/docs/api-reference/project-users/object) + object. + examples: + request: + curl: | + curl -X POST https://api.openai.com/v1/organization/projects/proj_abc/users/user_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "role": "owner" + }' + response: | + { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + delete: + summary: Deletes a user from the project. + operationId: delete-project-user + tags: + - Projects + parameters: + - name: project_id + in: path + description: The ID of the project. + required: true + schema: + type: string + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + responses: + "200": + description: Project user deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/ProjectUserDeleteResponse" + "400": + description: Error response for various conditions. + content: + application/json: + schema: + $ref: "#/components/schemas/ErrorResponse" + x-oaiMeta: + name: Delete project user + group: administration + returns: Confirmation that project has been deleted or an error in case of an + archived project, which has no users + examples: + request: + curl: | + curl -X DELETE https://api.openai.com/v1/organization/projects/proj_abc/users/user_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.project.user.deleted", + "id": "user_abc", + "deleted": true + } + /organization/usage/audio_speeches: + get: + summary: Get audio speeches usage details for the organization. + operationId: usage-audio-speeches + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Audio speeches + group: usage-audio-speeches + returns: A list of paginated, time bucketed [Audio speeches + usage](/docs/api-reference/usage/audio_speeches_object) objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/organization/usage/audio_speeches?start_time=1730419200&limit=1" \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.audio_speeches.result", + "characters": 45, + "num_model_requests": 1, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null + } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/audio_transcriptions: + get: + summary: Get audio transcriptions usage details for the organization. + operationId: usage-audio-transcriptions + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Audio transcriptions + group: usage-audio-transcriptions + returns: A list of paginated, time bucketed [Audio transcriptions + usage](/docs/api-reference/usage/audio_transcriptions_object) objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/organization/usage/audio_transcriptions?start_time=1730419200&limit=1" \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.audio_transcriptions.result", + "seconds": 20, + "num_model_requests": 1, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null + } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/code_interpreter_sessions: + get: + summary: Get code interpreter sessions usage details for the organization. + operationId: usage-code-interpreter-sessions + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Code interpreter sessions + group: usage-code-interpreter-sessions + returns: A list of paginated, time bucketed [Code interpreter sessions + usage](/docs/api-reference/usage/code_interpreter_sessions_object) + objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/organization/usage/code_interpreter_sessions?start_time=1730419200&limit=1" \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.code_interpreter_sessions.result", + "num_sessions": 1, + "project_id": null + } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/completions: + get: + summary: Get completions usage details for the organization. + operationId: usage-completions + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: batch + in: query + description: > + If `true`, return batch jobs only. If `false`, return non-batch jobs + only. By default, return both. + required: false + schema: + type: boolean + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model`, `batch` or + any combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - batch + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Completions + group: usage-completions + returns: A list of paginated, time bucketed [Completions + usage](/docs/api-reference/usage/completions_object) objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/organization/usage/completions?start_time=1730419200&limit=1" \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.completions.result", + "input_tokens": 1000, + "output_tokens": 500, + "input_cached_tokens": 800, + "input_audio_tokens": 0, + "output_audio_tokens": 0, + "num_model_requests": 5, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null, + "batch": null + } + ] + } + ], + "has_more": true, + "next_page": "page_AAAAAGdGxdEiJdKOAAAAAGcqsYA=" + } + /organization/usage/embeddings: + get: + summary: Get embeddings usage details for the organization. + operationId: usage-embeddings + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Embeddings + group: usage-embeddings + returns: A list of paginated, time bucketed [Embeddings + usage](/docs/api-reference/usage/embeddings_object) objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/organization/usage/embeddings?start_time=1730419200&limit=1" \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.embeddings.result", + "input_tokens": 16, + "num_model_requests": 2, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null + } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/images: + get: + summary: Get images usage details for the organization. + operationId: usage-images + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: sources + in: query + description: Return only usages for these sources. Possible values are + `image.generation`, `image.edit`, `image.variation` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - image.generation + - image.edit + - image.variation + - name: sizes + in: query + description: Return only usages for these image sizes. Possible values are + `256x256`, `512x512`, `1024x1024`, `1792x1792`, `1024x1792` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - 256x256 + - 512x512 + - 1024x1024 + - 1792x1792 + - 1024x1792 + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model`, `size`, + `source` or any combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - size + - source + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Images + group: usage-images + returns: A list of paginated, time bucketed [Images + usage](/docs/api-reference/usage/images_object) objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/organization/usage/images?start_time=1730419200&limit=1" \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.images.result", + "images": 2, + "num_model_requests": 2, + "size": null, + "source": null, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null + } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/moderations: + get: + summary: Get moderations usage details for the organization. + operationId: usage-moderations + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: user_ids + in: query + description: Return only usage for these users. + required: false + schema: + type: array + items: + type: string + - name: api_key_ids + in: query + description: Return only usage for these API keys. + required: false + schema: + type: array + items: + type: string + - name: models + in: query + description: Return only usage for these models. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`, `user_id`, `api_key_id`, `model` or any + combination of them. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - user_id + - api_key_id + - model + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Moderations + group: usage-moderations + returns: A list of paginated, time bucketed [Moderations + usage](/docs/api-reference/usage/moderations_object) objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/organization/usage/moderations?start_time=1730419200&limit=1" \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.moderations.result", + "input_tokens": 16, + "num_model_requests": 2, + "project_id": null, + "user_id": null, + "api_key_id": null, + "model": null + } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/usage/vector_stores: + get: + summary: Get vector stores usage details for the organization. + operationId: usage-vector-stores + tags: + - Usage + parameters: + - name: start_time + in: query + description: Start time (Unix seconds) of the query time range, inclusive. + required: true + schema: + type: integer + - name: end_time + in: query + description: End time (Unix seconds) of the query time range, exclusive. + required: false + schema: + type: integer + - name: bucket_width + in: query + description: Width of each time bucket in response. Currently `1m`, `1h` and + `1d` are supported, default to `1d`. + required: false + schema: + type: string + enum: + - 1m + - 1h + - 1d + default: 1d + - name: project_ids + in: query + description: Return only usage for these projects. + required: false + schema: + type: array + items: + type: string + - name: group_by + in: query + description: Group the usage data by the specified fields. Support fields + include `project_id`. + required: false + schema: + type: array + items: + type: string + enum: + - project_id + - name: limit + in: query + description: | + Specifies the number of buckets to return. + - `bucket_width=1d`: default: 7, max: 31 + - `bucket_width=1h`: default: 24, max: 168 + - `bucket_width=1m`: default: 60, max: 1440 + required: false + schema: + type: integer + - name: page + in: query + description: A cursor for use in pagination. Corresponding to the `next_page` + field from the previous response. + schema: + type: string + responses: + "200": + description: Usage data retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UsageResponse" + x-oaiMeta: + name: Vector stores + group: usage-vector-stores + returns: A list of paginated, time bucketed [Vector stores + usage](/docs/api-reference/usage/vector_stores_object) objects. + examples: + request: + curl: | + curl "https://api.openai.com/v1/organization/usage/vector_stores?start_time=1730419200&limit=1" \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: > + { + "object": "page", + "data": [ + { + "object": "bucket", + "start_time": 1730419200, + "end_time": 1730505600, + "results": [ + { + "object": "organization.usage.vector_stores.result", + "usage_bytes": 1024, + "project_id": null + } + ] + } + ], + "has_more": false, + "next_page": null + } + /organization/users: + get: + summary: Lists all of the users in the organization. + operationId: list-users + tags: + - Users + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + required: false + schema: + type: string + - name: emails + in: query + description: Filter by the email address of users. + required: false + schema: + type: array + items: + type: string + responses: + "200": + description: Users listed successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UserListResponse" + x-oaiMeta: + name: List users + group: administration + returns: A list of [User](/docs/api-reference/users/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/users?after=user_abc&limit=20 \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "list", + "data": [ + { + "object": "organization.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + ], + "first_id": "user-abc", + "last_id": "user-xyz", + "has_more": false + } + /organization/users/{user_id}: + get: + summary: Retrieves a user by their identifier. + operationId: retrieve-user + tags: + - Users + parameters: + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + responses: + "200": + description: User retrieved successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/User" + x-oaiMeta: + name: Retrieve user + group: administration + returns: The [User](/docs/api-reference/users/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/organization/users/user_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + post: + summary: Modifies a user's role in the organization. + operationId: modify-user + tags: + - Users + parameters: + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + requestBody: + description: The new user role to modify. This must be one of `owner` or `member`. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/UserRoleUpdateRequest" + responses: + "200": + description: User role updated successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/User" + x-oaiMeta: + name: Modify user + group: administration + returns: The updated [User](/docs/api-reference/users/object) object. + examples: + request: + curl: > + curl -X POST https://api.openai.com/v1/organization/users/user_abc + \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "role": "owner" + }' + response: | + { + "object": "organization.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + delete: + summary: Deletes a user from the organization. + operationId: delete-user + tags: + - Users + parameters: + - name: user_id + in: path + description: The ID of the user. + required: true + schema: + type: string + responses: + "200": + description: User deleted successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/UserDeleteResponse" + x-oaiMeta: + name: Delete user + group: administration + returns: Confirmation of the deleted user + examples: + request: + curl: > + curl -X DELETE + https://api.openai.com/v1/organization/users/user_abc \ + -H "Authorization: Bearer $OPENAI_ADMIN_KEY" \ + -H "Content-Type: application/json" + response: | + { + "object": "organization.user.deleted", + "id": "user_abc", + "deleted": true + } + /realtime/sessions: + post: + summary: > + Create an ephemeral API token for use in client-side applications with + the + + Realtime API. Can be configured with the same session parameters as the + + `session.update` client event. + + + It responds with a session object, plus a `client_secret` key which + contains + + a usable ephemeral API token that can be used to authenticate browser + clients + + for the Realtime API. + operationId: create-realtime-session + tags: + - Realtime + requestBody: + description: Create an ephemeral API key with the given session configuration. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/RealtimeSessionCreateRequest" + responses: + "200": + description: Session created successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/RealtimeSessionCreateResponse" + x-oaiMeta: + name: Create session + group: realtime + returns: The created Realtime session object, plus an ephemeral key + examples: + request: + curl: | + curl -X POST https://api.openai.com/v1/realtime/sessions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{ + "model": "gpt-4o-realtime-preview", + "modalities": ["audio", "text"], + "instructions": "You are a friendly assistant." + }' + response: | + { + "id": "sess_001", + "object": "realtime.session", + "model": "gpt-4o-realtime-preview", + "modalities": ["audio", "text"], + "instructions": "You are a friendly assistant.", + "voice": "alloy", + "input_audio_format": "pcm16", + "output_audio_format": "pcm16", + "input_audio_transcription": { + "model": "whisper-1" + }, + "turn_detection": null, + "tools": [], + "tool_choice": "none", + "temperature": 0.7, + "max_response_output_tokens": 200, + "speed": 1.1, + "tracing": "auto", + "client_secret": { + "value": "ek_abc123", + "expires_at": 1234567890 + } + } + /realtime/transcription_sessions: + post: + summary: > + Create an ephemeral API token for use in client-side applications with + the + + Realtime API specifically for realtime transcriptions. + + Can be configured with the same session parameters as the + `transcription_session.update` client event. + + + It responds with a session object, plus a `client_secret` key which + contains + + a usable ephemeral API token that can be used to authenticate browser + clients + + for the Realtime API. + operationId: create-realtime-transcription-session + tags: + - Realtime + requestBody: + description: Create an ephemeral API key with the given session configuration. + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/RealtimeTranscriptionSessionCreateRequest" + responses: + "200": + description: Session created successfully. + content: + application/json: + schema: + $ref: "#/components/schemas/RealtimeTranscriptionSessionCreateResponse" + x-oaiMeta: + name: Create transcription session + group: realtime + returns: The created [Realtime transcription session + object](/docs/api-reference/realtime-sessions/transcription_session_object), + plus an ephemeral key + examples: + request: + curl: > + curl -X POST + https://api.openai.com/v1/realtime/transcription_sessions \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{}' + response: | + { + "id": "sess_BBwZc7cFV3XizEyKGDCGL", + "object": "realtime.transcription_session", + "modalities": ["audio", "text"], + "turn_detection": { + "type": "server_vad", + "threshold": 0.5, + "prefix_padding_ms": 300, + "silence_duration_ms": 200 + }, + "input_audio_format": "pcm16", + "input_audio_transcription": { + "model": "gpt-4o-transcribe", + "language": null, + "prompt": "" + }, + "client_secret": null + } + /responses: + post: + operationId: createResponse + tags: + - Responses + summary: > + Creates a model response. Provide [text](/docs/guides/text) or + + [image](/docs/guides/images) inputs to generate + [text](/docs/guides/text) + + or [JSON](/docs/guides/structured-outputs) outputs. Have the model call + + your own [custom code](/docs/guides/function-calling) or use built-in + + [tools](/docs/guides/tools) like [web + search](/docs/guides/tools-web-search) + + or [file search](/docs/guides/tools-file-search) to use your own data + + as input for the model's response. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateResponse" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Response" + text/event-stream: + schema: + $ref: "#/components/schemas/ResponseStreamEvent" + x-oaiMeta: + name: Create a model response + group: responses + returns: | + Returns a [Response](/docs/api-reference/responses/object) object. + path: create + examples: + - title: Text input + request: + curl: > + curl https://api.openai.com/v1/responses \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "gpt-4.1", + "input": "Tell me a three sentence bedtime story about a unicorn." + }' + javascript: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const response = await openai.responses.create({ + model: "gpt-4.1", + input: "Tell me a three sentence bedtime story about a unicorn." + }); + + + console.log(response); + python: > + from openai import OpenAI + + + client = OpenAI() + + + response = client.responses.create( + model="gpt-4.1", + input="Tell me a three sentence bedtime story about a unicorn." + ) + + + print(response) + csharp: > + using System; + + using OpenAI.Responses; + + + OpenAIResponseClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + OpenAIResponse response = client.CreateResponse("Tell me a three + sentence bedtime story about a unicorn."); + + + Console.WriteLine(response.GetOutputText()); + response: > + { + "id": "resp_67ccd2bed1ec8190b14f964abc0542670bb6a6b452d3795b", + "object": "response", + "created_at": 1741476542, + "status": "completed", + "error": null, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4.1-2025-04-14", + "output": [ + { + "type": "message", + "id": "msg_67ccd2bf17f0819081ff3bb2cf6508e60bb6a6b452d3795b", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "output_text", + "text": "In a peaceful grove beneath a silver moon, a unicorn named Lumina discovered a hidden pool that reflected the stars. As she dipped her horn into the water, the pool began to shimmer, revealing a pathway to a magical realm of endless night skies. Filled with wonder, Lumina whispered a wish for all who dream to find their own hidden magic, and as she glanced back, her hoofprints sparkled like stardust.", + "annotations": [] + } + ] + } + ], + "parallel_tool_calls": true, + "previous_response_id": null, + "reasoning": { + "effort": null, + "summary": null + }, + "store": true, + "temperature": 1.0, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [], + "top_p": 1.0, + "truncation": "disabled", + "usage": { + "input_tokens": 36, + "input_tokens_details": { + "cached_tokens": 0 + }, + "output_tokens": 87, + "output_tokens_details": { + "reasoning_tokens": 0 + }, + "total_tokens": 123 + }, + "user": null, + "metadata": {} + } + - title: Image input + request: + curl: > + curl https://api.openai.com/v1/responses \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "gpt-4.1", + "input": [ + { + "role": "user", + "content": [ + {"type": "input_text", "text": "what is in this image?"}, + { + "type": "input_image", + "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" + } + ] + } + ] + }' + javascript: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const response = await openai.responses.create({ + model: "gpt-4.1", + input: [ + { + role: "user", + content: [ + { type: "input_text", text: "what is in this image?" }, + { + type: "input_image", + image_url: + "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg", + }, + ], + }, + ], + }); + + + console.log(response); + python: > + from openai import OpenAI + + + client = OpenAI() + + + response = client.responses.create( + model="gpt-4.1", + input=[ + { + "role": "user", + "content": [ + { "type": "input_text", "text": "what is in this image?" }, + { + "type": "input_image", + "image_url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" + } + ] + } + ] + ) + + + print(response) + csharp: > + using System; + + using System.Collections.Generic; + + + using OpenAI.Responses; + + + OpenAIResponseClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + List inputItems = + + [ + ResponseItem.CreateUserMessageItem( + [ + ResponseContentPart.CreateInputTextPart("What is in this image?"), + ResponseContentPart.CreateInputImagePart(new Uri("https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg")) + ] + ) + ]; + + + OpenAIResponse response = client.CreateResponse(inputItems); + + + Console.WriteLine(response.GetOutputText()); + response: > + { + "id": "resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41", + "object": "response", + "created_at": 1741476777, + "status": "completed", + "error": null, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4.1-2025-04-14", + "output": [ + { + "type": "message", + "id": "msg_67ccd3acc8d48190a77525dc6de64b4104becb25c45c1d41", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "output_text", + "text": "The image depicts a scenic landscape with a wooden boardwalk or pathway leading through lush, green grass under a blue sky with some clouds. The setting suggests a peaceful natural area, possibly a park or nature reserve. There are trees and shrubs in the background.", + "annotations": [] + } + ] + } + ], + "parallel_tool_calls": true, + "previous_response_id": null, + "reasoning": { + "effort": null, + "summary": null + }, + "store": true, + "temperature": 1.0, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [], + "top_p": 1.0, + "truncation": "disabled", + "usage": { + "input_tokens": 328, + "input_tokens_details": { + "cached_tokens": 0 + }, + "output_tokens": 52, + "output_tokens_details": { + "reasoning_tokens": 0 + }, + "total_tokens": 380 + }, + "user": null, + "metadata": {} + } + - title: Web search + request: + curl: | + curl https://api.openai.com/v1/responses \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "gpt-4.1", + "tools": [{ "type": "web_search_preview" }], + "input": "What was a positive news story from today?" + }' + javascript: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const response = await openai.responses.create({ + model: "gpt-4.1", + tools: [{ type: "web_search_preview" }], + input: "What was a positive news story from today?", + }); + + console.log(response); + python: | + from openai import OpenAI + + client = OpenAI() + + response = client.responses.create( + model="gpt-4.1", + tools=[{ "type": "web_search_preview" }], + input="What was a positive news story from today?", + ) + + print(response) + csharp: > + using System; + + + using OpenAI.Responses; + + + OpenAIResponseClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + string userInputText = "What was a positive news story from + today?"; + + + ResponseCreationOptions options = new() + + { + Tools = + { + ResponseTool.CreateWebSearchTool() + }, + }; + + + OpenAIResponse response = client.CreateResponse(userInputText, + options); + + + Console.WriteLine(response.GetOutputText()); + response: > + { + "id": "resp_67ccf18ef5fc8190b16dbee19bc54e5f087bb177ab789d5c", + "object": "response", + "created_at": 1741484430, + "status": "completed", + "error": null, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4.1-2025-04-14", + "output": [ + { + "type": "web_search_call", + "id": "ws_67ccf18f64008190a39b619f4c8455ef087bb177ab789d5c", + "status": "completed" + }, + { + "type": "message", + "id": "msg_67ccf190ca3881909d433c50b1f6357e087bb177ab789d5c", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "output_text", + "text": "As of today, March 9, 2025, one notable positive news story...", + "annotations": [ + { + "type": "url_citation", + "start_index": 442, + "end_index": 557, + "url": "https://.../?utm_source=chatgpt.com", + "title": "..." + }, + { + "type": "url_citation", + "start_index": 962, + "end_index": 1077, + "url": "https://.../?utm_source=chatgpt.com", + "title": "..." + }, + { + "type": "url_citation", + "start_index": 1336, + "end_index": 1451, + "url": "https://.../?utm_source=chatgpt.com", + "title": "..." + } + ] + } + ] + } + ], + "parallel_tool_calls": true, + "previous_response_id": null, + "reasoning": { + "effort": null, + "summary": null + }, + "store": true, + "temperature": 1.0, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [ + { + "type": "web_search_preview", + "domains": [], + "search_context_size": "medium", + "user_location": { + "type": "approximate", + "city": null, + "country": "US", + "region": null, + "timezone": null + } + } + ], + "top_p": 1.0, + "truncation": "disabled", + "usage": { + "input_tokens": 328, + "input_tokens_details": { + "cached_tokens": 0 + }, + "output_tokens": 356, + "output_tokens_details": { + "reasoning_tokens": 0 + }, + "total_tokens": 684 + }, + "user": null, + "metadata": {} + } + - title: File search + request: + curl: > + curl https://api.openai.com/v1/responses \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "gpt-4.1", + "tools": [{ + "type": "file_search", + "vector_store_ids": ["vs_1234567890"], + "max_num_results": 20 + }], + "input": "What are the attributes of an ancient brown dragon?" + }' + javascript: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const response = await openai.responses.create({ + model: "gpt-4.1", + tools: [{ + type: "file_search", + vector_store_ids: ["vs_1234567890"], + max_num_results: 20 + }], + input: "What are the attributes of an ancient brown dragon?", + }); + + + console.log(response); + python: | + from openai import OpenAI + + client = OpenAI() + + response = client.responses.create( + model="gpt-4.1", + tools=[{ + "type": "file_search", + "vector_store_ids": ["vs_1234567890"], + "max_num_results": 20 + }], + input="What are the attributes of an ancient brown dragon?", + ) + + print(response) + csharp: > + using System; + + + using OpenAI.Responses; + + + OpenAIResponseClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + string userInputText = "What are the attributes of an ancient + brown dragon?"; + + + ResponseCreationOptions options = new() + + { + Tools = + { + ResponseTool.CreateFileSearchTool( + vectorStoreIds: ["vs_1234567890"], + maxResultCount: 20 + ) + }, + }; + + + OpenAIResponse response = client.CreateResponse(userInputText, + options); + + + Console.WriteLine(response.GetOutputText()); + response: > + { + "id": "resp_67ccf4c55fc48190b71bd0463ad3306d09504fb6872380d7", + "object": "response", + "created_at": 1741485253, + "status": "completed", + "error": null, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4.1-2025-04-14", + "output": [ + { + "type": "file_search_call", + "id": "fs_67ccf4c63cd08190887ef6464ba5681609504fb6872380d7", + "status": "completed", + "queries": [ + "attributes of an ancient brown dragon" + ], + "results": null + }, + { + "type": "message", + "id": "msg_67ccf4c93e5c81909d595b369351a9d309504fb6872380d7", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "output_text", + "text": "The attributes of an ancient brown dragon include...", + "annotations": [ + { + "type": "file_citation", + "index": 320, + "file_id": "file-4wDz5b167pAf72nx1h9eiN", + "filename": "dragons.pdf" + }, + { + "type": "file_citation", + "index": 576, + "file_id": "file-4wDz5b167pAf72nx1h9eiN", + "filename": "dragons.pdf" + }, + { + "type": "file_citation", + "index": 815, + "file_id": "file-4wDz5b167pAf72nx1h9eiN", + "filename": "dragons.pdf" + }, + { + "type": "file_citation", + "index": 815, + "file_id": "file-4wDz5b167pAf72nx1h9eiN", + "filename": "dragons.pdf" + }, + { + "type": "file_citation", + "index": 1030, + "file_id": "file-4wDz5b167pAf72nx1h9eiN", + "filename": "dragons.pdf" + }, + { + "type": "file_citation", + "index": 1030, + "file_id": "file-4wDz5b167pAf72nx1h9eiN", + "filename": "dragons.pdf" + }, + { + "type": "file_citation", + "index": 1156, + "file_id": "file-4wDz5b167pAf72nx1h9eiN", + "filename": "dragons.pdf" + }, + { + "type": "file_citation", + "index": 1225, + "file_id": "file-4wDz5b167pAf72nx1h9eiN", + "filename": "dragons.pdf" + } + ] + } + ] + } + ], + "parallel_tool_calls": true, + "previous_response_id": null, + "reasoning": { + "effort": null, + "summary": null + }, + "store": true, + "temperature": 1.0, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [ + { + "type": "file_search", + "filters": null, + "max_num_results": 20, + "ranking_options": { + "ranker": "auto", + "score_threshold": 0.0 + }, + "vector_store_ids": [ + "vs_1234567890" + ] + } + ], + "top_p": 1.0, + "truncation": "disabled", + "usage": { + "input_tokens": 18307, + "input_tokens_details": { + "cached_tokens": 0 + }, + "output_tokens": 348, + "output_tokens_details": { + "reasoning_tokens": 0 + }, + "total_tokens": 18655 + }, + "user": null, + "metadata": {} + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/responses \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "gpt-4.1", + "instructions": "You are a helpful assistant.", + "input": "Hello!", + "stream": true + }' + python: | + from openai import OpenAI + + client = OpenAI() + + response = client.responses.create( + model="gpt-4.1", + instructions="You are a helpful assistant.", + input="Hello!", + stream=True + ) + + for event in response: + print(event) + javascript: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + const response = await openai.responses.create({ + model: "gpt-4.1", + instructions: "You are a helpful assistant.", + input: "Hello!", + stream: true, + }); + + for await (const event of response) { + console.log(event); + } + csharp: > + using System; + + using System.ClientModel; + + using System.Threading.Tasks; + + + using OpenAI.Responses; + + + OpenAIResponseClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + string userInputText = "Hello!"; + + + ResponseCreationOptions options = new() + + { + Instructions = "You are a helpful assistant.", + }; + + + AsyncCollectionResult responseUpdates = + client.CreateResponseStreamingAsync(userInputText, options); + + + await foreach (StreamingResponseUpdate responseUpdate in + responseUpdates) + + { + if (responseUpdate is StreamingResponseOutputTextDeltaUpdate outputTextDeltaUpdate) + { + Console.Write(outputTextDeltaUpdate.Delta); + } + } + response: | + event: response.created + data: {"type":"response.created","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"in_progress","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-4.1-2025-04-14","output":[],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":null,"user":null,"metadata":{}}} + + event: response.in_progress + data: {"type":"response.in_progress","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"in_progress","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-4.1-2025-04-14","output":[],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":null,"user":null,"metadata":{}}} + + event: response.output_item.added + data: {"type":"response.output_item.added","output_index":0,"item":{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"in_progress","role":"assistant","content":[]}} + + event: response.content_part.added + data: {"type":"response.content_part.added","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"part":{"type":"output_text","text":"","annotations":[]}} + + event: response.output_text.delta + data: {"type":"response.output_text.delta","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"delta":"Hi"} + + ... + + event: response.output_text.done + data: {"type":"response.output_text.done","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"text":"Hi there! How can I assist you today?"} + + event: response.content_part.done + data: {"type":"response.content_part.done","item_id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","output_index":0,"content_index":0,"part":{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}} + + event: response.output_item.done + data: {"type":"response.output_item.done","output_index":0,"item":{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}]}} + + event: response.completed + data: {"type":"response.completed","response":{"id":"resp_67c9fdcecf488190bdd9a0409de3a1ec07b8b0ad4e5eb654","object":"response","created_at":1741290958,"status":"completed","error":null,"incomplete_details":null,"instructions":"You are a helpful assistant.","max_output_tokens":null,"model":"gpt-4.1-2025-04-14","output":[{"id":"msg_67c9fdcf37fc8190ba82116e33fb28c507b8b0ad4e5eb654","type":"message","status":"completed","role":"assistant","content":[{"type":"output_text","text":"Hi there! How can I assist you today?","annotations":[]}]}],"parallel_tool_calls":true,"previous_response_id":null,"reasoning":{"effort":null,"summary":null},"store":true,"temperature":1.0,"text":{"format":{"type":"text"}},"tool_choice":"auto","tools":[],"top_p":1.0,"truncation":"disabled","usage":{"input_tokens":37,"output_tokens":11,"output_tokens_details":{"reasoning_tokens":0},"total_tokens":48},"user":null,"metadata":{}}} + - title: Functions + request: + curl: > + curl https://api.openai.com/v1/responses \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "gpt-4.1", + "input": "What is the weather like in Boston today?", + "tools": [ + { + "type": "function", + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location", "unit"] + } + } + ], + "tool_choice": "auto" + }' + python: > + from openai import OpenAI + + + client = OpenAI() + + + tools = [ + { + "type": "function", + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location", "unit"], + } + } + ] + + + response = client.responses.create( + model="gpt-4.1", + tools=tools, + input="What is the weather like in Boston today?", + tool_choice="auto" + ) + + + print(response) + javascript: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const tools = [ + { + type: "function", + name: "get_current_weather", + description: "Get the current weather in a given location", + parameters: { + type: "object", + properties: { + location: { + type: "string", + description: "The city and state, e.g. San Francisco, CA", + }, + unit: { type: "string", enum: ["celsius", "fahrenheit"] }, + }, + required: ["location", "unit"], + }, + }, + ]; + + + const response = await openai.responses.create({ + model: "gpt-4.1", + tools: tools, + input: "What is the weather like in Boston today?", + tool_choice: "auto", + }); + + + console.log(response); + csharp: > + using System; + + using OpenAI.Responses; + + + OpenAIResponseClient client = new( + model: "gpt-4.1", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + ResponseTool getCurrentWeatherFunctionTool = + ResponseTool.CreateFunctionTool( + functionName: "get_current_weather", + functionDescription: "Get the current weather in a given location", + functionParameters: BinaryData.FromString(""" + { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]} + }, + "required": ["location", "unit"] + } + """ + ) + ); + + + string userInputText = "What is the weather like in Boston + today?"; + + + ResponseCreationOptions options = new() + + { + Tools = + { + getCurrentWeatherFunctionTool + }, + ToolChoice = ResponseToolChoice.CreateAutoChoice(), + }; + + + OpenAIResponse response = client.CreateResponse(userInputText, + options); + response: > + { + "id": "resp_67ca09c5efe0819096d0511c92b8c890096610f474011cc0", + "object": "response", + "created_at": 1741294021, + "status": "completed", + "error": null, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4.1-2025-04-14", + "output": [ + { + "type": "function_call", + "id": "fc_67ca09c6bedc8190a7abfec07b1a1332096610f474011cc0", + "call_id": "call_unLAR8MvFNptuiZK6K6HCy5k", + "name": "get_current_weather", + "arguments": "{\"location\":\"Boston, MA\",\"unit\":\"celsius\"}", + "status": "completed" + } + ], + "parallel_tool_calls": true, + "previous_response_id": null, + "reasoning": { + "effort": null, + "summary": null + }, + "store": true, + "temperature": 1.0, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [ + { + "type": "function", + "description": "Get the current weather in a given location", + "name": "get_current_weather", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": [ + "celsius", + "fahrenheit" + ] + } + }, + "required": [ + "location", + "unit" + ] + }, + "strict": true + } + ], + "top_p": 1.0, + "truncation": "disabled", + "usage": { + "input_tokens": 291, + "output_tokens": 23, + "output_tokens_details": { + "reasoning_tokens": 0 + }, + "total_tokens": 314 + }, + "user": null, + "metadata": {} + } + - title: Reasoning + request: + curl: | + curl https://api.openai.com/v1/responses \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "model": "o3-mini", + "input": "How much wood would a woodchuck chuck?", + "reasoning": { + "effort": "high" + } + }' + javascript: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + const response = await openai.responses.create({ + model: "o3-mini", + input: "How much wood would a woodchuck chuck?", + reasoning: { + effort: "high" + } + }); + + console.log(response); + python: | + from openai import OpenAI + client = OpenAI() + + response = client.responses.create( + model="o3-mini", + input="How much wood would a woodchuck chuck?", + reasoning={ + "effort": "high" + } + ) + + print(response) + csharp: > + using System; + + using OpenAI.Responses; + + + OpenAIResponseClient client = new( + model: "o3-mini", + apiKey: Environment.GetEnvironmentVariable("OPENAI_API_KEY") + ); + + + string userInputText = "How much wood would a woodchuck chuck?"; + + + ResponseCreationOptions options = new() + + { + ReasoningOptions = new() + { + ReasoningEffortLevel = ResponseReasoningEffortLevel.High, + }, + }; + + + OpenAIResponse response = client.CreateResponse(userInputText, + options); + + + Console.WriteLine(response.GetOutputText()); + response: > + { + "id": "resp_67ccd7eca01881908ff0b5146584e408072912b2993db808", + "object": "response", + "created_at": 1741477868, + "status": "completed", + "error": null, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "o1-2024-12-17", + "output": [ + { + "type": "message", + "id": "msg_67ccd7f7b5848190a6f3e95d809f6b44072912b2993db808", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "output_text", + "text": "The classic tongue twister...", + "annotations": [] + } + ] + } + ], + "parallel_tool_calls": true, + "previous_response_id": null, + "reasoning": { + "effort": "high", + "summary": null + }, + "store": true, + "temperature": 1.0, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [], + "top_p": 1.0, + "truncation": "disabled", + "usage": { + "input_tokens": 81, + "input_tokens_details": { + "cached_tokens": 0 + }, + "output_tokens": 1035, + "output_tokens_details": { + "reasoning_tokens": 832 + }, + "total_tokens": 1116 + }, + "user": null, + "metadata": {} + } + /responses/{response_id}: + get: + operationId: getResponse + tags: + - Responses + summary: | + Retrieves a model response with the given ID. + parameters: + - in: path + name: response_id + required: true + schema: + type: string + example: resp_677efb5139a88190b512bc3fef8e535d + description: The ID of the response to retrieve. + - in: query + name: include + schema: + type: array + items: + $ref: "#/components/schemas/Includable" + description: | + Additional fields to include in the response. See the `include` + parameter for Response creation above for more information. + - in: query + name: stream + schema: + type: boolean + description: | + If set to true, the model response data will be streamed to the client + as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). + See the [Streaming section below](/docs/api-reference/responses-streaming) + for more information. + - in: query + name: starting_after + schema: + type: integer + description: | + The sequence number of the event after which to start streaming. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Response" + x-oaiMeta: + name: Get a model response + group: responses + returns: > + The [Response](/docs/api-reference/responses/object) object matching + the + + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/responses/resp_123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" + javascript: | + import OpenAI from "openai"; + const client = new OpenAI(); + + const response = await client.responses.retrieve("resp_123"); + console.log(response); + python: | + from openai import OpenAI + client = OpenAI() + + response = client.responses.retrieve("resp_123") + print(response) + response: > + { + "id": "resp_67cb71b351908190a308f3859487620d06981a8637e6bc44", + "object": "response", + "created_at": 1741386163, + "status": "completed", + "error": null, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4o-2024-08-06", + "output": [ + { + "type": "message", + "id": "msg_67cb71b3c2b0819084d481baaaf148f206981a8637e6bc44", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "output_text", + "text": "Silent circuits hum, \nThoughts emerge in data streams— \nDigital dawn breaks.", + "annotations": [] + } + ] + } + ], + "parallel_tool_calls": true, + "previous_response_id": null, + "reasoning": { + "effort": null, + "summary": null + }, + "store": true, + "temperature": 1.0, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [], + "top_p": 1.0, + "truncation": "disabled", + "usage": { + "input_tokens": 32, + "input_tokens_details": { + "cached_tokens": 0 + }, + "output_tokens": 18, + "output_tokens_details": { + "reasoning_tokens": 0 + }, + "total_tokens": 50 + }, + "user": null, + "metadata": {} + } + delete: + operationId: deleteResponse + tags: + - Responses + summary: | + Deletes a model response with the given ID. + parameters: + - in: path + name: response_id + required: true + schema: + type: string + example: resp_677efb5139a88190b512bc3fef8e535d + description: The ID of the response to delete. + responses: + "200": + description: OK + "404": + description: Not Found + content: + application/json: + schema: + $ref: "#/components/schemas/Error" + x-oaiMeta: + name: Delete a model response + group: responses + returns: | + A success message. + examples: + request: + curl: | + curl -X DELETE https://api.openai.com/v1/responses/resp_123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" + javascript: | + import OpenAI from "openai"; + const client = new OpenAI(); + + const response = await client.responses.del("resp_123"); + console.log(response); + python: | + from openai import OpenAI + client = OpenAI() + + response = client.responses.delete("resp_123") + print(response) + response: | + { + "id": "resp_6786a1bec27481909a17d673315b29f6", + "object": "response", + "deleted": true + } + /responses/{response_id}/cancel: + post: + operationId: cancelResponse + tags: + - Responses + summary: | + Cancels a model response with the given ID. Only responses created with + the `background` parameter set to `true` can be cancelled. + [Learn more](/docs/guides/background). + parameters: + - in: path + name: response_id + required: true + schema: + type: string + example: resp_677efb5139a88190b512bc3fef8e535d + description: The ID of the response to cancel. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Response" + "404": + description: Not Found + content: + application/json: + schema: + $ref: "#/components/schemas/Error" + x-oaiMeta: + name: Cancel a response + group: responses + returns: | + A [Response](/docs/api-reference/responses/object) object. + examples: + request: + curl: | + curl -X POST https://api.openai.com/v1/responses/resp_123/cancel \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" + javascript: | + import OpenAI from "openai"; + const client = new OpenAI(); + + const response = await client.responses.cancel("resp_123"); + console.log(response); + python: | + from openai import OpenAI + client = OpenAI() + + response = client.responses.cancel("resp_123") + print(response) + response: > + { + "id": "resp_67cb71b351908190a308f3859487620d06981a8637e6bc44", + "object": "response", + "created_at": 1741386163, + "status": "completed", + "error": null, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4o-2024-08-06", + "output": [ + { + "type": "message", + "id": "msg_67cb71b3c2b0819084d481baaaf148f206981a8637e6bc44", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "output_text", + "text": "Silent circuits hum, \nThoughts emerge in data streams— \nDigital dawn breaks.", + "annotations": [] + } + ] + } + ], + "parallel_tool_calls": true, + "previous_response_id": null, + "reasoning": { + "effort": null, + "summary": null + }, + "store": true, + "temperature": 1.0, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [], + "top_p": 1.0, + "truncation": "disabled", + "usage": { + "input_tokens": 32, + "input_tokens_details": { + "cached_tokens": 0 + }, + "output_tokens": 18, + "output_tokens_details": { + "reasoning_tokens": 0 + }, + "total_tokens": 50 + }, + "user": null, + "metadata": {} + } + /responses/{response_id}/input_items: + get: + operationId: listInputItems + tags: + - Responses + summary: Returns a list of input items for a given response. + parameters: + - in: path + name: response_id + required: true + schema: + type: string + description: The ID of the response to retrieve input items for. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between + + 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - in: query + name: order + schema: + type: string + enum: + - asc + - desc + description: | + The order to return the input items in. Default is `desc`. + - `asc`: Return the input items in ascending order. + - `desc`: Return the input items in descending order. + - in: query + name: after + schema: + type: string + description: | + An item ID to list items after, used in pagination. + - in: query + name: before + schema: + type: string + description: | + An item ID to list items before, used in pagination. + - in: query + name: include + schema: + type: array + items: + $ref: "#/components/schemas/Includable" + description: | + Additional fields to include in the response. See the `include` + parameter for Response creation above for more information. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ResponseItemList" + x-oaiMeta: + name: List input items + group: responses + returns: A list of input item objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/responses/resp_abc123/input_items \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" + javascript: > + import OpenAI from "openai"; + + const client = new OpenAI(); + + + const response = await + client.responses.inputItems.list("resp_123"); + + console.log(response.data); + python: | + from openai import OpenAI + client = OpenAI() + + response = client.responses.input_items.list("resp_123") + print(response.data) + response: > + { + "object": "list", + "data": [ + { + "id": "msg_abc123", + "type": "message", + "role": "user", + "content": [ + { + "type": "input_text", + "text": "Tell me a three sentence bedtime story about a unicorn." + } + ] + } + ], + "first_id": "msg_abc123", + "last_id": "msg_abc123", + "has_more": false + } + /threads: + post: + operationId: createThread + tags: + - Assistants + summary: Create a thread. + requestBody: + content: + application/json: + schema: + $ref: "#/components/schemas/CreateThreadRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ThreadObject" + x-oaiMeta: + name: Create thread + group: threads + beta: true + returns: A [thread](/docs/api-reference/threads) object. + examples: + - title: Empty + request: + curl: | + curl https://api.openai.com/v1/threads \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '' + python: | + from openai import OpenAI + client = OpenAI() + + empty_thread = client.beta.threads.create() + print(empty_thread) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const emptyThread = await openai.beta.threads.create(); + + console.log(emptyThread); + } + + main(); + response: | + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1699012949, + "metadata": {}, + "tool_resources": {} + } + - title: Messages + request: + curl: | + curl https://api.openai.com/v1/threads \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "messages": [{ + "role": "user", + "content": "Hello, what is AI?" + }, { + "role": "user", + "content": "How does AI work? Explain it in simple terms." + }] + }' + python: | + from openai import OpenAI + client = OpenAI() + + message_thread = client.beta.threads.create( + messages=[ + { + "role": "user", + "content": "Hello, what is AI?" + }, + { + "role": "user", + "content": "How does AI work? Explain it in simple terms." + }, + ] + ) + + print(message_thread) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const messageThread = await openai.beta.threads.create({ + messages: [ + { + role: "user", + content: "Hello, what is AI?" + }, + { + role: "user", + content: "How does AI work? Explain it in simple terms.", + }, + ], + }); + + console.log(messageThread); + } + + + main(); + response: | + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1699014083, + "metadata": {}, + "tool_resources": {} + } + /threads/runs: + post: + operationId: createThreadAndRun + tags: + - Assistants + summary: Create a thread and run it in one request. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateThreadAndRunRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Create thread and run + group: threads + beta: true + returns: A [run](/docs/api-reference/runs/object) object. + examples: + - title: Default + request: + curl: > + curl https://api.openai.com/v1/threads/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123", + "thread": { + "messages": [ + {"role": "user", "content": "Explain deep learning to a 5 year old."} + ] + } + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + run = client.beta.threads.create_and_run( + assistant_id="asst_abc123", + thread={ + "messages": [ + {"role": "user", "content": "Explain deep learning to a 5 year old."} + ] + } + ) + + + print(run) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const run = await openai.beta.threads.createAndRun({ + assistant_id: "asst_abc123", + thread: { + messages: [ + { role: "user", content: "Explain deep learning to a 5 year old." }, + ], + }, + }); + + console.log(run); + } + + + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699076792, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "queued", + "started_at": null, + "expires_at": 1699077392, + "cancelled_at": null, + "failed_at": null, + "completed_at": null, + "required_action": null, + "last_error": null, + "model": "gpt-4o", + "instructions": "You are a helpful assistant.", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "temperature": 1.0, + "top_p": 1.0, + "max_completion_tokens": null, + "max_prompt_tokens": null, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "incomplete_details": null, + "usage": null, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/threads/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_123", + "thread": { + "messages": [ + {"role": "user", "content": "Hello"} + ] + }, + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + stream = client.beta.threads.create_and_run( + assistant_id="asst_123", + thread={ + "messages": [ + {"role": "user", "content": "Hello"} + ] + }, + stream=True + ) + + for event in stream: + print(event) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const stream = await openai.beta.threads.createAndRun({ + assistant_id: "asst_123", + thread: { + messages: [ + { role: "user", content: "Hello" }, + ], + }, + stream: true + }); + + for await (const event of stream) { + console.log(event); + } + } + + main(); + response: | + event: thread.created + data: {"id":"thread_123","object":"thread","created_at":1710348075,"metadata":{}} + + event: thread.run.created + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} + + event: thread.run.queued + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} + + event: thread.run.in_progress + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"tool_resources":{},"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} + + event: thread.run.step.created + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.run.step.in_progress + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.message.created + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[], "metadata":{}} + + event: thread.message.in_progress + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[], "metadata":{}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} + + ... + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" today"}}]}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} + + event: thread.message.completed + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710348077,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! How can I assist you today?","annotations":[]}}], "metadata":{}} + + event: thread.run.step.completed + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710348077,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} + + event: thread.run.completed + {"id":"run_123","object":"thread.run","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1713226836,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1713226837,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":345,"completion_tokens":11,"total_tokens":356},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true} + + event: done + data: [DONE] + - title: Streaming with Functions + request: + curl: > + curl https://api.openai.com/v1/threads/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123", + "thread": { + "messages": [ + {"role": "user", "content": "What is the weather like in San Francisco?"} + ] + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location"] + } + } + } + ], + "stream": true + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ] + + + stream = client.beta.threads.create_and_run( + thread={ + "messages": [ + {"role": "user", "content": "What is the weather like in San Francisco?"} + ] + }, + assistant_id="asst_abc123", + tools=tools, + stream=True + ) + + + for event in stream: + print(event) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ]; + + + async function main() { + const stream = await openai.beta.threads.createAndRun({ + assistant_id: "asst_123", + thread: { + messages: [ + { role: "user", content: "What is the weather like in San Francisco?" }, + ], + }, + tools: tools, + stream: true + }); + + for await (const event of stream) { + console.log(event); + } + } + + + main(); + response: | + event: thread.created + data: {"id":"thread_123","object":"thread","created_at":1710351818,"metadata":{}} + + event: thread.run.created + data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.queued + data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.in_progress + data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710351818,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.step.created + data: {"id":"step_001","object":"thread.run.step","created_at":1710351819,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710352418,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[]},"usage":null} + + event: thread.run.step.in_progress + data: {"id":"step_001","object":"thread.run.step","created_at":1710351819,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710352418,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[]},"usage":null} + + event: thread.run.step.delta + data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"id":"call_XXNp8YGaFrjrSjgqxtC8JJ1B","type":"function","function":{"name":"get_current_weather","arguments":"","output":null}}]}}} + + event: thread.run.step.delta + data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"{\""}}]}}} + + event: thread.run.step.delta + data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"location"}}]}}} + + ... + + event: thread.run.step.delta + data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"ahrenheit"}}]}}} + + event: thread.run.step.delta + data: {"id":"step_001","object":"thread.run.step.delta","delta":{"step_details":{"type":"tool_calls","tool_calls":[{"index":0,"type":"function","function":{"arguments":"\"}"}}]}}} + + event: thread.run.requires_action + data: {"id":"run_123","object":"thread.run","created_at":1710351818,"assistant_id":"asst_123","thread_id":"thread_123","status":"requires_action","started_at":1710351818,"expires_at":1710352418,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":{"type":"submit_tool_outputs","submit_tool_outputs":{"tool_calls":[{"id":"call_XXNp8YGaFrjrSjgqxtC8JJ1B","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\":\"San Francisco, CA\",\"unit\":\"fahrenheit\"}"}}]}},"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":345,"completion_tokens":11,"total_tokens":356},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: done + data: [DONE] + /threads/{thread_id}: + get: + operationId: getThread + tags: + - Assistants + summary: Retrieves a thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ThreadObject" + x-oaiMeta: + name: Retrieve thread + group: threads + beta: true + returns: The [thread](/docs/api-reference/threads/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + my_thread = client.beta.threads.retrieve("thread_abc123") + print(my_thread) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const myThread = await openai.beta.threads.retrieve( + "thread_abc123" + ); + + console.log(myThread); + } + + main(); + response: | + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1699014083, + "metadata": {}, + "tool_resources": { + "code_interpreter": { + "file_ids": [] + } + } + } + post: + operationId: modifyThread + tags: + - Assistants + summary: Modifies a thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to modify. Only the `metadata` can be modified. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ModifyThreadRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ThreadObject" + x-oaiMeta: + name: Modify thread + group: threads + beta: true + returns: The modified [thread](/docs/api-reference/threads/object) object + matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "metadata": { + "modified": "true", + "user": "abc123" + } + }' + python: | + from openai import OpenAI + client = OpenAI() + + my_updated_thread = client.beta.threads.update( + "thread_abc123", + metadata={ + "modified": "true", + "user": "abc123" + } + ) + print(my_updated_thread) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const updatedThread = await openai.beta.threads.update( + "thread_abc123", + { + metadata: { modified: "true", user: "abc123" }, + } + ); + + console.log(updatedThread); + } + + main(); + response: | + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1699014083, + "metadata": { + "modified": "true", + "user": "abc123" + }, + "tool_resources": {} + } + delete: + operationId: deleteThread + tags: + - Assistants + summary: Delete a thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteThreadResponse" + x-oaiMeta: + name: Delete thread + group: threads + beta: true + returns: Deletion status + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -X DELETE + python: | + from openai import OpenAI + client = OpenAI() + + response = client.beta.threads.delete("thread_abc123") + print(response) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const response = await openai.beta.threads.del("thread_abc123"); + + console.log(response); + } + main(); + response: | + { + "id": "thread_abc123", + "object": "thread.deleted", + "deleted": true + } + /threads/{thread_id}/messages: + get: + operationId: listMessages + tags: + - Assistants + summary: Returns a list of messages for a given thread. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) the messages + belong to. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + - name: run_id + in: query + description: | + Filter messages by the run ID that generated them. + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListMessagesResponse" + x-oaiMeta: + name: List messages + group: threads + beta: true + returns: A list of [message](/docs/api-reference/messages) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/messages \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: > + from openai import OpenAI + + client = OpenAI() + + + thread_messages = + client.beta.threads.messages.list("thread_abc123") + + print(thread_messages.data) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const threadMessages = await openai.beta.threads.messages.list( + "thread_abc123" + ); + + console.log(threadMessages.data); + } + + main(); + response: > + { + "object": "list", + "data": [ + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1699016383, + "assistant_id": null, + "thread_id": "thread_abc123", + "run_id": null, + "role": "user", + "content": [ + { + "type": "text", + "text": { + "value": "How does AI work? Explain it in simple terms.", + "annotations": [] + } + } + ], + "attachments": [], + "metadata": {} + }, + { + "id": "msg_abc456", + "object": "thread.message", + "created_at": 1699016383, + "assistant_id": null, + "thread_id": "thread_abc123", + "run_id": null, + "role": "user", + "content": [ + { + "type": "text", + "text": { + "value": "Hello, what is AI?", + "annotations": [] + } + } + ], + "attachments": [], + "metadata": {} + } + ], + "first_id": "msg_abc123", + "last_id": "msg_abc456", + "has_more": false + } + post: + operationId: createMessage + tags: + - Assistants + summary: Create a message. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) to create a + message for. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateMessageRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/MessageObject" + x-oaiMeta: + name: Create message + group: threads + beta: true + returns: A [message](/docs/api-reference/messages/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/messages \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "role": "user", + "content": "How does AI work? Explain it in simple terms." + }' + python: | + from openai import OpenAI + client = OpenAI() + + thread_message = client.beta.threads.messages.create( + "thread_abc123", + role="user", + content="How does AI work? Explain it in simple terms.", + ) + print(thread_message) + node.js: >- + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const threadMessages = await openai.beta.threads.messages.create( + "thread_abc123", + { role: "user", content: "How does AI work? Explain it in simple terms." } + ); + + console.log(threadMessages); + } + + + main(); + response: | + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1713226573, + "assistant_id": null, + "thread_id": "thread_abc123", + "run_id": null, + "role": "user", + "content": [ + { + "type": "text", + "text": { + "value": "How does AI work? Explain it in simple terms.", + "annotations": [] + } + } + ], + "attachments": [], + "metadata": {} + } + /threads/{thread_id}/messages/{message_id}: + get: + operationId: getMessage + tags: + - Assistants + summary: Retrieve a message. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) to which this + message belongs. + - in: path + name: message_id + required: true + schema: + type: string + description: The ID of the message to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/MessageObject" + x-oaiMeta: + name: Retrieve message + group: threads + beta: true + returns: The [message](/docs/api-reference/messages/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + message = client.beta.threads.messages.retrieve( + message_id="msg_abc123", + thread_id="thread_abc123", + ) + print(message) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const message = await openai.beta.threads.messages.retrieve( + "thread_abc123", + "msg_abc123" + ); + + console.log(message); + } + + main(); + response: | + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1699017614, + "assistant_id": null, + "thread_id": "thread_abc123", + "run_id": null, + "role": "user", + "content": [ + { + "type": "text", + "text": { + "value": "How does AI work? Explain it in simple terms.", + "annotations": [] + } + } + ], + "attachments": [], + "metadata": {} + } + post: + operationId: modifyMessage + tags: + - Assistants + summary: Modifies a message. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to which this message belongs. + - in: path + name: message_id + required: true + schema: + type: string + description: The ID of the message to modify. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ModifyMessageRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/MessageObject" + x-oaiMeta: + name: Modify message + group: threads + beta: true + returns: The modified [message](/docs/api-reference/messages/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "metadata": { + "modified": "true", + "user": "abc123" + } + }' + python: | + from openai import OpenAI + client = OpenAI() + + message = client.beta.threads.messages.update( + message_id="msg_abc12", + thread_id="thread_abc123", + metadata={ + "modified": "true", + "user": "abc123", + }, + ) + print(message) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const message = await openai.beta.threads.messages.update( + "thread_abc123", + "msg_abc123", + { + metadata: { + modified: "true", + user: "abc123", + }, + } + }' + response: | + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1699017614, + "assistant_id": null, + "thread_id": "thread_abc123", + "run_id": null, + "role": "user", + "content": [ + { + "type": "text", + "text": { + "value": "How does AI work? Explain it in simple terms.", + "annotations": [] + } + } + ], + "file_ids": [], + "metadata": { + "modified": "true", + "user": "abc123" + } + } + delete: + operationId: deleteMessage + tags: + - Assistants + summary: Deletes a message. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to which this message belongs. + - in: path + name: message_id + required: true + schema: + type: string + description: The ID of the message to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteMessageResponse" + x-oaiMeta: + name: Delete message + group: threads + beta: true + returns: Deletion status + examples: + request: + curl: | + curl -X DELETE https://api.openai.com/v1/threads/thread_abc123/messages/msg_abc123 \ + -H "Content-Type: application/json" \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + deleted_message = client.beta.threads.messages.delete( + message_id="msg_abc12", + thread_id="thread_abc123", + ) + print(deleted_message) + node.js: |- + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const deletedMessage = await openai.beta.threads.messages.del( + "thread_abc123", + "msg_abc123" + ); + + console.log(deletedMessage); + } + response: | + { + "id": "msg_abc123", + "object": "thread.message.deleted", + "deleted": true + } + /threads/{thread_id}/runs: + get: + operationId: listRuns + tags: + - Assistants + summary: Returns a list of runs belonging to a thread. + parameters: + - name: thread_id + in: path + required: true + schema: + type: string + description: The ID of the thread the run belongs to. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListRunsResponse" + x-oaiMeta: + name: List runs + group: threads + beta: true + returns: A list of [run](/docs/api-reference/runs/object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + runs = client.beta.threads.runs.list( + "thread_abc123" + ) + + print(runs) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const runs = await openai.beta.threads.runs.list( + "thread_abc123" + ); + + console.log(runs); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699075072, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699075072, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699075073, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "tool_resources": { + "code_interpreter": { + "file_ids": [ + "file-abc123", + "file-abc456" + ] + } + }, + "metadata": {}, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + }, + { + "id": "run_abc456", + "object": "thread.run", + "created_at": 1699063290, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699063290, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699063291, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "tool_resources": { + "code_interpreter": { + "file_ids": [ + "file-abc123", + "file-abc456" + ] + } + }, + "metadata": {}, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + ], + "first_id": "run_abc123", + "last_id": "run_abc456", + "has_more": false + } + post: + operationId: createRun + tags: + - Assistants + summary: Create a run. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to run. + - name: include[] + in: query + description: | + A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result content. + + See the [file search tool documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) for more information. + schema: + type: array + items: + type: string + enum: + - step_details.tool_calls[*].file_search.results[*].content + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateRunRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Create run + group: threads + beta: true + returns: A [run](/docs/api-reference/runs/object) object. + examples: + - title: Default + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123" + }' + python: | + from openai import OpenAI + client = OpenAI() + + run = client.beta.threads.runs.create( + thread_id="thread_abc123", + assistant_id="asst_abc123" + ) + + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const run = await openai.beta.threads.runs.create( + "thread_abc123", + { assistant_id: "asst_abc123" } + ); + + console.log(run); + } + + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699063290, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "queued", + "started_at": 1699063290, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699063291, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "metadata": {}, + "usage": null, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/threads/thread_123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_123", + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + stream = client.beta.threads.runs.create( + thread_id="thread_123", + assistant_id="asst_123", + stream=True + ) + + for event in stream: + print(event) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const stream = await openai.beta.threads.runs.create( + "thread_123", + { assistant_id: "asst_123", stream: true } + ); + + for await (const event of stream) { + console.log(event); + } + } + + main(); + response: | + event: thread.run.created + data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.queued + data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.in_progress + data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710330641,"expires_at":1710331240,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.step.created + data: {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.run.step.in_progress + data: {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.message.created + data: {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.in_progress + data: {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} + + ... + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" today"}}]}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} + + event: thread.message.completed + data: {"id":"msg_001","object":"thread.message","created_at":1710330641,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710330642,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! How can I assist you today?","annotations":[]}}],"metadata":{}} + + event: thread.run.step.completed + data: {"id":"step_001","object":"thread.run.step","created_at":1710330641,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710330642,"expires_at":1710331240,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} + + event: thread.run.completed + data: {"id":"run_123","object":"thread.run","created_at":1710330640,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710330641,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710330642,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: done + data: [DONE] + - title: Streaming with Functions + request: + curl: > + curl https://api.openai.com/v1/threads/thread_abc123/runs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "assistant_id": "asst_abc123", + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location"] + } + } + } + ], + "stream": true + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ] + + + stream = client.beta.threads.runs.create( + thread_id="thread_abc123", + assistant_id="asst_abc123", + tools=tools, + stream=True + ) + + + for event in stream: + print(event) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + const tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA", + }, + "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}, + }, + "required": ["location"], + }, + } + } + ]; + + + async function main() { + const stream = await openai.beta.threads.runs.create( + "thread_abc123", + { + assistant_id: "asst_abc123", + tools: tools, + stream: true + } + ); + + for await (const event of stream) { + console.log(event); + } + } + + + main(); + response: | + event: thread.run.created + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.queued + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":null,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.in_progress + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710348075,"expires_at":1710348675,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.step.created + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.run.step.in_progress + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":null} + + event: thread.message.created + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.in_progress + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"Hello","annotations":[]}}]}} + + ... + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" today"}}]}} + + event: thread.message.delta + data: {"id":"msg_001","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"?"}}]}} + + event: thread.message.completed + data: {"id":"msg_001","object":"thread.message","created_at":1710348076,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710348077,"role":"assistant","content":[{"type":"text","text":{"value":"Hello! How can I assist you today?","annotations":[]}}],"metadata":{}} + + event: thread.run.step.completed + data: {"id":"step_001","object":"thread.run.step","created_at":1710348076,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710348077,"expires_at":1710348675,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_001"}},"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31}} + + event: thread.run.completed + data: {"id":"run_123","object":"thread.run","created_at":1710348075,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710348075,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710348077,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: done + data: [DONE] + /threads/{thread_id}/runs/{run_id}: + get: + operationId: getRun + tags: + - Assistants + summary: Retrieves a run. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) that was run. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Retrieve run + group: threads + beta: true + returns: The [run](/docs/api-reference/runs/object) object matching the + specified ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + run = client.beta.threads.runs.retrieve( + thread_id="thread_abc123", + run_id="run_abc123" + ) + + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const run = await openai.beta.threads.runs.retrieve( + "thread_abc123", + "run_abc123" + ); + + console.log(run); + } + + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699075072, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699075072, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699075073, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "metadata": {}, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + post: + operationId: modifyRun + tags: + - Assistants + summary: Modifies a run. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) that was run. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run to modify. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/ModifyRunRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Modify run + group: threads + beta: true + returns: The modified [run](/docs/api-reference/runs/object) object matching the + specified ID. + examples: + request: + curl: > + curl + https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "metadata": { + "user_id": "user_abc123" + } + }' + python: | + from openai import OpenAI + client = OpenAI() + + run = client.beta.threads.runs.update( + thread_id="thread_abc123", + run_id="run_abc123", + metadata={"user_id": "user_abc123"}, + ) + + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const run = await openai.beta.threads.runs.update( + "thread_abc123", + "run_abc123", + { + metadata: { + user_id: "user_abc123", + }, + } + ); + + console.log(run); + } + + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699075072, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699075072, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699075073, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "incomplete_details": null, + "tools": [ + { + "type": "code_interpreter" + } + ], + "tool_resources": { + "code_interpreter": { + "file_ids": [ + "file-abc123", + "file-abc456" + ] + } + }, + "metadata": { + "user_id": "user_abc123" + }, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + /threads/{thread_id}/runs/{run_id}/cancel: + post: + operationId: cancelRun + tags: + - Assistants + summary: Cancels a run that is `in_progress`. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to which this run belongs. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run to cancel. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Cancel a run + group: threads + beta: true + returns: The modified [run](/docs/api-reference/runs/object) object matching the + specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/cancel \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "OpenAI-Beta: assistants=v2" \ + -X POST + python: | + from openai import OpenAI + client = OpenAI() + + run = client.beta.threads.runs.cancel( + thread_id="thread_abc123", + run_id="run_abc123" + ) + + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const run = await openai.beta.threads.runs.cancel( + "thread_abc123", + "run_abc123" + ); + + console.log(run); + } + + main(); + response: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1699076126, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "cancelling", + "started_at": 1699076126, + "expires_at": 1699076726, + "cancelled_at": null, + "failed_at": null, + "completed_at": null, + "last_error": null, + "model": "gpt-4o", + "instructions": "You summarize books.", + "tools": [ + { + "type": "file_search" + } + ], + "tool_resources": { + "file_search": { + "vector_store_ids": ["vs_123"] + } + }, + "metadata": {}, + "usage": null, + "temperature": 1.0, + "top_p": 1.0, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + /threads/{thread_id}/runs/{run_id}/steps: + get: + operationId: listRunSteps + tags: + - Assistants + summary: Returns a list of run steps belonging to a run. + parameters: + - name: thread_id + in: path + required: true + schema: + type: string + description: The ID of the thread the run and run steps belong to. + - name: run_id + in: path + required: true + schema: + type: string + description: The ID of the run the run steps belong to. + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + - name: include[] + in: query + description: | + A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result content. + + See the [file search tool documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) for more information. + schema: + type: array + items: + type: string + enum: + - step_details.tool_calls[*].file_search.results[*].content + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListRunStepsResponse" + x-oaiMeta: + name: List run steps + group: threads + beta: true + returns: A list of [run step](/docs/api-reference/run-steps/step-object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + run_steps = client.beta.threads.runs.steps.list( + thread_id="thread_abc123", + run_id="run_abc123" + ) + + print(run_steps) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const runStep = await openai.beta.threads.runs.steps.list( + "thread_abc123", + "run_abc123" + ); + console.log(runStep); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "step_abc123", + "object": "thread.run.step", + "created_at": 1699063291, + "run_id": "run_abc123", + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "type": "message_creation", + "status": "completed", + "cancelled_at": null, + "completed_at": 1699063291, + "expired_at": null, + "failed_at": null, + "last_error": null, + "step_details": { + "type": "message_creation", + "message_creation": { + "message_id": "msg_abc123" + } + }, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + } + } + ], + "first_id": "step_abc123", + "last_id": "step_abc456", + "has_more": false + } + /threads/{thread_id}/runs/{run_id}/steps/{step_id}: + get: + operationId: getRunStep + tags: + - Assistants + summary: Retrieves a run step. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the thread to which the run and run step belongs. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run to which the run step belongs. + - in: path + name: step_id + required: true + schema: + type: string + description: The ID of the run step to retrieve. + - name: include[] + in: query + description: | + A list of additional fields to include in the response. Currently the only supported value is `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result content. + + See the [file search tool documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) for more information. + schema: + type: array + items: + type: string + enum: + - step_details.tool_calls[*].file_search.results[*].content + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunStepObject" + x-oaiMeta: + name: Retrieve run step + group: threads + beta: true + returns: The [run step](/docs/api-reference/run-steps/step-object) object + matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/threads/thread_abc123/runs/run_abc123/steps/step_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + run_step = client.beta.threads.runs.steps.retrieve( + thread_id="thread_abc123", + run_id="run_abc123", + step_id="step_abc123" + ) + + print(run_step) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const runStep = await openai.beta.threads.runs.steps.retrieve( + "thread_abc123", + "run_abc123", + "step_abc123" + ); + console.log(runStep); + } + + main(); + response: | + { + "id": "step_abc123", + "object": "thread.run.step", + "created_at": 1699063291, + "run_id": "run_abc123", + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "type": "message_creation", + "status": "completed", + "cancelled_at": null, + "completed_at": 1699063291, + "expired_at": null, + "failed_at": null, + "last_error": null, + "step_details": { + "type": "message_creation", + "message_creation": { + "message_id": "msg_abc123" + } + }, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + } + } + /threads/{thread_id}/runs/{run_id}/submit_tool_outputs: + post: + operationId: submitToolOuputsToRun + tags: + - Assistants + summary: > + When a run has the `status: "requires_action"` and + `required_action.type` is `submit_tool_outputs`, this endpoint can be + used to submit the outputs from the tool calls once they're all + completed. All outputs must be submitted in a single request. + parameters: + - in: path + name: thread_id + required: true + schema: + type: string + description: The ID of the [thread](/docs/api-reference/threads) to which this + run belongs. + - in: path + name: run_id + required: true + schema: + type: string + description: The ID of the run that requires the tool output submission. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/SubmitToolOutputsRunRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/RunObject" + x-oaiMeta: + name: Submit tool outputs to run + group: threads + beta: true + returns: The modified [run](/docs/api-reference/runs/object) object matching the + specified ID. + examples: + - title: Default + request: + curl: | + curl https://api.openai.com/v1/threads/thread_123/runs/run_123/submit_tool_outputs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "tool_outputs": [ + { + "tool_call_id": "call_001", + "output": "70 degrees and sunny." + } + ] + }' + python: | + from openai import OpenAI + client = OpenAI() + + run = client.beta.threads.runs.submit_tool_outputs( + thread_id="thread_123", + run_id="run_123", + tool_outputs=[ + { + "tool_call_id": "call_001", + "output": "70 degrees and sunny." + } + ] + ) + + print(run) + node.js: | + import OpenAI from "openai"; + + const openai = new OpenAI(); + + async function main() { + const run = await openai.beta.threads.runs.submitToolOutputs( + "thread_123", + "run_123", + { + tool_outputs: [ + { + tool_call_id: "call_001", + output: "70 degrees and sunny.", + }, + ], + } + ); + + console.log(run); + } + + main(); + response: > + { + "id": "run_123", + "object": "thread.run", + "created_at": 1699075592, + "assistant_id": "asst_123", + "thread_id": "thread_123", + "status": "queued", + "started_at": 1699075592, + "expires_at": 1699076192, + "cancelled_at": null, + "failed_at": null, + "completed_at": null, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather in a given location", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and state, e.g. San Francisco, CA" + }, + "unit": { + "type": "string", + "enum": ["celsius", "fahrenheit"] + } + }, + "required": ["location"] + } + } + } + ], + "metadata": {}, + "usage": null, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + - title: Streaming + request: + curl: | + curl https://api.openai.com/v1/threads/thread_123/runs/run_123/submit_tool_outputs \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "tool_outputs": [ + { + "tool_call_id": "call_001", + "output": "70 degrees and sunny." + } + ], + "stream": true + }' + python: | + from openai import OpenAI + client = OpenAI() + + stream = client.beta.threads.runs.submit_tool_outputs( + thread_id="thread_123", + run_id="run_123", + tool_outputs=[ + { + "tool_call_id": "call_001", + "output": "70 degrees and sunny." + } + ], + stream=True + ) + + for event in stream: + print(event) + node.js: > + import OpenAI from "openai"; + + + const openai = new OpenAI(); + + + async function main() { + const stream = await openai.beta.threads.runs.submitToolOutputs( + "thread_123", + "run_123", + { + tool_outputs: [ + { + tool_call_id: "call_001", + output: "70 degrees and sunny.", + }, + ], + } + ); + + for await (const event of stream) { + console.log(event); + } + } + + + main(); + response: | + event: thread.run.step.completed + data: {"id":"step_001","object":"thread.run.step","created_at":1710352449,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"tool_calls","status":"completed","cancelled_at":null,"completed_at":1710352475,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"tool_calls","tool_calls":[{"id":"call_iWr0kQ2EaYMaxNdl0v3KYkx7","type":"function","function":{"name":"get_current_weather","arguments":"{\"location\":\"San Francisco, CA\",\"unit\":\"fahrenheit\"}","output":"70 degrees and sunny."}}]},"usage":{"prompt_tokens":291,"completion_tokens":24,"total_tokens":315}} + + event: thread.run.queued + data: {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"queued","started_at":1710352448,"expires_at":1710353047,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.in_progress + data: {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"in_progress","started_at":1710352475,"expires_at":1710353047,"cancelled_at":null,"failed_at":null,"completed_at":null,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":null,"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: thread.run.step.created + data: {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":null} + + event: thread.run.step.in_progress + data: {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"in_progress","cancelled_at":null,"completed_at":null,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":null} + + event: thread.message.created + data: {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.in_progress + data: {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"in_progress","incomplete_details":null,"incomplete_at":null,"completed_at":null,"role":"assistant","content":[],"metadata":{}} + + event: thread.message.delta + data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"The","annotations":[]}}]}} + + event: thread.message.delta + data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" current"}}]}} + + event: thread.message.delta + data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" weather"}}]}} + + ... + + event: thread.message.delta + data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":" sunny"}}]}} + + event: thread.message.delta + data: {"id":"msg_002","object":"thread.message.delta","delta":{"content":[{"index":0,"type":"text","text":{"value":"."}}]}} + + event: thread.message.completed + data: {"id":"msg_002","object":"thread.message","created_at":1710352476,"assistant_id":"asst_123","thread_id":"thread_123","run_id":"run_123","status":"completed","incomplete_details":null,"incomplete_at":null,"completed_at":1710352477,"role":"assistant","content":[{"type":"text","text":{"value":"The current weather in San Francisco, CA is 70 degrees Fahrenheit and sunny.","annotations":[]}}],"metadata":{}} + + event: thread.run.step.completed + data: {"id":"step_002","object":"thread.run.step","created_at":1710352476,"run_id":"run_123","assistant_id":"asst_123","thread_id":"thread_123","type":"message_creation","status":"completed","cancelled_at":null,"completed_at":1710352477,"expires_at":1710353047,"failed_at":null,"last_error":null,"step_details":{"type":"message_creation","message_creation":{"message_id":"msg_002"}},"usage":{"prompt_tokens":329,"completion_tokens":18,"total_tokens":347}} + + event: thread.run.completed + data: {"id":"run_123","object":"thread.run","created_at":1710352447,"assistant_id":"asst_123","thread_id":"thread_123","status":"completed","started_at":1710352475,"expires_at":null,"cancelled_at":null,"failed_at":null,"completed_at":1710352477,"required_action":null,"last_error":null,"model":"gpt-4o","instructions":null,"tools":[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather in a given location","parameters":{"type":"object","properties":{"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"},"unit":{"type":"string","enum":["celsius","fahrenheit"]}},"required":["location"]}}}],"metadata":{},"temperature":1.0,"top_p":1.0,"max_completion_tokens":null,"max_prompt_tokens":null,"truncation_strategy":{"type":"auto","last_messages":null},"incomplete_details":null,"usage":{"prompt_tokens":20,"completion_tokens":11,"total_tokens":31},"response_format":"auto","tool_choice":"auto","parallel_tool_calls":true}} + + event: done + data: [DONE] + /uploads: + post: + operationId: createUpload + tags: + - Uploads + summary: > + Creates an intermediate [Upload](/docs/api-reference/uploads/object) + object + + that you can add [Parts](/docs/api-reference/uploads/part-object) to. + + Currently, an Upload can accept at most 8 GB in total and expires after + an + + hour after you create it. + + + Once you complete the Upload, we will create a + + [File](/docs/api-reference/files/object) object that contains all the + parts + + you uploaded. This File is usable in the rest of our platform as a + regular + + File object. + + + For certain `purpose` values, the correct `mime_type` must be + specified. + + Please refer to documentation for the + + [supported MIME types for your use + case](/docs/assistants/tools/file-search#supported-files). + + + For guidance on the proper filename extensions for each purpose, please + + follow the documentation on [creating a + + File](/docs/api-reference/files/create). + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateUploadRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Upload" + x-oaiMeta: + name: Create upload + group: uploads + returns: The [Upload](/docs/api-reference/uploads/object) object with status + `pending`. + examples: + request: + curl: | + curl https://api.openai.com/v1/uploads \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -d '{ + "purpose": "fine-tune", + "filename": "training_examples.jsonl", + "bytes": 2147483648, + "mime_type": "text/jsonl" + }' + response: | + { + "id": "upload_abc123", + "object": "upload", + "bytes": 2147483648, + "created_at": 1719184911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + "status": "pending", + "expires_at": 1719127296 + } + /uploads/{upload_id}/cancel: + post: + operationId: cancelUpload + tags: + - Uploads + summary: | + Cancels the Upload. No Parts may be added after an Upload is cancelled. + parameters: + - in: path + name: upload_id + required: true + schema: + type: string + example: upload_abc123 + description: | + The ID of the Upload. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Upload" + x-oaiMeta: + name: Cancel upload + group: uploads + returns: The [Upload](/docs/api-reference/uploads/object) object with status + `cancelled`. + examples: + request: + curl: | + curl https://api.openai.com/v1/uploads/upload_abc123/cancel + response: | + { + "id": "upload_abc123", + "object": "upload", + "bytes": 2147483648, + "created_at": 1719184911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + "status": "cancelled", + "expires_at": 1719127296 + } + /uploads/{upload_id}/complete: + post: + operationId: completeUpload + tags: + - Uploads + summary: > + Completes the [Upload](/docs/api-reference/uploads/object). + + + Within the returned Upload object, there is a nested + [File](/docs/api-reference/files/object) object that is ready to use in + the rest of the platform. + + + You can specify the order of the Parts by passing in an ordered list of + the Part IDs. + + + The number of bytes uploaded upon completion must match the number of + bytes initially specified when creating the Upload object. No Parts may + be added after an Upload is completed. + parameters: + - in: path + name: upload_id + required: true + schema: + type: string + example: upload_abc123 + description: | + The ID of the Upload. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CompleteUploadRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/Upload" + x-oaiMeta: + name: Complete upload + group: uploads + returns: The [Upload](/docs/api-reference/uploads/object) object with status + `completed` with an additional `file` property containing the created + usable File object. + examples: + request: + curl: | + curl https://api.openai.com/v1/uploads/upload_abc123/complete + -d '{ + "part_ids": ["part_def456", "part_ghi789"] + }' + response: | + { + "id": "upload_abc123", + "object": "upload", + "bytes": 2147483648, + "created_at": 1719184911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + "status": "completed", + "expires_at": 1719127296, + "file": { + "id": "file-xyz321", + "object": "file", + "bytes": 2147483648, + "created_at": 1719186911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + } + } + /uploads/{upload_id}/parts: + post: + operationId: addUploadPart + tags: + - Uploads + summary: > + Adds a [Part](/docs/api-reference/uploads/part-object) to an + [Upload](/docs/api-reference/uploads/object) object. A Part represents a + chunk of bytes from the file you are trying to upload. + + + Each Part can be at most 64 MB, and you can add Parts until you hit the + Upload maximum of 8 GB. + + + It is possible to add multiple Parts in parallel. You can decide the + intended order of the Parts when you [complete the + Upload](/docs/api-reference/uploads/complete). + parameters: + - in: path + name: upload_id + required: true + schema: + type: string + example: upload_abc123 + description: | + The ID of the Upload. + requestBody: + required: true + content: + multipart/form-data: + schema: + $ref: "#/components/schemas/AddUploadPartRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/UploadPart" + x-oaiMeta: + name: Add upload part + group: uploads + returns: The upload [Part](/docs/api-reference/uploads/part-object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/uploads/upload_abc123/parts + -F data="aHR0cHM6Ly9hcGkub3BlbmFpLmNvbS92MS91cGxvYWRz..." + response: | + { + "id": "part_def456", + "object": "upload.part", + "created_at": 1719185911, + "upload_id": "upload_abc123" + } + /vector_stores: + get: + operationId: listVectorStores + tags: + - Vector stores + summary: Returns a list of vector stores. + parameters: + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListVectorStoresResponse" + x-oaiMeta: + name: List vector stores + group: vector_stores + returns: A list of [vector store](/docs/api-reference/vector-stores/object) + objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_stores = client.vector_stores.list() + print(vector_stores) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStores = await openai.vectorStores.list(); + console.log(vectorStores); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + }, + { + "id": "vs_abc456", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ v2", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + } + ], + "first_id": "vs_abc123", + "last_id": "vs_abc456", + "has_more": false + } + post: + operationId: createVectorStore + tags: + - Vector stores + summary: Create a vector store. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateVectorStoreRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreObject" + x-oaiMeta: + name: Create vector store + group: vector_stores + returns: A [vector store](/docs/api-reference/vector-stores/object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "name": "Support FAQ" + }' + python: | + from openai import OpenAI + client = OpenAI() + + vector_store = client.vector_stores.create( + name="Support FAQ" + ) + print(vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStore = await openai.vectorStores.create({ + name: "Support FAQ" + }); + console.log(vectorStore); + } + + main(); + response: | + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + } + /vector_stores/{vector_store_id}: + get: + operationId: getVectorStore + tags: + - Vector stores + summary: Retrieves a vector store. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store to retrieve. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreObject" + x-oaiMeta: + name: Retrieve vector store + group: vector_stores + returns: The [vector store](/docs/api-reference/vector-stores/object) object + matching the specified ID. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store = client.vector_stores.retrieve( + vector_store_id="vs_abc123" + ) + print(vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStore = await openai.vectorStores.retrieve( + "vs_abc123" + ); + console.log(vectorStore); + } + + main(); + response: | + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776 + } + post: + operationId: modifyVectorStore + tags: + - Vector stores + summary: Modifies a vector store. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store to modify. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/UpdateVectorStoreRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreObject" + x-oaiMeta: + name: Modify vector store + group: vector_stores + returns: The modified [vector store](/docs/api-reference/vector-stores/object) + object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + -d '{ + "name": "Support FAQ" + }' + python: | + from openai import OpenAI + client = OpenAI() + + vector_store = client.vector_stores.update( + vector_store_id="vs_abc123", + name="Support FAQ" + ) + print(vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStore = await openai.vectorStores.update( + "vs_abc123", + { + name: "Support FAQ" + } + ); + console.log(vectorStore); + } + + main(); + response: | + { + "id": "vs_abc123", + "object": "vector_store", + "created_at": 1699061776, + "name": "Support FAQ", + "bytes": 139920, + "file_counts": { + "in_progress": 0, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 3 + } + } + delete: + operationId: deleteVectorStore + tags: + - Vector stores + summary: Delete a vector store. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteVectorStoreResponse" + x-oaiMeta: + name: Delete vector store + group: vector_stores + returns: Deletion status + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -X DELETE + python: | + from openai import OpenAI + client = OpenAI() + + deleted_vector_store = client.vector_stores.delete( + vector_store_id="vs_abc123" + ) + print(deleted_vector_store) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const deletedVectorStore = await openai.vectorStores.del( + "vs_abc123" + ); + console.log(deletedVectorStore); + } + + main(); + response: | + { + id: "vs_abc123", + object: "vector_store.deleted", + deleted: true + } + /vector_stores/{vector_store_id}/file_batches: + post: + operationId: createVectorStoreFileBatch + tags: + - Vector stores + summary: Create a vector store file batch. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: | + The ID of the vector store for which to create a File Batch. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateVectorStoreFileBatchRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileBatchObject" + x-oaiMeta: + name: Create vector store file batch + group: vector_stores + returns: A [vector store file + batch](/docs/api-reference/vector-stores-file-batches/batch-object) + object. + examples: + request: + curl: > + curl + https://api.openai.com/v1/vector_stores/vs_abc123/file_batches \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "file_ids": ["file-abc123", "file-abc456"] + }' + python: > + from openai import OpenAI + + client = OpenAI() + + + vector_store_file_batch = + client.vector_stores.file_batches.create( + vector_store_id="vs_abc123", + file_ids=["file-abc123", "file-abc456"] + ) + + print(vector_store_file_batch) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const myVectorStoreFileBatch = await openai.vectorStores.fileBatches.create( + "vs_abc123", + { + file_ids: ["file-abc123", "file-abc456"] + } + ); + console.log(myVectorStoreFileBatch); + } + + + main(); + response: | + { + "id": "vsfb_abc123", + "object": "vector_store.file_batch", + "created_at": 1699061776, + "vector_store_id": "vs_abc123", + "status": "in_progress", + "file_counts": { + "in_progress": 1, + "completed": 1, + "failed": 0, + "cancelled": 0, + "total": 0, + } + } + /vector_stores/{vector_store_id}/file_batches/{batch_id}: + get: + operationId: getVectorStoreFileBatch + tags: + - Vector stores + summary: Retrieves a vector store file batch. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: The ID of the vector store that the file batch belongs to. + - in: path + name: batch_id + required: true + schema: + type: string + example: vsfb_abc123 + description: The ID of the file batch being retrieved. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileBatchObject" + x-oaiMeta: + name: Retrieve vector store file batch + group: vector_stores + returns: The [vector store file + batch](/docs/api-reference/vector-stores-file-batches/batch-object) + object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: > + from openai import OpenAI + + client = OpenAI() + + + vector_store_file_batch = + client.vector_stores.file_batches.retrieve( + vector_store_id="vs_abc123", + batch_id="vsfb_abc123" + ) + + print(vector_store_file_batch) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const vectorStoreFileBatch = await openai.vectorStores.fileBatches.retrieve( + "vs_abc123", + "vsfb_abc123" + ); + console.log(vectorStoreFileBatch); + } + + + main(); + response: | + { + "id": "vsfb_abc123", + "object": "vector_store.file_batch", + "created_at": 1699061776, + "vector_store_id": "vs_abc123", + "status": "in_progress", + "file_counts": { + "in_progress": 1, + "completed": 1, + "failed": 0, + "cancelled": 0, + "total": 0, + } + } + /vector_stores/{vector_store_id}/file_batches/{batch_id}/cancel: + post: + operationId: cancelVectorStoreFileBatch + tags: + - Vector stores + summary: Cancel a vector store file batch. This attempts to cancel the + processing of files in this batch as soon as possible. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store that the file batch belongs to. + - in: path + name: batch_id + required: true + schema: + type: string + description: The ID of the file batch to cancel. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileBatchObject" + x-oaiMeta: + name: Cancel vector store file batch + group: vector_stores + returns: The modified vector store file batch object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123/cancel \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -X POST + python: > + from openai import OpenAI + + client = OpenAI() + + + deleted_vector_store_file_batch = + client.vector_stores.file_batches.cancel( + vector_store_id="vs_abc123", + file_batch_id="vsfb_abc123" + ) + + print(deleted_vector_store_file_batch) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const deletedVectorStoreFileBatch = await openai.vectorStores.fileBatches.cancel( + "vs_abc123", + "vsfb_abc123" + ); + console.log(deletedVectorStoreFileBatch); + } + + + main(); + response: | + { + "id": "vsfb_abc123", + "object": "vector_store.file_batch", + "created_at": 1699061776, + "vector_store_id": "vs_abc123", + "status": "in_progress", + "file_counts": { + "in_progress": 12, + "completed": 3, + "failed": 0, + "cancelled": 0, + "total": 15, + } + } + /vector_stores/{vector_store_id}/file_batches/{batch_id}/files: + get: + operationId: listFilesInVectorStoreBatch + tags: + - Vector stores + summary: Returns a list of vector store files in a batch. + parameters: + - name: vector_store_id + in: path + description: The ID of the vector store that the files belong to. + required: true + schema: + type: string + - name: batch_id + in: path + description: The ID of the file batch that the files belong to. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + - name: filter + in: query + description: Filter by file status. One of `in_progress`, `completed`, `failed`, + `cancelled`. + schema: + type: string + enum: + - in_progress + - completed + - failed + - cancelled + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListVectorStoreFilesResponse" + x-oaiMeta: + name: List vector store files in a batch + group: vector_stores + returns: A list of [vector store + file](/docs/api-reference/vector-stores-files/file-object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files_batches/vsfb_abc123/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_files = client.vector_stores.file_batches.list_files( + vector_store_id="vs_abc123", + batch_id="vsfb_abc123" + ) + print(vector_store_files) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const vectorStoreFiles = await openai.vectorStores.fileBatches.listFiles( + "vs_abc123", + "vsfb_abc123" + ); + console.log(vectorStoreFiles); + } + + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + }, + { + "id": "file-abc456", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + } + ], + "first_id": "file-abc123", + "last_id": "file-abc456", + "has_more": false + } + /vector_stores/{vector_store_id}/files: + get: + operationId: listVectorStoreFiles + tags: + - Vector stores + summary: Returns a list of vector store files. + parameters: + - name: vector_store_id + in: path + description: The ID of the vector store that the files belong to. + required: true + schema: + type: string + - name: limit + in: query + description: > + A limit on the number of objects to be returned. Limit can range + between 1 and 100, and the default is 20. + required: false + schema: + type: integer + default: 20 + - name: order + in: query + description: > + Sort order by the `created_at` timestamp of the objects. `asc` for + ascending order and `desc` for descending order. + schema: + type: string + default: desc + enum: + - asc + - desc + - name: after + in: query + description: > + A cursor for use in pagination. `after` is an object ID that defines + your place in the list. For instance, if you make a list request and + receive 100 objects, ending with obj_foo, your subsequent call can + include after=obj_foo in order to fetch the next page of the list. + schema: + type: string + - name: before + in: query + description: > + A cursor for use in pagination. `before` is an object ID that + defines your place in the list. For instance, if you make a list + request and receive 100 objects, starting with obj_foo, your + subsequent call can include before=obj_foo in order to fetch the + previous page of the list. + schema: + type: string + - name: filter + in: query + description: Filter by file status. One of `in_progress`, `completed`, `failed`, + `cancelled`. + schema: + type: string + enum: + - in_progress + - completed + - failed + - cancelled + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/ListVectorStoreFilesResponse" + x-oaiMeta: + name: List vector store files + group: vector_stores + returns: A list of [vector store + file](/docs/api-reference/vector-stores-files/file-object) objects. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_files = client.vector_stores.files.list( + vector_store_id="vs_abc123" + ) + print(vector_store_files) + node.js: | + import OpenAI from "openai"; + const openai = new OpenAI(); + + async function main() { + const vectorStoreFiles = await openai.vectorStores.files.list( + "vs_abc123" + ); + console.log(vectorStoreFiles); + } + + main(); + response: | + { + "object": "list", + "data": [ + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + }, + { + "id": "file-abc456", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abc123" + } + ], + "first_id": "file-abc123", + "last_id": "file-abc456", + "has_more": false + } + post: + operationId: createVectorStoreFile + tags: + - Vector stores + summary: Create a vector store file by attaching a + [File](/docs/api-reference/files) to a [vector + store](/docs/api-reference/vector-stores/object). + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: | + The ID of the vector store for which to create a File. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/CreateVectorStoreFileRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileObject" + x-oaiMeta: + name: Create vector store file + group: vector_stores + returns: A [vector store + file](/docs/api-reference/vector-stores-files/file-object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -d '{ + "file_id": "file-abc123" + }' + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_file = client.vector_stores.files.create( + vector_store_id="vs_abc123", + file_id="file-abc123" + ) + print(vector_store_file) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const myVectorStoreFile = await openai.vectorStores.files.create( + "vs_abc123", + { + file_id: "file-abc123" + } + ); + console.log(myVectorStoreFile); + } + + + main(); + response: | + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "usage_bytes": 1234, + "vector_store_id": "vs_abcd", + "status": "completed", + "last_error": null + } + /vector_stores/{vector_store_id}/files/{file_id}: + get: + operationId: getVectorStoreFile + tags: + - Vector stores + summary: Retrieves a vector store file. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: The ID of the vector store that the file belongs to. + - in: path + name: file_id + required: true + schema: + type: string + example: file-abc123 + description: The ID of the file being retrieved. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileObject" + x-oaiMeta: + name: Retrieve vector store file + group: vector_stores + returns: The [vector store + file](/docs/api-reference/vector-stores-files/file-object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" + python: | + from openai import OpenAI + client = OpenAI() + + vector_store_file = client.vector_stores.files.retrieve( + vector_store_id="vs_abc123", + file_id="file-abc123" + ) + print(vector_store_file) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const vectorStoreFile = await openai.vectorStores.files.retrieve( + "vs_abc123", + "file-abc123" + ); + console.log(vectorStoreFile); + } + + + main(); + response: | + { + "id": "file-abc123", + "object": "vector_store.file", + "created_at": 1699061776, + "vector_store_id": "vs_abcd", + "status": "completed", + "last_error": null + } + delete: + operationId: deleteVectorStoreFile + tags: + - Vector stores + summary: Delete a vector store file. This will remove the file from the vector + store but the file itself will not be deleted. To delete the file, use + the [delete file](/docs/api-reference/files/delete) endpoint. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + description: The ID of the vector store that the file belongs to. + - in: path + name: file_id + required: true + schema: + type: string + description: The ID of the file to delete. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/DeleteVectorStoreFileResponse" + x-oaiMeta: + name: Delete vector store file + group: vector_stores + returns: Deletion status + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123 \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -H "OpenAI-Beta: assistants=v2" \ + -X DELETE + python: | + from openai import OpenAI + client = OpenAI() + + deleted_vector_store_file = client.vector_stores.files.delete( + vector_store_id="vs_abc123", + file_id="file-abc123" + ) + print(deleted_vector_store_file) + node.js: > + import OpenAI from "openai"; + + const openai = new OpenAI(); + + + async function main() { + const deletedVectorStoreFile = await openai.vectorStores.files.del( + "vs_abc123", + "file-abc123" + ); + console.log(deletedVectorStoreFile); + } + + + main(); + response: | + { + id: "file-abc123", + object: "vector_store.file.deleted", + deleted: true + } + post: + operationId: updateVectorStoreFileAttributes + tags: + - Vector stores + summary: Update attributes on a vector store file. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: The ID of the vector store the file belongs to. + - in: path + name: file_id + required: true + schema: + type: string + example: file-abc123 + description: The ID of the file to update attributes. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/UpdateVectorStoreFileAttributesRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileObject" + x-oaiMeta: + name: Update vector store file attributes + group: vector_stores + returns: The updated [vector store + file](/docs/api-reference/vector-stores-files/file-object) object. + examples: + request: + curl: | + curl https://api.openai.com/v1/vector_stores/{vector_store_id}/files/{file_id} \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{"attributes": {"key1": "value1", "key2": 2}}' + response: | + { + "id": "file-abc123", + "object": "vector_store.file", + "usage_bytes": 1234, + "created_at": 1699061776, + "vector_store_id": "vs_abcd", + "status": "completed", + "last_error": null, + "chunking_strategy": {...}, + "attributes": {"key1": "value1", "key2": 2} + } + /vector_stores/{vector_store_id}/files/{file_id}/content: + get: + operationId: retrieveVectorStoreFileContent + tags: + - Vector stores + summary: Retrieve the parsed contents of a vector store file. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: The ID of the vector store. + - in: path + name: file_id + required: true + schema: + type: string + example: file-abc123 + description: The ID of the file within the vector store. + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreFileContentResponse" + x-oaiMeta: + name: Retrieve vector store file content + group: vector_stores + returns: The parsed contents of the specified vector store file. + examples: + request: + curl: | + curl \ + https://api.openai.com/v1/vector_stores/vs_abc123/files/file-abc123/content \ + -H "Authorization: Bearer $OPENAI_API_KEY" + response: | + { + "file_id": "file-abc123", + "filename": "example.txt", + "attributes": {"key": "value"}, + "content": [ + {"type": "text", "text": "..."}, + ... + ] + } + /vector_stores/{vector_store_id}/search: + post: + operationId: searchVectorStore + tags: + - Vector stores + summary: Search a vector store for relevant chunks based on a query and file + attributes filter. + parameters: + - in: path + name: vector_store_id + required: true + schema: + type: string + example: vs_abc123 + description: The ID of the vector store to search. + requestBody: + required: true + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreSearchRequest" + responses: + "200": + description: OK + content: + application/json: + schema: + $ref: "#/components/schemas/VectorStoreSearchResultsPage" + x-oaiMeta: + name: Search vector store + group: vector_stores + returns: A page of search results from the vector store. + examples: + request: + curl: | + curl -X POST \ + https://api.openai.com/v1/vector_stores/vs_abc123/search \ + -H "Authorization: Bearer $OPENAI_API_KEY" \ + -H "Content-Type: application/json" \ + -d '{"query": "What is the return policy?", "filters": {...}}' + response: | + { + "object": "vector_store.search_results.page", + "search_query": "What is the return policy?", + "data": [ + { + "file_id": "file_123", + "filename": "document.pdf", + "score": 0.95, + "attributes": { + "author": "John Doe", + "date": "2023-01-01" + }, + "content": [ + { + "type": "text", + "text": "Relevant chunk" + } + ] + }, + { + "file_id": "file_456", + "filename": "notes.txt", + "score": 0.89, + "attributes": { + "author": "Jane Smith", + "date": "2023-01-02" + }, + "content": [ + { + "type": "text", + "text": "Sample text content from the vector store." + } + ] + } + ], + "has_more": false, + "next_page": null + } +components: + schemas: + AddUploadPartRequest: + type: object + additionalProperties: false + properties: + data: + description: | + The chunk of bytes for this Part. + type: string + format: binary + required: + - data + AdminApiKey: + type: object + description: Represents an individual Admin API key in an org. + properties: + object: + type: string + example: organization.admin_api_key + description: The object type, which is always `organization.admin_api_key` + x-stainless-const: true + id: + type: string + example: key_abc + description: The identifier, which can be referenced in API endpoints + name: + type: string + example: Administration Key + description: The name of the API key + redacted_value: + type: string + example: sk-admin...def + description: The redacted value of the API key + value: + type: string + example: sk-admin-1234abcd + description: The value of the API key. Only shown on create. + created_at: + type: integer + format: int64 + example: 1711471533 + description: The Unix timestamp (in seconds) of when the API key was created + last_used_at: + type: integer + format: int64 + nullable: true + example: 1711471534 + description: The Unix timestamp (in seconds) of when the API key was last used + owner: + type: object + properties: + type: + type: string + example: user + description: Always `user` + object: + type: string + example: organization.user + description: The object type, which is always organization.user + id: + type: string + example: sa_456 + description: The identifier, which can be referenced in API endpoints + name: + type: string + example: My Service Account + description: The name of the user + created_at: + type: integer + format: int64 + example: 1711471533 + description: The Unix timestamp (in seconds) of when the user was created + role: + type: string + example: owner + description: Always `owner` + required: + - object + - redacted_value + - name + - created_at + - last_used_at + - id + - owner + x-oaiMeta: + name: The admin API key object + example: | + { + "object": "organization.admin_api_key", + "id": "key_abc", + "name": "Main Admin Key", + "redacted_value": "sk-admin...xyz", + "created_at": 1711471533, + "last_used_at": 1711471534, + "owner": { + "type": "user", + "object": "organization.user", + "id": "user_123", + "name": "John Doe", + "created_at": 1711471533, + "role": "owner" + } + } + ApiKeyList: + type: object + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/AdminApiKey" + has_more: + type: boolean + example: false + first_id: + type: string + example: key_abc + last_id: + type: string + example: key_xyz + AssistantObject: + type: object + title: Assistant + description: Represents an `assistant` that can call the model and use tools. + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `assistant`. + type: string + enum: + - assistant + x-stainless-const: true + created_at: + description: The Unix timestamp (in seconds) for when the assistant was created. + type: integer + name: + description: | + The name of the assistant. The maximum length is 256 characters. + type: string + maxLength: 256 + nullable: true + description: + description: > + The description of the assistant. The maximum length is 512 + characters. + type: string + maxLength: 512 + nullable: true + model: + description: > + ID of the model to use. You can use the [List + models](/docs/api-reference/models/list) API to see all of your + available models, or see our [Model overview](/docs/models) for + descriptions of them. + type: string + instructions: + description: > + The system instructions that the assistant uses. The maximum length + is 256,000 characters. + type: string + maxLength: 256000 + nullable: true + tools: + description: > + A list of tool enabled on the assistant. There can be a maximum of + 128 tools per assistant. Tools can be of types `code_interpreter`, + `file_search`, or `function`. + default: [] + type: array + maxItems: 128 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + tool_resources: + type: object + description: > + A set of resources that are used by the assistant's tools. The + resources are specific to the type of tool. For example, the + `code_interpreter` tool requires a list of file IDs, while the + `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter`` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The ID of the [vector + store](/docs/api-reference/vector-stores/object) attached to + this assistant. There can be a maximum of 1 vector store + attached to the assistant. + maxItems: 1 + items: + type: string + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + temperature: + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or temperature but not both. + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - id + - object + - created_at + - name + - description + - model + - instructions + - tools + - metadata + x-oaiMeta: + name: The assistant object + beta: true + example: > + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1698984975, + "name": "Math Tutor", + "description": null, + "model": "gpt-4o", + "instructions": "You are a personal math tutor. When asked a question, write and run Python code to answer the question.", + "tools": [ + { + "type": "code_interpreter" + } + ], + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + AssistantStreamEvent: + description: > + Represents an event emitted when streaming a Run. + + + Each event in a server-sent events stream has an `event` and `data` + property: + + + ``` + + event: thread.created + + data: {"id": "thread_123", "object": "thread", ...} + + ``` + + + We emit events whenever a new object is created, transitions to a new + state, or is being + + streamed in parts (deltas). For example, we emit `thread.run.created` + when a new run + + is created, `thread.run.completed` when a run completes, and so on. When + an Assistant chooses + + to create a message during a run, we emit a `thread.message.created + event`, a + + `thread.message.in_progress` event, many `thread.message.delta` events, + and finally a + + `thread.message.completed` event. + + + We may add additional events over time, so we recommend handling unknown + events gracefully + + in your code. See the [Assistants API + quickstart](/docs/assistants/overview) to learn how to + + integrate the Assistants API with streaming. + oneOf: + - $ref: "#/components/schemas/ThreadStreamEvent" + - $ref: "#/components/schemas/RunStreamEvent" + - $ref: "#/components/schemas/RunStepStreamEvent" + - $ref: "#/components/schemas/MessageStreamEvent" + - $ref: "#/components/schemas/ErrorEvent" + - $ref: "#/components/schemas/DoneEvent" + x-oaiMeta: + name: Assistant stream events + beta: true + AssistantSupportedModels: + type: string + enum: + - gpt-4.1 + - gpt-4.1-mini + - gpt-4.1-nano + - gpt-4.1-2025-04-14 + - gpt-4.1-mini-2025-04-14 + - gpt-4.1-nano-2025-04-14 + - o3-mini + - o3-mini-2025-01-31 + - o1 + - o1-2024-12-17 + - gpt-4o + - gpt-4o-2024-11-20 + - gpt-4o-2024-08-06 + - gpt-4o-2024-05-13 + - gpt-4o-mini + - gpt-4o-mini-2024-07-18 + - gpt-4.5-preview + - gpt-4.5-preview-2025-02-27 + - gpt-4-turbo + - gpt-4-turbo-2024-04-09 + - gpt-4-0125-preview + - gpt-4-turbo-preview + - gpt-4-1106-preview + - gpt-4-vision-preview + - gpt-4 + - gpt-4-0314 + - gpt-4-0613 + - gpt-4-32k + - gpt-4-32k-0314 + - gpt-4-32k-0613 + - gpt-3.5-turbo + - gpt-3.5-turbo-16k + - gpt-3.5-turbo-0613 + - gpt-3.5-turbo-1106 + - gpt-3.5-turbo-0125 + - gpt-3.5-turbo-16k-0613 + AssistantToolsCode: + type: object + title: Code interpreter tool + properties: + type: + type: string + description: "The type of tool being defined: `code_interpreter`" + enum: + - code_interpreter + x-stainless-const: true + required: + - type + AssistantToolsFileSearch: + type: object + title: FileSearch tool + properties: + type: + type: string + description: "The type of tool being defined: `file_search`" + enum: + - file_search + x-stainless-const: true + file_search: + type: object + description: Overrides for the file search tool. + properties: + max_num_results: + type: integer + minimum: 1 + maximum: 50 + description: | + The maximum number of results the file search tool should output. The default is 20 for `gpt-4*` models and 5 for `gpt-3.5-turbo`. This number should be between 1 and 50 inclusive. + + Note that the file search tool may output fewer than `max_num_results` results. See the [file search tool documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) for more information. + ranking_options: + $ref: "#/components/schemas/FileSearchRankingOptions" + required: + - type + AssistantToolsFileSearchTypeOnly: + type: object + title: FileSearch tool + properties: + type: + type: string + description: "The type of tool being defined: `file_search`" + enum: + - file_search + x-stainless-const: true + required: + - type + AssistantToolsFunction: + type: object + title: Function tool + properties: + type: + type: string + description: "The type of tool being defined: `function`" + enum: + - function + x-stainless-const: true + function: + $ref: "#/components/schemas/FunctionObject" + required: + - type + - function + AssistantsApiResponseFormatOption: + description: > + Specifies the format that the model must output. Compatible with + [GPT-4o](/docs/models#gpt-4o), [GPT-4 + Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models + since `gpt-3.5-turbo-1106`. + + + Setting to `{ "type": "json_schema", "json_schema": {...} }` enables + Structured Outputs which ensures the model will match your supplied JSON + schema. Learn more in the [Structured Outputs + guide](/docs/guides/structured-outputs). + + + Setting to `{ "type": "json_object" }` enables JSON mode, which ensures + the message the model generates is valid JSON. + + + **Important:** when using JSON mode, you **must** also instruct the + model to produce JSON yourself via a system or user message. Without + this, the model may generate an unending stream of whitespace until the + generation reaches the token limit, resulting in a long-running and + seemingly "stuck" request. Also note that the message content may be + partially cut off if `finish_reason="length"`, which indicates the + generation exceeded `max_tokens` or the conversation exceeded the max + context length. + oneOf: + - type: string + description: | + `auto` is the default value + enum: + - auto + x-stainless-const: true + - $ref: "#/components/schemas/ResponseFormatText" + - $ref: "#/components/schemas/ResponseFormatJsonObject" + - $ref: "#/components/schemas/ResponseFormatJsonSchema" + AssistantsApiToolChoiceOption: + description: > + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tools and instead generates a + message. + + `auto` is the default value and means the model can pick between + generating a message or calling one or more tools. + + `required` means the model must call one or more tools before responding + to the user. + + Specifying a particular tool like `{"type": "file_search"}` or `{"type": + "function", "function": {"name": "my_function"}}` forces the model to + call that tool. + oneOf: + - type: string + description: > + `none` means the model will not call any tools and instead generates + a message. `auto` means the model can pick between generating a + message or calling one or more tools. `required` means the model + must call one or more tools before responding to the user. + enum: + - none + - auto + - required + - $ref: "#/components/schemas/AssistantsNamedToolChoice" + AssistantsNamedToolChoice: + type: object + description: Specifies a tool the model should use. Use to force the model to + call a specific tool. + properties: + type: + type: string + enum: + - function + - code_interpreter + - file_search + description: The type of the tool. If type is `function`, the function name must + be set + function: + type: object + properties: + name: + type: string + description: The name of the function to call. + required: + - name + required: + - type + AudioResponseFormat: + description: > + The format of the output, in one of these options: `json`, `text`, + `srt`, `verbose_json`, or `vtt`. For `gpt-4o-transcribe` and + `gpt-4o-mini-transcribe`, the only supported format is `json`. + type: string + enum: + - json + - text + - srt + - verbose_json + - vtt + default: json + AuditLog: + type: object + description: A log of a user action or configuration change within this organization. + properties: + id: + type: string + description: The ID of this log. + type: + $ref: "#/components/schemas/AuditLogEventType" + effective_at: + type: integer + description: The Unix timestamp (in seconds) of the event. + project: + type: object + description: The project that the action was scoped to. Absent for actions not + scoped to projects. + properties: + id: + type: string + description: The project ID. + name: + type: string + description: The project title. + actor: + $ref: "#/components/schemas/AuditLogActor" + api_key.created: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The tracking ID of the API key. + data: + type: object + description: The payload used to create the API key. + properties: + scopes: + type: array + items: + type: string + description: A list of scopes allowed for the API key, e.g. + `["api.model.request"]` + api_key.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The tracking ID of the API key. + changes_requested: + type: object + description: The payload used to update the API key. + properties: + scopes: + type: array + items: + type: string + description: A list of scopes allowed for the API key, e.g. + `["api.model.request"]` + api_key.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The tracking ID of the API key. + checkpoint_permission.created: + type: object + description: The project and fine-tuned model checkpoint that the checkpoint + permission was created for. + properties: + id: + type: string + description: The ID of the checkpoint permission. + data: + type: object + description: The payload used to create the checkpoint permission. + properties: + project_id: + type: string + description: The ID of the project that the checkpoint permission was created + for. + fine_tuned_model_checkpoint: + type: string + description: The ID of the fine-tuned model checkpoint. + checkpoint_permission.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The ID of the checkpoint permission. + invite.sent: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The ID of the invite. + data: + type: object + description: The payload used to create the invite. + properties: + email: + type: string + description: The email invited to the organization. + role: + type: string + description: The role the email was invited to be. Is either `owner` or + `member`. + invite.accepted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The ID of the invite. + invite.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The ID of the invite. + login.failed: + type: object + description: The details for events with this `type`. + properties: + error_code: + type: string + description: The error code of the failure. + error_message: + type: string + description: The error message of the failure. + logout.failed: + type: object + description: The details for events with this `type`. + properties: + error_code: + type: string + description: The error code of the failure. + error_message: + type: string + description: The error message of the failure. + organization.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The organization ID. + changes_requested: + type: object + description: The payload used to update the organization settings. + properties: + title: + type: string + description: The organization title. + description: + type: string + description: The organization description. + name: + type: string + description: The organization name. + threads_ui_visibility: + type: string + description: Visibility of the threads page which shows messages created with + the Assistants API and Playground. One of `ANY_ROLE`, + `OWNERS`, or `NONE`. + usage_dashboard_visibility: + type: string + description: Visibility of the usage dashboard which shows activity and costs + for your organization. One of `ANY_ROLE` or `OWNERS`. + api_call_logging: + type: string + description: How your organization logs data from supported API calls. One of + `disabled`, `enabled_per_call`, `enabled_for_all_projects`, + or `enabled_for_selected_projects` + api_call_logging_project_ids: + type: string + description: The list of project ids if api_call_logging is set to + `enabled_for_selected_projects` + project.created: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The project ID. + data: + type: object + description: The payload used to create the project. + properties: + name: + type: string + description: The project name. + title: + type: string + description: The title of the project as seen on the dashboard. + project.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The project ID. + changes_requested: + type: object + description: The payload used to update the project. + properties: + title: + type: string + description: The title of the project as seen on the dashboard. + project.archived: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The project ID. + rate_limit.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The rate limit ID + changes_requested: + type: object + description: The payload used to update the rate limits. + properties: + max_requests_per_1_minute: + type: integer + description: The maximum requests per minute. + max_tokens_per_1_minute: + type: integer + description: The maximum tokens per minute. + max_images_per_1_minute: + type: integer + description: The maximum images per minute. Only relevant for certain models. + max_audio_megabytes_per_1_minute: + type: integer + description: The maximum audio megabytes per minute. Only relevant for certain + models. + max_requests_per_1_day: + type: integer + description: The maximum requests per day. Only relevant for certain models. + batch_1_day_max_input_tokens: + type: integer + description: The maximum batch input tokens per day. Only relevant for certain + models. + rate_limit.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The rate limit ID + service_account.created: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The service account ID. + data: + type: object + description: The payload used to create the service account. + properties: + role: + type: string + description: The role of the service account. Is either `owner` or `member`. + service_account.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The service account ID. + changes_requested: + type: object + description: The payload used to updated the service account. + properties: + role: + type: string + description: The role of the service account. Is either `owner` or `member`. + service_account.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The service account ID. + user.added: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The user ID. + data: + type: object + description: The payload used to add the user to the project. + properties: + role: + type: string + description: The role of the user. Is either `owner` or `member`. + user.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The project ID. + changes_requested: + type: object + description: The payload used to update the user. + properties: + role: + type: string + description: The role of the user. Is either `owner` or `member`. + user.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The user ID. + certificate.created: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The certificate ID. + name: + type: string + description: The name of the certificate. + certificate.updated: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The certificate ID. + name: + type: string + description: The name of the certificate. + certificate.deleted: + type: object + description: The details for events with this `type`. + properties: + id: + type: string + description: The certificate ID. + name: + type: string + description: The name of the certificate. + certificate: + type: string + description: The certificate content in PEM format. + certificates.activated: + type: object + description: The details for events with this `type`. + properties: + certificates: + type: array + items: + type: object + properties: + id: + type: string + description: The certificate ID. + name: + type: string + description: The name of the certificate. + certificates.deactivated: + type: object + description: The details for events with this `type`. + properties: + certificates: + type: array + items: + type: object + properties: + id: + type: string + description: The certificate ID. + name: + type: string + description: The name of the certificate. + required: + - id + - type + - effective_at + - actor + x-oaiMeta: + name: The audit log object + example: > + { + "id": "req_xxx_20240101", + "type": "api_key.created", + "effective_at": 1720804090, + "actor": { + "type": "session", + "session": { + "user": { + "id": "user-xxx", + "email": "user@example.com" + }, + "ip_address": "127.0.0.1", + "user_agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36" + } + }, + "api_key.created": { + "id": "key_xxxx", + "data": { + "scopes": ["resource.operation"] + } + } + } + AuditLogActor: + type: object + description: The actor who performed the audit logged action. + properties: + type: + type: string + description: The type of actor. Is either `session` or `api_key`. + enum: + - session + - api_key + session: + $ref: "#/components/schemas/AuditLogActorSession" + api_key: + $ref: "#/components/schemas/AuditLogActorApiKey" + AuditLogActorApiKey: + type: object + description: The API Key used to perform the audit logged action. + properties: + id: + type: string + description: The tracking id of the API key. + type: + type: string + description: The type of API key. Can be either `user` or `service_account`. + enum: + - user + - service_account + user: + $ref: "#/components/schemas/AuditLogActorUser" + service_account: + $ref: "#/components/schemas/AuditLogActorServiceAccount" + AuditLogActorServiceAccount: + type: object + description: The service account that performed the audit logged action. + properties: + id: + type: string + description: The service account id. + AuditLogActorSession: + type: object + description: The session in which the audit logged action was performed. + properties: + user: + $ref: "#/components/schemas/AuditLogActorUser" + ip_address: + type: string + description: The IP address from which the action was performed. + AuditLogActorUser: + type: object + description: The user who performed the audit logged action. + properties: + id: + type: string + description: The user id. + email: + type: string + description: The user email. + AuditLogEventType: + type: string + description: The event type. + enum: + - api_key.created + - api_key.updated + - api_key.deleted + - checkpoint_permission.created + - checkpoint_permission.deleted + - invite.sent + - invite.accepted + - invite.deleted + - login.succeeded + - login.failed + - logout.succeeded + - logout.failed + - organization.updated + - project.created + - project.updated + - project.archived + - service_account.created + - service_account.updated + - service_account.deleted + - rate_limit.updated + - rate_limit.deleted + - user.added + - user.updated + - user.deleted + AutoChunkingStrategyRequestParam: + type: object + title: Auto Chunking Strategy + description: The default strategy. This strategy currently uses a + `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`. + additionalProperties: false + properties: + type: + type: string + description: Always `auto`. + enum: + - auto + x-stainless-const: true + required: + - type + Batch: + type: object + properties: + id: + type: string + object: + type: string + enum: + - batch + description: The object type, which is always `batch`. + x-stainless-const: true + endpoint: + type: string + description: The OpenAI API endpoint used by the batch. + errors: + type: object + properties: + object: + type: string + description: The object type, which is always `list`. + data: + type: array + items: + type: object + properties: + code: + type: string + description: An error code identifying the error type. + message: + type: string + description: A human-readable message providing more details about the error. + param: + type: string + description: The name of the parameter that caused the error, if applicable. + nullable: true + line: + type: integer + description: The line number of the input file where the error occurred, if + applicable. + nullable: true + input_file_id: + type: string + description: The ID of the input file for the batch. + completion_window: + type: string + description: The time frame within which the batch should be processed. + status: + type: string + description: The current status of the batch. + enum: + - validating + - failed + - in_progress + - finalizing + - completed + - expired + - cancelling + - cancelled + output_file_id: + type: string + description: The ID of the file containing the outputs of successfully executed + requests. + error_file_id: + type: string + description: The ID of the file containing the outputs of requests with errors. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch was created. + in_progress_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch started + processing. + expires_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch will expire. + finalizing_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch started + finalizing. + completed_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch was completed. + failed_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch failed. + expired_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch expired. + cancelling_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch started + cancelling. + cancelled_at: + type: integer + description: The Unix timestamp (in seconds) for when the batch was cancelled. + request_counts: + type: object + properties: + total: + type: integer + description: Total number of requests in the batch. + completed: + type: integer + description: Number of requests that have been completed successfully. + failed: + type: integer + description: Number of requests that have failed. + required: + - total + - completed + - failed + description: The request counts for different statuses within the batch. + metadata: + $ref: "#/components/schemas/Metadata" + required: + - id + - object + - endpoint + - input_file_id + - completion_window + - status + - created_at + x-oaiMeta: + name: The batch object + example: | + { + "id": "batch_abc123", + "object": "batch", + "endpoint": "/v1/completions", + "errors": null, + "input_file_id": "file-abc123", + "completion_window": "24h", + "status": "completed", + "output_file_id": "file-cvaTdG", + "error_file_id": "file-HOWS94", + "created_at": 1711471533, + "in_progress_at": 1711471538, + "expires_at": 1711557933, + "finalizing_at": 1711493133, + "completed_at": 1711493163, + "failed_at": null, + "expired_at": null, + "cancelling_at": null, + "cancelled_at": null, + "request_counts": { + "total": 100, + "completed": 95, + "failed": 5 + }, + "metadata": { + "customer_id": "user_123456789", + "batch_description": "Nightly eval job", + } + } + BatchRequestInput: + type: object + description: The per-line object of the batch input file + properties: + custom_id: + type: string + description: A developer-provided per-request id that will be used to match + outputs to inputs. Must be unique for each request in a batch. + method: + type: string + enum: + - POST + description: The HTTP method to be used for the request. Currently only `POST` + is supported. + x-stainless-const: true + url: + type: string + description: The OpenAI API relative URL to be used for the request. Currently + `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are + supported. + x-oaiMeta: + name: The request input object + example: > + {"custom_id": "request-1", "method": "POST", "url": + "/v1/chat/completions", "body": {"model": "gpt-4o-mini", "messages": + [{"role": "system", "content": "You are a helpful assistant."}, + {"role": "user", "content": "What is 2+2?"}]}} + BatchRequestOutput: + type: object + description: The per-line object of the batch output and error files + properties: + id: + type: string + custom_id: + type: string + description: A developer-provided per-request id that will be used to match + outputs to inputs. + response: + type: object + nullable: true + properties: + status_code: + type: integer + description: The HTTP status code of the response + request_id: + type: string + description: An unique identifier for the OpenAI API request. Please include + this request ID when contacting support. + body: + type: object + x-oaiTypeLabel: map + description: The JSON body of the response + error: + type: object + nullable: true + description: For requests that failed with a non-HTTP error, this will contain + more information on the cause of the failure. + properties: + code: + type: string + description: A machine-readable error code. + message: + type: string + description: A human-readable error message. + x-oaiMeta: + name: The request output object + example: > + {"id": "batch_req_wnaDys", "custom_id": "request-2", "response": + {"status_code": 200, "request_id": "req_c187b3", "body": {"id": + "chatcmpl-9758Iw", "object": "chat.completion", "created": 1711475054, + "model": "gpt-4o-mini", "choices": [{"index": 0, "message": {"role": + "assistant", "content": "2 + 2 equals 4."}, "finish_reason": "stop"}], + "usage": {"prompt_tokens": 24, "completion_tokens": 15, + "total_tokens": 39}, "system_fingerprint": null}}, "error": null} + Certificate: + type: object + description: Represents an individual `certificate` uploaded to the organization. + properties: + object: + type: string + enum: + - certificate + - organization.certificate + - organization.project.certificate + description: > + The object type. + + + - If creating, updating, or getting a specific certificate, the + object type is `certificate`. + + - If listing, activating, or deactivating certificates for the + organization, the object type is `organization.certificate`. + + - If listing, activating, or deactivating certificates for a + project, the object type is `organization.project.certificate`. + x-stainless-const: true + id: + type: string + description: The identifier, which can be referenced in API endpoints + name: + type: string + description: The name of the certificate. + created_at: + type: integer + description: The Unix timestamp (in seconds) of when the certificate was uploaded. + certificate_details: + type: object + properties: + valid_at: + type: integer + description: The Unix timestamp (in seconds) of when the certificate becomes + valid. + expires_at: + type: integer + description: The Unix timestamp (in seconds) of when the certificate expires. + content: + type: string + description: The content of the certificate in PEM format. + active: + type: boolean + description: Whether the certificate is currently active at the specified scope. + Not returned when getting details for a specific certificate. + required: + - object + - id + - name + - created_at + - certificate_details + x-oaiMeta: + name: The certificate object + example: > + { + "object": "certificate", + "id": "cert_abc", + "name": "My Certificate", + "created_at": 1234567, + "certificate_details": { + "valid_at": 1234567, + "expires_at": 12345678, + "content": "-----BEGIN CERTIFICATE----- MIIGAjCCA...6znFlOW+ -----END CERTIFICATE-----" + } + } + ChatCompletionDeleted: + type: object + properties: + object: + type: string + description: The type of object being deleted. + enum: + - chat.completion.deleted + x-stainless-const: true + id: + type: string + description: The ID of the chat completion that was deleted. + deleted: + type: boolean + description: Whether the chat completion was deleted. + required: + - object + - id + - deleted + ChatCompletionFunctionCallOption: + type: object + description: > + Specifying a particular function via `{"name": "my_function"}` forces + the model to call that function. + properties: + name: + type: string + description: The name of the function to call. + required: + - name + ChatCompletionFunctions: + type: object + deprecated: true + properties: + description: + type: string + description: A description of what the function does, used by the model to + choose when and how to call the function. + name: + type: string + description: The name of the function to be called. Must be a-z, A-Z, 0-9, or + contain underscores and dashes, with a maximum length of 64. + parameters: + $ref: "#/components/schemas/FunctionParameters" + required: + - name + ChatCompletionList: + type: object + title: ChatCompletionList + description: | + An object representing a list of Chat Completions. + properties: + object: + type: string + enum: + - list + default: list + description: | + The type of this object. It is always set to "list". + x-stainless-const: true + data: + type: array + description: | + An array of chat completion objects. + items: + $ref: "#/components/schemas/CreateChatCompletionResponse" + first_id: + type: string + description: The identifier of the first chat completion in the data array. + last_id: + type: string + description: The identifier of the last chat completion in the data array. + has_more: + type: boolean + description: Indicates whether there are more Chat Completions available. + required: + - object + - data + - first_id + - last_id + - has_more + x-oaiMeta: + name: The chat completion list object + group: chat + example: > + { + "object": "list", + "data": [ + { + "object": "chat.completion", + "id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2", + "model": "gpt-4o-2024-08-06", + "created": 1738960610, + "request_id": "req_ded8ab984ec4bf840f37566c1011c417", + "tool_choice": null, + "usage": { + "total_tokens": 31, + "completion_tokens": 18, + "prompt_tokens": 13 + }, + "seed": 4944116822809979520, + "top_p": 1.0, + "temperature": 1.0, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "system_fingerprint": "fp_50cad350e4", + "input_user": null, + "service_tier": "default", + "tools": null, + "metadata": {}, + "choices": [ + { + "index": 0, + "message": { + "content": "Mind of circuits hum, \nLearning patterns in silence— \nFuture's quiet spark.", + "role": "assistant", + "tool_calls": null, + "function_call": null + }, + "finish_reason": "stop", + "logprobs": null + } + ], + "response_format": null + } + ], + "first_id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2", + "last_id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2", + "has_more": false + } + ChatCompletionMessageList: + type: object + title: ChatCompletionMessageList + description: | + An object representing a list of chat completion messages. + properties: + object: + type: string + enum: + - list + default: list + description: | + The type of this object. It is always set to "list". + x-stainless-const: true + data: + type: array + description: | + An array of chat completion message objects. + items: + allOf: + - $ref: "#/components/schemas/ChatCompletionResponseMessage" + - type: object + required: + - id + properties: + id: + type: string + description: The identifier of the chat message. + first_id: + type: string + description: The identifier of the first chat message in the data array. + last_id: + type: string + description: The identifier of the last chat message in the data array. + has_more: + type: boolean + description: Indicates whether there are more chat messages available. + required: + - object + - data + - first_id + - last_id + - has_more + x-oaiMeta: + name: The chat completion message list object + group: chat + example: | + { + "object": "list", + "data": [ + { + "id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0", + "role": "user", + "content": "write a haiku about ai", + "name": null, + "content_parts": null + } + ], + "first_id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0", + "last_id": "chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0", + "has_more": false + } + ChatCompletionMessageToolCall: + type: object + properties: + id: + type: string + description: The ID of the tool call. + type: + type: string + enum: + - function + description: The type of the tool. Currently, only `function` is supported. + x-stainless-const: true + function: + type: object + description: The function that the model called. + properties: + name: + type: string + description: The name of the function to call. + arguments: + type: string + description: The arguments to call the function with, as generated by the model + in JSON format. Note that the model does not always generate + valid JSON, and may hallucinate parameters not defined by your + function schema. Validate the arguments in your code before + calling your function. + required: + - name + - arguments + required: + - id + - type + - function + ChatCompletionMessageToolCallChunk: + type: object + properties: + index: + type: integer + id: + type: string + description: The ID of the tool call. + type: + type: string + enum: + - function + description: The type of the tool. Currently, only `function` is supported. + x-stainless-const: true + function: + type: object + properties: + name: + type: string + description: The name of the function to call. + arguments: + type: string + description: The arguments to call the function with, as generated by the model + in JSON format. Note that the model does not always generate + valid JSON, and may hallucinate parameters not defined by your + function schema. Validate the arguments in your code before + calling your function. + required: + - index + ChatCompletionMessageToolCalls: + type: array + description: The tool calls generated by the model, such as function calls. + items: + $ref: "#/components/schemas/ChatCompletionMessageToolCall" + ChatCompletionModalities: + type: array + nullable: true + description: > + Output types that you would like the model to generate for this request. + + Most models are capable of generating text, which is the default: + + + `["text"]` + + + The `gpt-4o-audio-preview` model can also be used to [generate + audio](/docs/guides/audio). To + + request that this model generate both text and audio responses, you can + + use: + + + `["text", "audio"]` + items: + type: string + enum: + - text + - audio + ChatCompletionNamedToolChoice: + type: object + description: Specifies a tool the model should use. Use to force the model to + call a specific function. + properties: + type: + type: string + enum: + - function + description: The type of the tool. Currently, only `function` is supported. + x-stainless-const: true + function: + type: object + properties: + name: + type: string + description: The name of the function to call. + required: + - name + required: + - type + - function + ChatCompletionRequestAssistantMessage: + type: object + title: Assistant message + description: | + Messages sent by the model in response to user messages. + properties: + content: + nullable: true + oneOf: + - type: string + description: The contents of the assistant message. + title: Text content + - type: array + description: An array of content parts with a defined type. Can be one or more + of type `text`, or exactly one of type `refusal`. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestAssistantMessageContentPart" + minItems: 1 + description: > + The contents of the assistant message. Required unless `tool_calls` + or `function_call` is specified. + refusal: + nullable: true + type: string + description: The refusal message by the assistant. + role: + type: string + enum: + - assistant + description: The role of the messages author, in this case `assistant`. + x-stainless-const: true + name: + type: string + description: An optional name for the participant. Provides the model + information to differentiate between participants of the same role. + audio: + type: object + nullable: true + description: | + Data about a previous audio response from the model. + [Learn more](/docs/guides/audio). + required: + - id + properties: + id: + type: string + description: | + Unique identifier for a previous audio response from the model. + tool_calls: + $ref: "#/components/schemas/ChatCompletionMessageToolCalls" + function_call: + type: object + deprecated: true + description: Deprecated and replaced by `tool_calls`. The name and arguments of + a function that should be called, as generated by the model. + nullable: true + properties: + arguments: + type: string + description: The arguments to call the function with, as generated by the model + in JSON format. Note that the model does not always generate + valid JSON, and may hallucinate parameters not defined by your + function schema. Validate the arguments in your code before + calling your function. + name: + type: string + description: The name of the function to call. + required: + - arguments + - name + required: + - role + ChatCompletionRequestAssistantMessageContentPart: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartRefusal" + ChatCompletionRequestDeveloperMessage: + type: object + title: Developer message + description: > + Developer-provided instructions that the model should follow, regardless + of + + messages sent by the user. With o1 models and newer, `developer` + messages + + replace the previous `system` messages. + properties: + content: + description: The contents of the developer message. + oneOf: + - type: string + description: The contents of the developer message. + title: Text content + - type: array + description: An array of content parts with a defined type. For developer + messages, only type `text` is supported. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + minItems: 1 + role: + type: string + enum: + - developer + description: The role of the messages author, in this case `developer`. + x-stainless-const: true + name: + type: string + description: An optional name for the participant. Provides the model + information to differentiate between participants of the same role. + required: + - content + - role + ChatCompletionRequestFunctionMessage: + type: object + title: Function message + deprecated: true + properties: + role: + type: string + enum: + - function + description: The role of the messages author, in this case `function`. + x-stainless-const: true + content: + nullable: true + type: string + description: The contents of the function message. + name: + type: string + description: The name of the function to call. + required: + - role + - content + - name + ChatCompletionRequestMessage: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestDeveloperMessage" + - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage" + - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" + - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" + - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" + - $ref: "#/components/schemas/ChatCompletionRequestFunctionMessage" + ChatCompletionRequestMessageContentPartAudio: + type: object + title: Audio content part + description: | + Learn about [audio inputs](/docs/guides/audio). + properties: + type: + type: string + enum: + - input_audio + description: The type of the content part. Always `input_audio`. + x-stainless-const: true + input_audio: + type: object + properties: + data: + type: string + description: Base64 encoded audio data. + format: + type: string + enum: + - wav + - mp3 + description: > + The format of the encoded audio data. Currently supports "wav" + and "mp3". + required: + - data + - format + required: + - type + - input_audio + ChatCompletionRequestMessageContentPartFile: + type: object + title: File content part + description: | + Learn about [file inputs](/docs/guides/text) for text generation. + properties: + type: + type: string + enum: + - file + description: The type of the content part. Always `file`. + x-stainless-const: true + file: + type: object + properties: + filename: + type: string + description: > + The name of the file, used when passing the file to the model as + a + + string. + file_data: + type: string + description: > + The base64 encoded file data, used when passing the file to the + model + + as a string. + file_id: + type: string + description: | + The ID of an uploaded file to use as input. + required: + - type + - file + ChatCompletionRequestMessageContentPartImage: + type: object + title: Image content part + description: | + Learn about [image inputs](/docs/guides/vision). + properties: + type: + type: string + enum: + - image_url + description: The type of the content part. + x-stainless-const: true + image_url: + type: object + properties: + url: + type: string + description: Either a URL of the image or the base64 encoded image data. + format: uri + detail: + type: string + description: Specifies the detail level of the image. Learn more in the [Vision + guide](/docs/guides/vision#low-or-high-fidelity-image-understanding). + enum: + - auto + - low + - high + default: auto + required: + - url + required: + - type + - image_url + ChatCompletionRequestMessageContentPartRefusal: + type: object + title: Refusal content part + properties: + type: + type: string + enum: + - refusal + description: The type of the content part. + x-stainless-const: true + refusal: + type: string + description: The refusal message generated by the model. + required: + - type + - refusal + ChatCompletionRequestMessageContentPartText: + type: object + title: Text content part + description: | + Learn about [text inputs](/docs/guides/text-generation). + properties: + type: + type: string + enum: + - text + description: The type of the content part. + x-stainless-const: true + text: + type: string + description: The text content. + required: + - type + - text + ChatCompletionRequestSystemMessage: + type: object + title: System message + description: > + Developer-provided instructions that the model should follow, regardless + of + + messages sent by the user. With o1 models and newer, use `developer` + messages + + for this purpose instead. + properties: + content: + description: The contents of the system message. + oneOf: + - type: string + description: The contents of the system message. + title: Text content + - type: array + description: An array of content parts with a defined type. For system messages, + only type `text` is supported. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestSystemMessageContentPart" + minItems: 1 + role: + type: string + enum: + - system + description: The role of the messages author, in this case `system`. + x-stainless-const: true + name: + type: string + description: An optional name for the participant. Provides the model + information to differentiate between participants of the same role. + required: + - content + - role + ChatCompletionRequestSystemMessageContentPart: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + ChatCompletionRequestToolMessage: + type: object + title: Tool message + properties: + role: + type: string + enum: + - tool + description: The role of the messages author, in this case `tool`. + x-stainless-const: true + content: + oneOf: + - type: string + description: The contents of the tool message. + title: Text content + - type: array + description: An array of content parts with a defined type. For tool messages, + only type `text` is supported. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestToolMessageContentPart" + minItems: 1 + description: The contents of the tool message. + tool_call_id: + type: string + description: Tool call that this message is responding to. + required: + - role + - content + - tool_call_id + ChatCompletionRequestToolMessageContentPart: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + ChatCompletionRequestUserMessage: + type: object + title: User message + description: | + Messages sent by an end user, containing prompts or additional context + information. + properties: + content: + description: | + The contents of the user message. + oneOf: + - type: string + description: The text contents of the message. + title: Text content + - type: array + description: An array of content parts with a defined type. Supported options + differ based on the [model](/docs/models) being used to generate + the response. Can contain text, image, or audio inputs. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestUserMessageContentPart" + minItems: 1 + role: + type: string + enum: + - user + description: The role of the messages author, in this case `user`. + x-stainless-const: true + name: + type: string + description: An optional name for the participant. Provides the model + information to differentiate between participants of the same role. + required: + - content + - role + ChatCompletionRequestUserMessageContentPart: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartImage" + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartAudio" + - $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartFile" + ChatCompletionResponseMessage: + type: object + description: A chat completion message generated by the model. + properties: + content: + type: string + description: The contents of the message. + nullable: true + refusal: + type: string + description: The refusal message generated by the model. + nullable: true + tool_calls: + $ref: "#/components/schemas/ChatCompletionMessageToolCalls" + annotations: + type: array + description: | + Annotations for the message, when applicable, as when using the + [web search tool](/docs/guides/tools-web-search?api-mode=chat). + items: + type: object + description: | + A URL citation when using web search. + required: + - type + - url_citation + properties: + type: + type: string + description: The type of the URL citation. Always `url_citation`. + enum: + - url_citation + x-stainless-const: true + url_citation: + type: object + description: A URL citation when using web search. + required: + - end_index + - start_index + - url + - title + properties: + end_index: + type: integer + description: The index of the last character of the URL citation in the message. + start_index: + type: integer + description: The index of the first character of the URL citation in the + message. + url: + type: string + description: The URL of the web resource. + title: + type: string + description: The title of the web resource. + role: + type: string + enum: + - assistant + description: The role of the author of this message. + x-stainless-const: true + function_call: + type: object + deprecated: true + description: Deprecated and replaced by `tool_calls`. The name and arguments of + a function that should be called, as generated by the model. + properties: + arguments: + type: string + description: The arguments to call the function with, as generated by the model + in JSON format. Note that the model does not always generate + valid JSON, and may hallucinate parameters not defined by your + function schema. Validate the arguments in your code before + calling your function. + name: + type: string + description: The name of the function to call. + required: + - name + - arguments + audio: + type: object + nullable: true + description: > + If the audio output modality is requested, this object contains data + + about the audio response from the model. [Learn + more](/docs/guides/audio). + required: + - id + - expires_at + - data + - transcript + properties: + id: + type: string + description: Unique identifier for this audio response. + expires_at: + type: integer + description: > + The Unix timestamp (in seconds) for when this audio response + will + + no longer be accessible on the server for use in multi-turn + + conversations. + data: + type: string + description: | + Base64 encoded audio bytes generated by the model, in the format + specified in the request. + transcript: + type: string + description: Transcript of the audio generated by the model. + required: + - role + - content + - refusal + ChatCompletionRole: + type: string + description: The role of the author of a message + enum: + - developer + - system + - user + - assistant + - tool + - function + ChatCompletionStreamOptions: + description: > + Options for streaming response. Only set this when you set `stream: + true`. + type: object + nullable: true + default: null + properties: + include_usage: + type: boolean + description: > + If set, an additional chunk will be streamed before the `data: + [DONE]` + + message. The `usage` field on this chunk shows the token usage + statistics + + for the entire request, and the `choices` field will always be an + empty + + array. + + + All other chunks will also include a `usage` field, but with a null + + value. **NOTE:** If the stream is interrupted, you may not receive + the + + final usage chunk which contains the total token usage for the + request. + ChatCompletionStreamResponseDelta: + type: object + description: A chat completion delta generated by streamed model responses. + properties: + content: + type: string + description: The contents of the chunk message. + nullable: true + function_call: + deprecated: true + type: object + description: Deprecated and replaced by `tool_calls`. The name and arguments of + a function that should be called, as generated by the model. + properties: + arguments: + type: string + description: The arguments to call the function with, as generated by the model + in JSON format. Note that the model does not always generate + valid JSON, and may hallucinate parameters not defined by your + function schema. Validate the arguments in your code before + calling your function. + name: + type: string + description: The name of the function to call. + tool_calls: + type: array + items: + $ref: "#/components/schemas/ChatCompletionMessageToolCallChunk" + role: + type: string + enum: + - developer + - system + - user + - assistant + - tool + description: The role of the author of this message. + refusal: + type: string + description: The refusal message generated by the model. + nullable: true + ChatCompletionTokenLogprob: + type: object + properties: + token: + description: The token. + type: string + logprob: + description: The log probability of this token, if it is within the top 20 most + likely tokens. Otherwise, the value `-9999.0` is used to signify + that the token is very unlikely. + type: number + bytes: + description: A list of integers representing the UTF-8 bytes representation of + the token. Useful in instances where characters are represented by + multiple tokens and their byte representations must be combined to + generate the correct text representation. Can be `null` if there is + no bytes representation for the token. + type: array + items: + type: integer + nullable: true + top_logprobs: + description: List of the most likely tokens and their log probability, at this + token position. In rare cases, there may be fewer than the number of + requested `top_logprobs` returned. + type: array + items: + type: object + properties: + token: + description: The token. + type: string + logprob: + description: The log probability of this token, if it is within the top 20 most + likely tokens. Otherwise, the value `-9999.0` is used to + signify that the token is very unlikely. + type: number + bytes: + description: A list of integers representing the UTF-8 bytes representation of + the token. Useful in instances where characters are + represented by multiple tokens and their byte representations + must be combined to generate the correct text representation. + Can be `null` if there is no bytes representation for the + token. + type: array + items: + type: integer + nullable: true + required: + - token + - logprob + - bytes + required: + - token + - logprob + - bytes + - top_logprobs + ChatCompletionTool: + type: object + properties: + type: + type: string + enum: + - function + description: The type of the tool. Currently, only `function` is supported. + x-stainless-const: true + function: + $ref: "#/components/schemas/FunctionObject" + required: + - type + - function + ChatCompletionToolChoiceOption: + description: > + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a + message. + + `auto` means the model can pick between generating a message or calling + one or more tools. + + `required` means the model must call one or more tools. + + Specifying a particular tool via `{"type": "function", "function": + {"name": "my_function"}}` forces the model to call that tool. + + + `none` is the default when no tools are present. `auto` is the default + if tools are present. + oneOf: + - type: string + description: > + `none` means the model will not call any tool and instead generates + a message. `auto` means the model can pick between generating a + message or calling one or more tools. `required` means the model + must call one or more tools. + enum: + - none + - auto + - required + - $ref: "#/components/schemas/ChatCompletionNamedToolChoice" + ChunkingStrategyRequestParam: + type: object + description: The chunking strategy used to chunk the file(s). If not set, will + use the `auto` strategy. + oneOf: + - $ref: "#/components/schemas/AutoChunkingStrategyRequestParam" + - $ref: "#/components/schemas/StaticChunkingStrategyRequestParam" + Click: + type: object + title: Click + description: | + A click action. + properties: + type: + type: string + enum: + - click + default: click + description: | + Specifies the event type. For a click action, this property is + always set to `click`. + x-stainless-const: true + button: + type: string + enum: + - left + - right + - wheel + - back + - forward + description: > + Indicates which mouse button was pressed during the click. One of + `left`, `right`, `wheel`, `back`, or `forward`. + x: + type: integer + description: | + The x-coordinate where the click occurred. + y: + type: integer + description: | + The y-coordinate where the click occurred. + required: + - type + - button + - x + - y + CodeInterpreterFileOutput: + type: object + title: Code interpreter file output + description: | + The output of a code interpreter tool call that is a file. + properties: + type: + type: string + enum: + - files + description: | + The type of the code interpreter file output. Always `files`. + x-stainless-const: true + files: + type: array + items: + type: object + properties: + mime_type: + type: string + description: | + The MIME type of the file. + file_id: + type: string + description: | + The ID of the file. + required: + - mime_type + - file_id + required: + - type + - files + CodeInterpreterTextOutput: + type: object + title: Code interpreter text output + description: | + The output of a code interpreter tool call that is text. + properties: + type: + type: string + enum: + - logs + description: | + The type of the code interpreter text output. Always `logs`. + x-stainless-const: true + logs: + type: string + description: | + The logs of the code interpreter tool call. + required: + - type + - logs + CodeInterpreterTool: + type: object + title: Code interpreter + description: | + A tool that runs Python code to help generate a response to a prompt. + properties: + type: + type: string + enum: + - code_interpreter + description: | + The type of the code interpreter tool. Always `code_interpreter`. + x-stainless-const: true + container: + description: > + The code interpreter container. Can be a container ID or an object + that + + specifies uploaded file IDs to make available to your code. + discriminator: + propertyName: type + oneOf: + - type: string + description: The container ID. + - $ref: "#/components/schemas/CodeInterpreterToolAuto" + required: + - type + - container + CodeInterpreterToolAuto: + type: object + title: CodeInterpreterContainerAuto + description: > + Configuration for a code interpreter container. Optionally specify the + IDs + + of the files to run the code on. + required: + - type + properties: + type: + type: string + enum: + - auto + description: Always `auto`. + x-stainless-const: true + file_ids: + type: array + items: + type: string + description: | + An optional list of uploaded files to make available to your code. + CodeInterpreterToolCall: + type: object + title: Code interpreter tool call + description: | + A tool call to run code. + properties: + id: + type: string + description: | + The unique ID of the code interpreter tool call. + type: + type: string + enum: + - code_interpreter_call + description: > + The type of the code interpreter tool call. Always + `code_interpreter_call`. + x-stainless-const: true + container_id: + type: string + description: | + The ID of the container used to run the code. + code: + type: string + description: | + The code to run. + status: + type: string + enum: + - in_progress + - interpreting + - completed + description: | + The status of the code interpreter tool call. + results: + type: array + items: + $ref: "#/components/schemas/CodeInterpreterToolOutput" + description: | + The results of the code interpreter tool call. + required: + - id + - type + - code + - status + - results + CodeInterpreterToolOutput: + title: Code interpreter tool output + description: | + The output of a code interpreter tool. + discriminator: + propertyName: type + oneOf: + - $ref: "#/components/schemas/CodeInterpreterTextOutput" + - $ref: "#/components/schemas/CodeInterpreterFileOutput" + ComparisonFilter: + type: object + additionalProperties: false + title: Comparison Filter + description: > + A filter used to compare a specified attribute key to a given value + using a defined comparison operation. + properties: + type: + type: string + default: eq + enum: + - eq + - ne + - gt + - gte + - lt + - lte + description: > + Specifies the comparison operator: `eq`, `ne`, `gt`, `gte`, `lt`, + `lte`. + + - `eq`: equals + + - `ne`: not equal + + - `gt`: greater than + + - `gte`: greater than or equal + + - `lt`: less than + + - `lte`: less than or equal + key: + type: string + description: The key to compare against the value. + value: + oneOf: + - type: string + - type: number + - type: boolean + description: The value to compare against the attribute key; supports string, + number, or boolean types. + required: + - type + - key + - value + x-oaiMeta: + name: ComparisonFilter + CompleteUploadRequest: + type: object + additionalProperties: false + properties: + part_ids: + type: array + description: | + The ordered list of Part IDs. + items: + type: string + md5: + description: > + The optional md5 checksum for the file contents to verify if the + bytes uploaded matches what you expect. + type: string + required: + - part_ids + CompletionUsage: + type: object + description: Usage statistics for the completion request. + properties: + completion_tokens: + type: integer + default: 0 + description: Number of tokens in the generated completion. + prompt_tokens: + type: integer + default: 0 + description: Number of tokens in the prompt. + total_tokens: + type: integer + default: 0 + description: Total number of tokens used in the request (prompt + completion). + completion_tokens_details: + type: object + description: Breakdown of tokens used in a completion. + properties: + accepted_prediction_tokens: + type: integer + default: 0 + description: | + When using Predicted Outputs, the number of tokens in the + prediction that appeared in the completion. + audio_tokens: + type: integer + default: 0 + description: Audio input tokens generated by the model. + reasoning_tokens: + type: integer + default: 0 + description: Tokens generated by the model for reasoning. + rejected_prediction_tokens: + type: integer + default: 0 + description: > + When using Predicted Outputs, the number of tokens in the + + prediction that did not appear in the completion. However, like + + reasoning tokens, these tokens are still counted in the total + + completion tokens for purposes of billing, output, and context + window + + limits. + prompt_tokens_details: + type: object + description: Breakdown of tokens used in the prompt. + properties: + audio_tokens: + type: integer + default: 0 + description: Audio input tokens present in the prompt. + cached_tokens: + type: integer + default: 0 + description: Cached tokens present in the prompt. + required: + - prompt_tokens + - completion_tokens + - total_tokens + CompoundFilter: + $recursiveAnchor: true + type: object + additionalProperties: false + title: Compound Filter + description: Combine multiple filters using `and` or `or`. + properties: + type: + type: string + description: "Type of operation: `and` or `or`." + enum: + - and + - or + filters: + type: array + description: Array of filters to combine. Items can be `ComparisonFilter` or + `CompoundFilter`. + items: + oneOf: + - $ref: "#/components/schemas/ComparisonFilter" + - $recursiveRef: "#" + required: + - type + - filters + x-oaiMeta: + name: CompoundFilter + ComputerAction: + oneOf: + - $ref: "#/components/schemas/Click" + - $ref: "#/components/schemas/DoubleClick" + - $ref: "#/components/schemas/Drag" + - $ref: "#/components/schemas/KeyPress" + - $ref: "#/components/schemas/Move" + - $ref: "#/components/schemas/Screenshot" + - $ref: "#/components/schemas/Scroll" + - $ref: "#/components/schemas/Type" + - $ref: "#/components/schemas/Wait" + ComputerScreenshotImage: + type: object + description: | + A computer screenshot image used with the computer use tool. + properties: + type: + type: string + enum: + - computer_screenshot + default: computer_screenshot + description: > + Specifies the event type. For a computer screenshot, this property + is + + always set to `computer_screenshot`. + x-stainless-const: true + image_url: + type: string + description: The URL of the screenshot image. + file_id: + type: string + description: The identifier of an uploaded file that contains the screenshot. + required: + - type + ComputerToolCall: + type: object + title: Computer tool call + description: > + A tool call to a computer use tool. See the + + [computer use guide](/docs/guides/tools-computer-use) for more + information. + properties: + type: + type: string + description: The type of the computer call. Always `computer_call`. + enum: + - computer_call + default: computer_call + id: + type: string + description: The unique ID of the computer call. + call_id: + type: string + description: | + An identifier used when responding to the tool call with output. + action: + $ref: "#/components/schemas/ComputerAction" + pending_safety_checks: + type: array + items: + $ref: "#/components/schemas/ComputerToolCallSafetyCheck" + description: | + The pending safety checks for the computer call. + status: + type: string + description: | + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + enum: + - in_progress + - completed + - incomplete + required: + - type + - id + - action + - call_id + - pending_safety_checks + - status + ComputerToolCallOutput: + type: object + title: Computer tool call output + description: | + The output of a computer tool call. + properties: + type: + type: string + description: > + The type of the computer tool call output. Always + `computer_call_output`. + enum: + - computer_call_output + default: computer_call_output + x-stainless-const: true + id: + type: string + description: | + The ID of the computer tool call output. + call_id: + type: string + description: | + The ID of the computer tool call that produced the output. + acknowledged_safety_checks: + type: array + description: > + The safety checks reported by the API that have been acknowledged by + the + + developer. + items: + $ref: "#/components/schemas/ComputerToolCallSafetyCheck" + output: + $ref: "#/components/schemas/ComputerScreenshotImage" + status: + type: string + description: > + The status of the message input. One of `in_progress`, `completed`, + or + + `incomplete`. Populated when input items are returned via API. + enum: + - in_progress + - completed + - incomplete + required: + - type + - call_id + - output + ComputerToolCallOutputResource: + allOf: + - $ref: "#/components/schemas/ComputerToolCallOutput" + - type: object + properties: + id: + type: string + description: | + The unique ID of the computer call tool output. + required: + - id + ComputerToolCallSafetyCheck: + type: object + description: | + A pending safety check for the computer call. + properties: + id: + type: string + description: The ID of the pending safety check. + code: + type: string + description: The type of the pending safety check. + message: + type: string + description: Details about the pending safety check. + required: + - id + - code + - message + ContainerFileListResource: + type: object + properties: + object: + type: string + enum: + - list + description: The type of object returned, must be 'list'. + data: + type: array + description: A list of container files. + items: + $ref: "#/components/schemas/ContainerFileResource" + first_id: + type: string + description: The ID of the first file in the list. + last_id: + type: string + description: The ID of the last file in the list. + has_more: + type: boolean + description: Whether there are more files available. + required: + - object + - data + - first_id + - last_id + - has_more + ContainerFileResource: + type: object + title: The container file object + properties: + id: + type: string + description: Unique identifier for the file. + object: + type: string + description: The type of this object (`container.file`). + container_id: + type: string + description: The container this file belongs to. + created_at: + type: integer + description: Unix timestamp (in seconds) when the file was created. + bytes: + type: integer + description: Size of the file in bytes. + path: + type: string + description: Path of the file in the container. + source: + type: string + description: Source of the file (e.g., `user`, `assistant`). + required: + - id + - object + - created_at + - bytes + - container_id + - path + - source + x-oaiMeta: + name: The container file object + example: > + { + "id": "cfile_682e0e8a43c88191a7978f477a09bdf5", + "object": "container.file", + "created_at": 1747848842, + "bytes": 880, + "container_id": "cntr_682e0e7318108198aa783fd921ff305e08e78805b9fdbb04", + "path": "/mnt/data/88e12fa445d32636f190a0b33daed6cb-tsconfig.json", + "source": "user" + } + ContainerListResource: + type: object + properties: + object: + type: string + enum: + - list + description: The type of object returned, must be 'list'. + data: + type: array + description: A list of containers. + items: + $ref: "#/components/schemas/ContainerResource" + first_id: + type: string + description: The ID of the first container in the list. + last_id: + type: string + description: The ID of the last container in the list. + has_more: + type: boolean + description: Whether there are more containers available. + required: + - object + - data + - first_id + - last_id + - has_more + ContainerResource: + type: object + title: The container object + properties: + id: + type: string + description: Unique identifier for the container. + object: + type: string + description: The type of this object. + name: + type: string + description: Name of the container. + created_at: + type: integer + description: Unix timestamp (in seconds) when the container was created. + status: + type: string + description: Status of the container (e.g., active, deleted). + expires_after: + type: object + description: > + The container will expire after this time period. + + The anchor is the reference point for the expiration. + + The minutes is the number of minutes after the anchor before the + container expires. + properties: + anchor: + type: string + description: The reference point for the expiration. + enum: + - last_active_at + minutes: + type: integer + description: The number of minutes after the anchor before the container + expires. + required: + - id + - object + - name + - created_at + - status + - id + - name + - created_at + - status + x-oaiMeta: + name: The container object + example: | + { + "id": "cntr_682dfebaacac8198bbfe9c2474fb6f4a085685cbe3cb5863", + "object": "container", + "created_at": 1747844794, + "status": "running", + "expires_after": { + "anchor": "last_active_at", + "minutes": 20 + }, + "last_active_at": 1747844794, + "name": "My Container" + } + Content: + description: | + Multi-modal input and output contents. + oneOf: + - title: Input content types + $ref: "#/components/schemas/InputContent" + - title: Output content types + $ref: "#/components/schemas/OutputContent" + Coordinate: + type: object + title: Coordinate + description: | + An x/y coordinate pair, e.g. `{ x: 100, y: 200 }`. + properties: + x: + type: integer + description: | + The x-coordinate. + y: + type: integer + description: | + The y-coordinate. + required: + - x + - y + CostsResult: + type: object + description: The aggregated costs details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.costs.result + x-stainless-const: true + amount: + type: object + description: The monetary value in its associated currency. + properties: + value: + type: number + description: The numeric value of the cost. + currency: + type: string + description: Lowercase ISO-4217 currency e.g. "usd" + line_item: + type: string + nullable: true + description: When `group_by=line_item`, this field provides the line item of the + grouped costs result. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped costs result. + required: + - object + x-oaiMeta: + name: Costs object + example: | + { + "object": "organization.costs.result", + "amount": { + "value": 0.06, + "currency": "usd" + }, + "line_item": "Image models", + "project_id": "proj_abc" + } + CreateAssistantRequest: + type: object + additionalProperties: false + properties: + model: + description: > + ID of the model to use. You can use the [List + models](/docs/api-reference/models/list) API to see all of your + available models, or see our [Model overview](/docs/models) for + descriptions of them. + example: gpt-4o + anyOf: + - type: string + - $ref: "#/components/schemas/AssistantSupportedModels" + x-oaiTypeLabel: string + name: + description: | + The name of the assistant. The maximum length is 256 characters. + type: string + nullable: true + maxLength: 256 + description: + description: > + The description of the assistant. The maximum length is 512 + characters. + type: string + nullable: true + maxLength: 512 + instructions: + description: > + The system instructions that the assistant uses. The maximum length + is 256,000 characters. + type: string + nullable: true + maxLength: 256000 + reasoning_effort: + $ref: "#/components/schemas/ReasoningEffort" + tools: + description: > + A list of tool enabled on the assistant. There can be a maximum of + 128 tools per assistant. Tools can be of types `code_interpreter`, + `file_search`, or `function`. + default: [] + type: array + maxItems: 128 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + tool_resources: + type: object + description: > + A set of resources that are used by the assistant's tools. The + resources are specific to the type of tool. For example, the + `code_interpreter` tool requires a list of file IDs, while the + `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The [vector store](/docs/api-reference/vector-stores/object) + attached to this assistant. There can be a maximum of 1 + vector store attached to the assistant. + maxItems: 1 + items: + type: string + vector_stores: + type: array + description: > + A helper to create a [vector + store](/docs/api-reference/vector-stores/object) with + file_ids and attach it to this assistant. There can be a + maximum of 1 vector store attached to the assistant. + maxItems: 1 + items: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs to add + to the vector store. There can be a maximum of 10000 + files in a vector store. + maxItems: 10000 + items: + type: string + chunking_strategy: + type: object + description: The chunking strategy used to chunk the file(s). If not set, will + use the `auto` strategy. + oneOf: + - type: object + title: Auto Chunking Strategy + description: The default strategy. This strategy currently uses a + `max_chunk_size_tokens` of `800` and + `chunk_overlap_tokens` of `400`. + additionalProperties: false + properties: + type: + type: string + description: Always `auto`. + enum: + - auto + x-stainless-const: true + required: + - type + - type: object + title: Static Chunking Strategy + additionalProperties: false + properties: + type: + type: string + description: Always `static`. + enum: + - static + x-stainless-const: true + static: + type: object + additionalProperties: false + properties: + max_chunk_size_tokens: + type: integer + minimum: 100 + maximum: 4096 + description: The maximum number of tokens in each chunk. The default value is + `800`. The minimum value is `100` and the + maximum value is `4096`. + chunk_overlap_tokens: + type: integer + description: > + The number of tokens that overlap between + chunks. The default value is `400`. + + + Note that the overlap must not exceed half + of `max_chunk_size_tokens`. + required: + - max_chunk_size_tokens + - chunk_overlap_tokens + required: + - type + - static + metadata: + $ref: "#/components/schemas/Metadata" + oneOf: + - required: + - vector_store_ids + - required: + - vector_stores + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + temperature: + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or temperature but not both. + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - model + CreateChatCompletionRequest: + allOf: + - $ref: "#/components/schemas/CreateModelResponseProperties" + - type: object + properties: + messages: + description: > + A list of messages comprising the conversation so far. Depending + on the + + [model](/docs/models) you use, different message types + (modalities) are + + supported, like [text](/docs/guides/text-generation), + + [images](/docs/guides/vision), and [audio](/docs/guides/audio). + type: array + minItems: 1 + items: + $ref: "#/components/schemas/ChatCompletionRequestMessage" + model: + description: > + Model ID used to generate the response, like `gpt-4o` or `o3`. + OpenAI + + offers a wide range of models with different capabilities, + performance + + characteristics, and price points. Refer to the [model + guide](/docs/models) + + to browse and compare available models. + $ref: "#/components/schemas/ModelIdsShared" + modalities: + $ref: "#/components/schemas/ResponseModalities" + reasoning_effort: + $ref: "#/components/schemas/ReasoningEffort" + max_completion_tokens: + description: > + An upper bound for the number of tokens that can be generated + for a completion, including visible output tokens and [reasoning + tokens](/docs/guides/reasoning). + type: integer + nullable: true + frequency_penalty: + type: number + default: 0 + minimum: -2 + maximum: 2 + nullable: true + description: > + Number between -2.0 and 2.0. Positive values penalize new tokens + based on + + their existing frequency in the text so far, decreasing the + model's + + likelihood to repeat the same line verbatim. + presence_penalty: + type: number + default: 0 + minimum: -2 + maximum: 2 + nullable: true + description: > + Number between -2.0 and 2.0. Positive values penalize new tokens + based on + + whether they appear in the text so far, increasing the model's + likelihood + + to talk about new topics. + web_search_options: + type: object + title: Web search + description: > + This tool searches the web for relevant results to use in a + response. + + Learn more about the [web search + tool](/docs/guides/tools-web-search?api-mode=chat). + properties: + user_location: + type: object + nullable: true + required: + - type + - approximate + description: | + Approximate location parameters for the search. + properties: + type: + type: string + description: > + The type of location approximation. Always `approximate`. + enum: + - approximate + x-stainless-const: true + approximate: + $ref: "#/components/schemas/WebSearchLocation" + search_context_size: + $ref: "#/components/schemas/WebSearchContextSize" + top_logprobs: + description: > + An integer between 0 and 20 specifying the number of most likely + tokens to + + return at each token position, each with an associated log + probability. + + `logprobs` must be set to `true` if this parameter is used. + type: integer + minimum: 0 + maximum: 20 + nullable: true + response_format: + description: > + An object specifying the format that the model must output. + + + Setting to `{ "type": "json_schema", "json_schema": {...} }` + enables + + Structured Outputs which ensures the model will match your + supplied JSON + + schema. Learn more in the [Structured Outputs + + guide](/docs/guides/structured-outputs). + + + Setting to `{ "type": "json_object" }` enables the older JSON + mode, which + + ensures the message the model generates is valid JSON. Using + `json_schema` + + is preferred for models that support it. + oneOf: + - $ref: "#/components/schemas/ResponseFormatText" + - $ref: "#/components/schemas/ResponseFormatJsonSchema" + - $ref: "#/components/schemas/ResponseFormatJsonObject" + audio: + type: object + nullable: true + description: > + Parameters for audio output. Required when audio output is + requested with + + `modalities: ["audio"]`. [Learn more](/docs/guides/audio). + required: + - voice + - format + properties: + voice: + $ref: "#/components/schemas/VoiceIdsShared" + description: > + The voice the model uses to respond. Supported voices are + + `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `nova`, + `onyx`, `sage`, and `shimmer`. + format: + type: string + enum: + - wav + - aac + - mp3 + - flac + - opus + - pcm16 + description: > + Specifies the output audio format. Must be one of `wav`, + `mp3`, `flac`, + + `opus`, or `pcm16`. + store: + type: boolean + default: false + nullable: true + description: > + Whether or not to store the output of this chat completion + request for + + use in our [model distillation](/docs/guides/distillation) or + + [evals](/docs/guides/evals) products. + stream: + description: | + If set to true, the model response data will be streamed to the client + as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). + See the [Streaming section below](/docs/api-reference/chat/streaming) + for more information, along with the [streaming responses](/docs/guides/streaming-responses) + guide for more information on how to handle the streaming events. + type: boolean + nullable: true + default: false + stop: + $ref: "#/components/schemas/StopConfiguration" + logit_bias: + type: object + x-oaiTypeLabel: map + default: null + nullable: true + additionalProperties: + type: integer + description: > + Modify the likelihood of specified tokens appearing in the + completion. + + + Accepts a JSON object that maps tokens (specified by their token + ID in the + + tokenizer) to an associated bias value from -100 to 100. + Mathematically, + + the bias is added to the logits generated by the model prior to + sampling. + + The exact effect will vary per model, but values between -1 and + 1 should + + decrease or increase likelihood of selection; values like -100 + or 100 + + should result in a ban or exclusive selection of the relevant + token. + logprobs: + description: > + Whether to return log probabilities of the output tokens or not. + If true, + + returns the log probabilities of each output token returned in + the + + `content` of `message`. + type: boolean + default: false + nullable: true + max_tokens: + description: > + The maximum number of [tokens](/tokenizer) that can be generated + in the + + chat completion. This value can be used to control + + [costs](https://openai.com/api/pricing/) for text generated via + API. + + + This value is now deprecated in favor of + `max_completion_tokens`, and is + + not compatible with [o-series models](/docs/guides/reasoning). + type: integer + nullable: true + deprecated: true + n: + type: integer + minimum: 1 + maximum: 128 + default: 1 + example: 1 + nullable: true + description: How many chat completion choices to generate for each input + message. Note that you will be charged based on the number of + generated tokens across all of the choices. Keep `n` as `1` to + minimize costs. + prediction: + nullable: true + description: > + Configuration for a [Predicted + Output](/docs/guides/predicted-outputs), + + which can greatly improve response times when large parts of the + model + + response are known ahead of time. This is most common when you + are + + regenerating a file with only minor changes to most of the + content. + oneOf: + - $ref: "#/components/schemas/PredictionContent" + seed: + type: integer + minimum: -9223372036854776000 + maximum: 9223372036854776000 + nullable: true + description: > + This feature is in Beta. + + If specified, our system will make a best effort to sample + deterministically, such that repeated requests with the same + `seed` and parameters should return the same result. + + Determinism is not guaranteed, and you should refer to the + `system_fingerprint` response parameter to monitor changes in + the backend. + x-oaiMeta: + beta: true + stream_options: + $ref: "#/components/schemas/ChatCompletionStreamOptions" + tools: + type: array + description: > + A list of tools the model may call. Currently, only functions + are supported as a tool. Use this to provide a list of functions + the model may generate JSON inputs for. A max of 128 functions + are supported. + items: + $ref: "#/components/schemas/ChatCompletionTool" + tool_choice: + $ref: "#/components/schemas/ChatCompletionToolChoiceOption" + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + function_call: + deprecated: true + description: > + Deprecated in favor of `tool_choice`. + + + Controls which (if any) function is called by the model. + + + `none` means the model will not call a function and instead + generates a + + message. + + + `auto` means the model can pick between generating a message or + calling a + + function. + + + Specifying a particular function via `{"name": "my_function"}` + forces the + + model to call that function. + + + `none` is the default when no functions are present. `auto` is + the default + + if functions are present. + oneOf: + - type: string + description: > + `none` means the model will not call a function and instead + generates a message. `auto` means the model can pick between + generating a message or calling a function. + enum: + - none + - auto + - $ref: "#/components/schemas/ChatCompletionFunctionCallOption" + functions: + deprecated: true + description: | + Deprecated in favor of `tools`. + + A list of functions the model may generate JSON inputs for. + type: array + minItems: 1 + maxItems: 128 + items: + $ref: "#/components/schemas/ChatCompletionFunctions" + required: + - model + - messages + CreateChatCompletionResponse: + type: object + description: Represents a chat completion response returned by model, based on + the provided input. + properties: + id: + type: string + description: A unique identifier for the chat completion. + choices: + type: array + description: A list of chat completion choices. Can be more than one if `n` is + greater than 1. + items: + type: object + required: + - finish_reason + - index + - message + - logprobs + properties: + finish_reason: + type: string + description: > + The reason the model stopped generating tokens. This will be + `stop` if the model hit a natural stop point or a provided + stop sequence, + + `length` if the maximum number of tokens specified in the + request was reached, + + `content_filter` if content was omitted due to a flag from our + content filters, + + `tool_calls` if the model called a tool, or `function_call` + (deprecated) if the model called a function. + enum: + - stop + - length + - tool_calls + - content_filter + - function_call + index: + type: integer + description: The index of the choice in the list of choices. + message: + $ref: "#/components/schemas/ChatCompletionResponseMessage" + logprobs: + description: Log probability information for the choice. + type: object + nullable: true + properties: + content: + description: A list of message content tokens with log probability information. + type: array + items: + $ref: "#/components/schemas/ChatCompletionTokenLogprob" + nullable: true + refusal: + description: A list of message refusal tokens with log probability information. + type: array + items: + $ref: "#/components/schemas/ChatCompletionTokenLogprob" + nullable: true + required: + - content + - refusal + created: + type: integer + description: The Unix timestamp (in seconds) of when the chat completion was + created. + model: + type: string + description: The model used for the chat completion. + service_tier: + $ref: "#/components/schemas/ServiceTier" + system_fingerprint: + type: string + description: > + This fingerprint represents the backend configuration that the model + runs with. + + + Can be used in conjunction with the `seed` request parameter to + understand when backend changes have been made that might impact + determinism. + object: + type: string + description: The object type, which is always `chat.completion`. + enum: + - chat.completion + x-stainless-const: true + usage: + $ref: "#/components/schemas/CompletionUsage" + required: + - choices + - created + - id + - model + - object + x-oaiMeta: + name: The chat completion object + group: chat + example: > + { + "id": "chatcmpl-B9MHDbslfkBeAs8l4bebGdFOJ6PeG", + "object": "chat.completion", + "created": 1741570283, + "model": "gpt-4o-2024-08-06", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": "The image shows a wooden boardwalk path running through a lush green field or meadow. The sky is bright blue with some scattered clouds, giving the scene a serene and peaceful atmosphere. Trees and shrubs are visible in the background.", + "refusal": null, + "annotations": [] + }, + "logprobs": null, + "finish_reason": "stop" + } + ], + "usage": { + "prompt_tokens": 1117, + "completion_tokens": 46, + "total_tokens": 1163, + "prompt_tokens_details": { + "cached_tokens": 0, + "audio_tokens": 0 + }, + "completion_tokens_details": { + "reasoning_tokens": 0, + "audio_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + }, + "service_tier": "default", + "system_fingerprint": "fp_fc9f1d7035" + } + CreateChatCompletionStreamResponse: + type: object + description: | + Represents a streamed chunk of a chat completion response returned + by the model, based on the provided input. + [Learn more](/docs/guides/streaming-responses). + properties: + id: + type: string + description: A unique identifier for the chat completion. Each chunk has the + same ID. + choices: + type: array + description: > + A list of chat completion choices. Can contain more than one + elements if `n` is greater than 1. Can also be empty for the + + last chunk if you set `stream_options: {"include_usage": true}`. + items: + type: object + required: + - delta + - finish_reason + - index + properties: + delta: + $ref: "#/components/schemas/ChatCompletionStreamResponseDelta" + logprobs: + description: Log probability information for the choice. + type: object + nullable: true + properties: + content: + description: A list of message content tokens with log probability information. + type: array + items: + $ref: "#/components/schemas/ChatCompletionTokenLogprob" + nullable: true + refusal: + description: A list of message refusal tokens with log probability information. + type: array + items: + $ref: "#/components/schemas/ChatCompletionTokenLogprob" + nullable: true + required: + - content + - refusal + finish_reason: + type: string + description: > + The reason the model stopped generating tokens. This will be + `stop` if the model hit a natural stop point or a provided + stop sequence, + + `length` if the maximum number of tokens specified in the + request was reached, + + `content_filter` if content was omitted due to a flag from our + content filters, + + `tool_calls` if the model called a tool, or `function_call` + (deprecated) if the model called a function. + enum: + - stop + - length + - tool_calls + - content_filter + - function_call + nullable: true + index: + type: integer + description: The index of the choice in the list of choices. + created: + type: integer + description: The Unix timestamp (in seconds) of when the chat completion was + created. Each chunk has the same timestamp. + model: + type: string + description: The model to generate the completion. + service_tier: + $ref: "#/components/schemas/ServiceTier" + system_fingerprint: + type: string + description: > + This fingerprint represents the backend configuration that the model + runs with. + + Can be used in conjunction with the `seed` request parameter to + understand when backend changes have been made that might impact + determinism. + object: + type: string + description: The object type, which is always `chat.completion.chunk`. + enum: + - chat.completion.chunk + x-stainless-const: true + usage: + $ref: "#/components/schemas/CompletionUsage" + nullable: true + description: > + An optional field that will only be present when you set + + `stream_options: {"include_usage": true}` in your request. When + present, it + + contains a null value **except for the last chunk** which contains + the + + token usage statistics for the entire request. + + + **NOTE:** If the stream is interrupted or cancelled, you may not + + receive the final usage chunk which contains the total token usage + for + + the request. + required: + - choices + - created + - id + - model + - object + x-oaiMeta: + name: The chat completion chunk object + group: chat + example: | + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]} + + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]} + + .... + + {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]} + CreateCompletionRequest: + type: object + properties: + model: + description: > + ID of the model to use. You can use the [List + models](/docs/api-reference/models/list) API to see all of your + available models, or see our [Model overview](/docs/models) for + descriptions of them. + anyOf: + - type: string + - type: string + enum: + - gpt-3.5-turbo-instruct + - davinci-002 + - babbage-002 + x-oaiTypeLabel: string + prompt: + description: > + The prompt(s) to generate completions for, encoded as a string, + array of strings, array of tokens, or array of token arrays. + + + Note that <|endoftext|> is the document separator that the model + sees during training, so if a prompt is not specified the model will + generate as if from the beginning of a new document. + default: <|endoftext|> + nullable: true + oneOf: + - type: string + default: "" + example: This is a test. + - type: array + items: + type: string + default: "" + example: This is a test. + - type: array + minItems: 1 + items: + type: integer + example: "[1212, 318, 257, 1332, 13]" + - type: array + minItems: 1 + items: + type: array + minItems: 1 + items: + type: integer + example: "[[1212, 318, 257, 1332, 13]]" + best_of: + type: integer + default: 1 + minimum: 0 + maximum: 20 + nullable: true + description: > + Generates `best_of` completions server-side and returns the "best" + (the one with the highest log probability per token). Results cannot + be streamed. + + + When used with `n`, `best_of` controls the number of candidate + completions and `n` specifies how many to return – `best_of` must be + greater than `n`. + + + **Note:** Because this parameter generates many completions, it can + quickly consume your token quota. Use carefully and ensure that you + have reasonable settings for `max_tokens` and `stop`. + echo: + type: boolean + default: false + nullable: true + description: | + Echo back the prompt in addition to the completion + frequency_penalty: + type: number + default: 0 + minimum: -2 + maximum: 2 + nullable: true + description: > + Number between -2.0 and 2.0. Positive values penalize new tokens + based on their existing frequency in the text so far, decreasing the + model's likelihood to repeat the same line verbatim. + + + [See more information about frequency and presence + penalties.](/docs/guides/text-generation) + logit_bias: + type: object + x-oaiTypeLabel: map + default: null + nullable: true + additionalProperties: + type: integer + description: > + Modify the likelihood of specified tokens appearing in the + completion. + + + Accepts a JSON object that maps tokens (specified by their token ID + in the GPT tokenizer) to an associated bias value from -100 to 100. + You can use this [tokenizer tool](/tokenizer?view=bpe) to convert + text to token IDs. Mathematically, the bias is added to the logits + generated by the model prior to sampling. The exact effect will vary + per model, but values between -1 and 1 should decrease or increase + likelihood of selection; values like -100 or 100 should result in a + ban or exclusive selection of the relevant token. + + + As an example, you can pass `{"50256": -100}` to prevent the + <|endoftext|> token from being generated. + logprobs: + type: integer + minimum: 0 + maximum: 5 + default: null + nullable: true + description: > + Include the log probabilities on the `logprobs` most likely output + tokens, as well the chosen tokens. For example, if `logprobs` is 5, + the API will return a list of the 5 most likely tokens. The API will + always return the `logprob` of the sampled token, so there may be up + to `logprobs+1` elements in the response. + + + The maximum value for `logprobs` is 5. + max_tokens: + type: integer + minimum: 0 + default: 16 + example: 16 + nullable: true + description: | + The maximum number of [tokens](/tokenizer) that can be generated in the completion. + + The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. + n: + type: integer + minimum: 1 + maximum: 128 + default: 1 + example: 1 + nullable: true + description: > + How many completions to generate for each prompt. + + + **Note:** Because this parameter generates many completions, it can + quickly consume your token quota. Use carefully and ensure that you + have reasonable settings for `max_tokens` and `stop`. + presence_penalty: + type: number + default: 0 + minimum: -2 + maximum: 2 + nullable: true + description: > + Number between -2.0 and 2.0. Positive values penalize new tokens + based on whether they appear in the text so far, increasing the + model's likelihood to talk about new topics. + + + [See more information about frequency and presence + penalties.](/docs/guides/text-generation) + seed: + type: integer + format: int64 + nullable: true + description: > + If specified, our system will make a best effort to sample + deterministically, such that repeated requests with the same `seed` + and parameters should return the same result. + + + Determinism is not guaranteed, and you should refer to the + `system_fingerprint` response parameter to monitor changes in the + backend. + stop: + $ref: "#/components/schemas/StopConfiguration" + stream: + description: | + Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). + type: boolean + nullable: true + default: false + stream_options: + $ref: "#/components/schemas/ChatCompletionStreamOptions" + suffix: + description: | + The suffix that comes after a completion of inserted text. + + This parameter is only supported for `gpt-3.5-turbo-instruct`. + default: null + nullable: true + type: string + example: test. + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + + + We generally recommend altering this or `top_p` but not both. + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or `temperature` but not both. + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + required: + - model + - prompt + CreateCompletionResponse: + type: object + description: > + Represents a completion response from the API. Note: both the streamed + and non-streamed response objects share the same shape (unlike the chat + endpoint). + properties: + id: + type: string + description: A unique identifier for the completion. + choices: + type: array + description: The list of completion choices the model generated for the input + prompt. + items: + type: object + required: + - finish_reason + - index + - logprobs + - text + properties: + finish_reason: + type: string + description: > + The reason the model stopped generating tokens. This will be + `stop` if the model hit a natural stop point or a provided + stop sequence, + + `length` if the maximum number of tokens specified in the + request was reached, + + or `content_filter` if content was omitted due to a flag from + our content filters. + enum: + - stop + - length + - content_filter + index: + type: integer + logprobs: + type: object + nullable: true + properties: + text_offset: + type: array + items: + type: integer + token_logprobs: + type: array + items: + type: number + tokens: + type: array + items: + type: string + top_logprobs: + type: array + items: + type: object + additionalProperties: + type: number + text: + type: string + created: + type: integer + description: The Unix timestamp (in seconds) of when the completion was created. + model: + type: string + description: The model used for completion. + system_fingerprint: + type: string + description: > + This fingerprint represents the backend configuration that the model + runs with. + + + Can be used in conjunction with the `seed` request parameter to + understand when backend changes have been made that might impact + determinism. + object: + type: string + description: The object type, which is always "text_completion" + enum: + - text_completion + x-stainless-const: true + usage: + $ref: "#/components/schemas/CompletionUsage" + required: + - id + - object + - created + - model + - choices + x-oaiMeta: + name: The completion object + legacy: true + example: | + { + "id": "cmpl-uqkvlQyYK7bGYrRHQ0eXlWi7", + "object": "text_completion", + "created": 1589478378, + "model": "gpt-4-turbo", + "choices": [ + { + "text": "\n\nThis is indeed a test", + "index": 0, + "logprobs": null, + "finish_reason": "length" + } + ], + "usage": { + "prompt_tokens": 5, + "completion_tokens": 7, + "total_tokens": 12 + } + } + CreateContainerBody: + type: object + properties: + name: + type: string + description: Name of the container to create. + file_ids: + type: array + description: IDs of files to copy to the container. + items: + type: string + expires_after: + type: object + description: Container expiration time in seconds relative to the 'anchor' time. + properties: + anchor: + type: string + enum: + - last_active_at + description: Time anchor for the expiration time. Currently only + 'last_active_at' is supported. + minutes: + type: integer + required: + - anchor + - minutes + required: + - name + CreateContainerFileBody: + type: object + properties: + file_id: + type: string + description: Name of the file to create. + file: + description: | + The File object (not file name) to be uploaded. + type: string + format: binary + required: [] + CreateEmbeddingRequest: + type: object + additionalProperties: false + properties: + input: + description: | + Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for all embedding models), cannot be an empty string, and any array must be 2048 dimensions or less. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. In addition to the per-input token limit, all embedding models enforce a maximum of 300,000 tokens summed across all inputs in a single request. + example: The quick brown fox jumped over the lazy dog + oneOf: + - type: string + title: string + description: The string that will be turned into an embedding. + default: "" + example: This is a test. + - type: array + title: array + description: The array of strings that will be turned into an embedding. + minItems: 1 + maxItems: 2048 + items: + type: string + default: "" + example: "['This is a test.']" + - type: array + title: array + description: The array of integers that will be turned into an embedding. + minItems: 1 + maxItems: 2048 + items: + type: integer + example: "[1212, 318, 257, 1332, 13]" + - type: array + title: array + description: The array of arrays containing integers that will be turned into an + embedding. + minItems: 1 + maxItems: 2048 + items: + type: array + minItems: 1 + items: + type: integer + example: "[[1212, 318, 257, 1332, 13]]" + model: + description: > + ID of the model to use. You can use the [List + models](/docs/api-reference/models/list) API to see all of your + available models, or see our [Model overview](/docs/models) for + descriptions of them. + example: text-embedding-3-small + anyOf: + - type: string + - type: string + enum: + - text-embedding-ada-002 + - text-embedding-3-small + - text-embedding-3-large + x-oaiTypeLabel: string + encoding_format: + description: The format to return the embeddings in. Can be either `float` or + [`base64`](https://pypi.org/project/pybase64/). + example: float + default: float + type: string + enum: + - float + - base64 + dimensions: + description: > + The number of dimensions the resulting output embeddings should + have. Only supported in `text-embedding-3` and later models. + type: integer + minimum: 1 + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + required: + - model + - input + CreateEmbeddingResponse: + type: object + properties: + data: + type: array + description: The list of embeddings generated by the model. + items: + $ref: "#/components/schemas/Embedding" + model: + type: string + description: The name of the model used to generate the embedding. + object: + type: string + description: The object type, which is always "list". + enum: + - list + x-stainless-const: true + usage: + type: object + description: The usage information for the request. + properties: + prompt_tokens: + type: integer + description: The number of tokens used by the prompt. + total_tokens: + type: integer + description: The total number of tokens used by the request. + required: + - prompt_tokens + - total_tokens + required: + - object + - model + - data + - usage + CreateEvalCompletionsRunDataSource: + type: object + title: CompletionsRunDataSource + description: > + A CompletionsRunDataSource object describing a model sampling + configuration. + properties: + type: + type: string + enum: + - completions + default: completions + description: The type of run data source. Always `completions`. + input_messages: + description: Used when sampling from a model. Dictates the structure of the + messages passed into the model. Can either be a reference to a + prebuilt trajectory (ie, `item.input_trajectory`), or a template + with variable references to the `item` namespace. + oneOf: + - type: object + title: TemplateInputMessages + properties: + type: + type: string + enum: + - template + description: The type of input messages. Always `template`. + template: + type: array + description: A list of chat messages forming the prompt or context. May include + variable references to the `item` namespace, ie + {{item.name}}. + items: + oneOf: + - $ref: "#/components/schemas/EasyInputMessage" + - $ref: "#/components/schemas/EvalItem" + required: + - type + - template + - type: object + title: ItemReferenceInputMessages + properties: + type: + type: string + enum: + - item_reference + description: The type of input messages. Always `item_reference`. + item_reference: + type: string + description: A reference to a variable in the `item` namespace. Ie, + "item.input_trajectory" + required: + - type + - item_reference + sampling_params: + type: object + properties: + temperature: + type: number + description: A higher temperature increases randomness in the outputs. + default: 1 + max_completion_tokens: + type: integer + description: The maximum number of tokens in the generated output. + top_p: + type: number + description: An alternative to temperature for nucleus sampling; 1.0 includes + all tokens. + default: 1 + seed: + type: integer + description: A seed value to initialize the randomness, during sampling. + default: 42 + response_format: + description: > + An object specifying the format that the model must output. + + + Setting to `{ "type": "json_schema", "json_schema": {...} }` + enables + + Structured Outputs which ensures the model will match your + supplied JSON + + schema. Learn more in the [Structured Outputs + + guide](/docs/guides/structured-outputs). + + + Setting to `{ "type": "json_object" }` enables the older JSON + mode, which + + ensures the message the model generates is valid JSON. Using + `json_schema` + + is preferred for models that support it. + oneOf: + - $ref: "#/components/schemas/ResponseFormatText" + - $ref: "#/components/schemas/ResponseFormatJsonSchema" + - $ref: "#/components/schemas/ResponseFormatJsonObject" + tools: + type: array + description: > + A list of tools the model may call. Currently, only functions + are supported as a tool. Use this to provide a list of functions + the model may generate JSON inputs for. A max of 128 functions + are supported. + items: + $ref: "#/components/schemas/ChatCompletionTool" + model: + type: string + description: The name of the model to use for generating completions (e.g. + "o3-mini"). + source: + description: Determines what populates the `item` namespace in this run's data + source. + oneOf: + - $ref: "#/components/schemas/EvalJsonlFileContentSource" + - $ref: "#/components/schemas/EvalJsonlFileIdSource" + - $ref: "#/components/schemas/EvalStoredCompletionsSource" + required: + - type + - source + x-oaiMeta: + name: The completions data source object used to configure an individual run + group: eval runs + example: | + { + "name": "gpt-4o-mini-2024-07-18", + "data_source": { + "type": "completions", + "input_messages": { + "type": "item_reference", + "item_reference": "item.input" + }, + "model": "gpt-4o-mini-2024-07-18", + "source": { + "type": "stored_completions", + "model": "gpt-4o-mini-2024-07-18" + } + } + } + CreateEvalCustomDataSourceConfig: + type: object + title: CustomDataSourceConfig + description: > + A CustomDataSourceConfig object that defines the schema for the data + source used for the evaluation runs. + + This schema is used to define the shape of the data that will be: + + - Used to define your testing criteria and + + - What data is required when creating a run + properties: + type: + type: string + enum: + - custom + default: custom + description: The type of data source. Always `custom`. + x-stainless-const: true + item_schema: + type: object + description: The json schema for each row in the data source. + additionalProperties: true + example: | + { + "type": "object", + "properties": { + "name": {"type": "string"}, + "age": {"type": "integer"} + }, + "required": ["name", "age"] + } + include_sample_schema: + type: boolean + default: false + description: Whether the eval should expect you to populate the sample namespace + (ie, by generating responses off of your data source) + required: + - item_schema + - type + x-oaiMeta: + name: The eval file data source config object + group: evals + example: | + { + "type": "custom", + "item_schema": { + "type": "object", + "properties": { + "name": {"type": "string"}, + "age": {"type": "integer"} + }, + "required": ["name", "age"] + }, + "include_sample_schema": true + } + CreateEvalItem: + title: CreateEvalItem + description: A chat message that makes up the prompt or context. May include + variable references to the `item` namespace, ie {{item.name}}. + type: object + oneOf: + - type: object + title: SimpleInputMessage + properties: + role: + type: string + description: The role of the message (e.g. "system", "assistant", "user"). + content: + type: string + description: The content of the message. + required: + - role + - content + - $ref: "#/components/schemas/EvalItem" + x-oaiMeta: + name: The chat message object used to configure an individual run + CreateEvalJsonlRunDataSource: + type: object + title: JsonlRunDataSource + description: > + A JsonlRunDataSource object with that specifies a JSONL file that + matches the eval + properties: + type: + type: string + enum: + - jsonl + default: jsonl + description: The type of data source. Always `jsonl`. + x-stainless-const: true + source: + description: Determines what populates the `item` namespace in the data source. + oneOf: + - $ref: "#/components/schemas/EvalJsonlFileContentSource" + - $ref: "#/components/schemas/EvalJsonlFileIdSource" + required: + - type + - source + x-oaiMeta: + name: The file data source object for the eval run configuration + group: evals + example: | + { + "type": "jsonl", + "source": { + "type": "file_id", + "id": "file-9GYS6xbkWgWhmE7VoLUWFg" + } + } + CreateEvalLabelModelGrader: + type: object + title: LabelModelGrader + description: > + A LabelModelGrader object which uses a model to assign labels to each + item + + in the evaluation. + properties: + type: + description: The object type, which is always `label_model`. + type: string + enum: + - label_model + x-stainless-const: true + name: + type: string + description: The name of the grader. + model: + type: string + description: The model to use for the evaluation. Must support structured outputs. + input: + type: array + description: A list of chat messages forming the prompt or context. May include + variable references to the `item` namespace, ie {{item.name}}. + items: + $ref: "#/components/schemas/CreateEvalItem" + labels: + type: array + items: + type: string + description: The labels to classify to each item in the evaluation. + passing_labels: + type: array + items: + type: string + description: The labels that indicate a passing result. Must be a subset of + labels. + required: + - type + - model + - input + - passing_labels + - labels + - name + x-oaiMeta: + name: The eval label model grader object + group: evals + example: > + { + "type": "label_model", + "model": "gpt-4o-2024-08-06", + "input": [ + { + "role": "system", + "content": "Classify the sentiment of the following statement as one of 'positive', 'neutral', or 'negative'" + }, + { + "role": "user", + "content": "Statement: {{item.response}}" + } + ], + "passing_labels": ["positive"], + "labels": ["positive", "neutral", "negative"], + "name": "Sentiment label grader" + } + CreateEvalLogsDataSourceConfig: + type: object + title: LogsDataSourceConfig + description: > + A data source config which specifies the metadata property of your logs + query. + + This is usually metadata like `usecase=chatbot` or `prompt-version=v2`, + etc. + properties: + type: + type: string + enum: + - logs + default: logs + description: The type of data source. Always `logs`. + x-stainless-const: true + metadata: + type: object + description: Metadata filters for the logs data source. + additionalProperties: true + example: | + { + "use_case": "customer_support_agent" + } + required: + - type + x-oaiMeta: + name: The logs data source object for evals + group: evals + example: | + { + "type": "logs", + "metadata": { + "use_case": "customer_support_agent" + } + } + CreateEvalRequest: + type: object + title: CreateEvalRequest + properties: + name: + type: string + description: The name of the evaluation. + metadata: + $ref: "#/components/schemas/Metadata" + data_source_config: + type: object + description: The configuration for the data source used for the evaluation runs. + Dictates the schema of the data used in the evaluation. + oneOf: + - $ref: "#/components/schemas/CreateEvalCustomDataSourceConfig" + - $ref: "#/components/schemas/CreateEvalLogsDataSourceConfig" + - $ref: "#/components/schemas/CreateEvalStoredCompletionsDataSourceConfig" + testing_criteria: + type: array + description: A list of graders for all eval runs in this group. Graders can + reference variables in the data source using double curly braces + notation, like `{{item.variable_name}}`. To reference the model's + output, use the `sample` namespace (ie, `{{sample.output_text}}`). + items: + oneOf: + - $ref: "#/components/schemas/CreateEvalLabelModelGrader" + - $ref: "#/components/schemas/EvalGraderStringCheck" + - $ref: "#/components/schemas/EvalGraderTextSimilarity" + - $ref: "#/components/schemas/EvalGraderPython" + - $ref: "#/components/schemas/EvalGraderScoreModel" + required: + - data_source_config + - testing_criteria + CreateEvalResponsesRunDataSource: + type: object + title: ResponsesRunDataSource + description: > + A ResponsesRunDataSource object describing a model sampling + configuration. + properties: + type: + type: string + enum: + - responses + default: responses + description: The type of run data source. Always `responses`. + input_messages: + description: Used when sampling from a model. Dictates the structure of the + messages passed into the model. Can either be a reference to a + prebuilt trajectory (ie, `item.input_trajectory`), or a template + with variable references to the `item` namespace. + oneOf: + - type: object + title: InputMessagesTemplate + properties: + type: + type: string + enum: + - template + description: The type of input messages. Always `template`. + template: + type: array + description: A list of chat messages forming the prompt or context. May include + variable references to the `item` namespace, ie + {{item.name}}. + items: + oneOf: + - type: object + title: ChatMessage + properties: + role: + type: string + description: The role of the message (e.g. "system", "assistant", "user"). + content: + type: string + description: The content of the message. + required: + - role + - content + - $ref: "#/components/schemas/EvalItem" + required: + - type + - template + - type: object + title: InputMessagesItemReference + properties: + type: + type: string + enum: + - item_reference + description: The type of input messages. Always `item_reference`. + item_reference: + type: string + description: A reference to a variable in the `item` namespace. Ie, "item.name" + required: + - type + - item_reference + sampling_params: + type: object + properties: + temperature: + type: number + description: A higher temperature increases randomness in the outputs. + default: 1 + max_completion_tokens: + type: integer + description: The maximum number of tokens in the generated output. + top_p: + type: number + description: An alternative to temperature for nucleus sampling; 1.0 includes + all tokens. + default: 1 + seed: + type: integer + description: A seed value to initialize the randomness, during sampling. + default: 42 + tools: + type: array + description: > + An array of tools the model may call while generating a + response. You + + can specify which tool to use by setting the `tool_choice` + parameter. + + + The two categories of tools you can provide the model are: + + + - **Built-in tools**: Tools that are provided by OpenAI that + extend the + model's capabilities, like [web search](/docs/guides/tools-web-search) + or [file search](/docs/guides/tools-file-search). Learn more about + [built-in tools](/docs/guides/tools). + - **Function calls (custom tools)**: Functions that are defined + by you, + enabling the model to call your own code. Learn more about + [function calling](/docs/guides/function-calling). + items: + $ref: "#/components/schemas/Tool" + text: + type: object + description: > + Configuration options for a text response from the model. Can be + plain + + text or structured JSON data. Learn more: + + - [Text inputs and outputs](/docs/guides/text) + + - [Structured Outputs](/docs/guides/structured-outputs) + properties: + format: + $ref: "#/components/schemas/TextResponseFormatConfiguration" + model: + type: string + description: The name of the model to use for generating completions (e.g. + "o3-mini"). + source: + description: Determines what populates the `item` namespace in this run's data + source. + oneOf: + - $ref: "#/components/schemas/EvalJsonlFileContentSource" + - $ref: "#/components/schemas/EvalJsonlFileIdSource" + - $ref: "#/components/schemas/EvalResponsesSource" + required: + - type + - source + x-oaiMeta: + name: The completions data source object used to configure an individual run + group: eval runs + example: | + { + "name": "gpt-4o-mini-2024-07-18", + "data_source": { + "type": "responses", + "input_messages": { + "type": "item_reference", + "item_reference": "item.input" + }, + "model": "gpt-4o-mini-2024-07-18", + "source": { + "type": "responses", + "model": "gpt-4o-mini-2024-07-18" + } + } + } + CreateEvalRunRequest: + type: object + title: CreateEvalRunRequest + properties: + name: + type: string + description: The name of the run. + metadata: + $ref: "#/components/schemas/Metadata" + data_source: + type: object + description: Details about the run's data source. + oneOf: + - $ref: "#/components/schemas/CreateEvalJsonlRunDataSource" + - $ref: "#/components/schemas/CreateEvalCompletionsRunDataSource" + - $ref: "#/components/schemas/CreateEvalResponsesRunDataSource" + required: + - data_source + CreateEvalStoredCompletionsDataSourceConfig: + type: object + title: StoredCompletionsDataSourceConfig + description: | + Deprecated in favor of LogsDataSourceConfig. + properties: + type: + type: string + enum: + - stored_completions + default: stored_completions + description: The type of data source. Always `stored_completions`. + x-stainless-const: true + metadata: + type: object + description: Metadata filters for the stored completions data source. + additionalProperties: true + example: | + { + "use_case": "customer_support_agent" + } + required: + - type + deprecated: true + x-oaiMeta: + name: The stored completions data source object for evals + group: evals + example: | + { + "type": "stored_completions", + "metadata": { + "use_case": "customer_support_agent" + } + } + CreateFileRequest: + type: object + additionalProperties: false + properties: + file: + description: | + The File object (not file name) to be uploaded. + type: string + format: binary + purpose: + description: > + The intended purpose of the uploaded file. One of: - `assistants`: + Used in the Assistants API - `batch`: Used in the Batch API - + `fine-tune`: Used for fine-tuning - `vision`: Images used for vision + fine-tuning - `user_data`: Flexible file type for any purpose - + `evals`: Used for eval data sets + type: string + enum: + - assistants + - batch + - fine-tune + - vision + - user_data + - evals + required: + - file + - purpose + CreateFineTuningCheckpointPermissionRequest: + type: object + additionalProperties: false + properties: + project_ids: + type: array + description: The project identifiers to grant access to. + items: + type: string + required: + - project_ids + CreateFineTuningJobRequest: + type: object + properties: + model: + description: > + The name of the model to fine-tune. You can select one of the + + [supported + models](/docs/guides/fine-tuning#which-models-can-be-fine-tuned). + example: gpt-4o-mini + anyOf: + - type: string + - type: string + enum: + - babbage-002 + - davinci-002 + - gpt-3.5-turbo + - gpt-4o-mini + x-oaiTypeLabel: string + training_file: + description: > + The ID of an uploaded file that contains training data. + + + See [upload file](/docs/api-reference/files/create) for how to + upload a file. + + + Your dataset must be formatted as a JSONL file. Additionally, you + must upload your file with the purpose `fine-tune`. + + + The contents of the file should differ depending on if the model + uses the [chat](/docs/api-reference/fine-tuning/chat-input), + [completions](/docs/api-reference/fine-tuning/completions-input) + format, or if the fine-tuning method uses the + [preference](/docs/api-reference/fine-tuning/preference-input) + format. + + + See the [fine-tuning guide](/docs/guides/model-optimization) for + more details. + type: string + example: file-abc123 + hyperparameters: + type: object + description: > + The hyperparameters used for the fine-tuning job. + + This value is now deprecated in favor of `method`, and should be + passed in under the `method` parameter. + properties: + batch_size: + description: > + Number of examples in each batch. A larger batch size means that + model parameters + + are updated less frequently, but with lower variance. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + maximum: 256 + default: auto + learning_rate_multiplier: + description: > + Scaling factor for the learning rate. A smaller learning rate + may be useful to avoid + + overfitting. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: number + minimum: 0 + exclusiveMinimum: true + default: auto + n_epochs: + description: > + The number of epochs to train the model for. An epoch refers to + one full cycle + + through the training dataset. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + maximum: 50 + default: auto + deprecated: true + suffix: + description: > + A string of up to 64 characters that will be added to your + fine-tuned model name. + + + For example, a `suffix` of "custom-model-name" would produce a model + name like `ft:gpt-4o-mini:openai:custom-model-name:7p4lURel`. + type: string + minLength: 1 + maxLength: 64 + default: null + nullable: true + validation_file: + description: > + The ID of an uploaded file that contains validation data. + + + If you provide this file, the data is used to generate validation + + metrics periodically during fine-tuning. These metrics can be viewed + in + + the fine-tuning results file. + + The same data should not be present in both train and validation + files. + + + Your dataset must be formatted as a JSONL file. You must upload your + file with the purpose `fine-tune`. + + + See the [fine-tuning guide](/docs/guides/model-optimization) for + more details. + type: string + nullable: true + example: file-abc123 + integrations: + type: array + description: A list of integrations to enable for your fine-tuning job. + nullable: true + items: + type: object + required: + - type + - wandb + properties: + type: + description: > + The type of integration to enable. Currently, only "wandb" + (Weights and Biases) is supported. + oneOf: + - type: string + enum: + - wandb + x-stainless-const: true + wandb: + type: object + description: > + The settings for your integration with Weights and Biases. + This payload specifies the project that + + metrics will be sent to. Optionally, you can set an explicit + display name for your run, add tags + + to your run, and set a default entity (team, username, etc) to + be associated with your run. + required: + - project + properties: + project: + description: > + The name of the project that the new run will be created + under. + type: string + example: my-wandb-project + name: + description: > + A display name to set for the run. If not set, we will use + the Job ID as the name. + nullable: true + type: string + entity: + description: > + The entity to use for the run. This allows you to set the + team or username of the WandB user that you would + + like associated with the run. If not set, the default + entity for the registered WandB API key is used. + nullable: true + type: string + tags: + description: > + A list of tags to be attached to the newly created run. + These tags are passed through directly to WandB. Some + + default tags are generated by OpenAI: "openai/finetune", + "openai/{base-model}", "openai/{ftjob-abcdef}". + type: array + items: + type: string + example: custom-tag + seed: + description: > + The seed controls the reproducibility of the job. Passing in the + same seed and job parameters should produce the same results, but + may differ in rare cases. + + If a seed is not specified, one will be generated for you. + type: integer + nullable: true + minimum: 0 + maximum: 2147483647 + example: 42 + method: + $ref: "#/components/schemas/FineTuneMethod" + metadata: + $ref: "#/components/schemas/Metadata" + required: + - model + - training_file + CreateImageEditRequest: + type: object + properties: + image: + anyOf: + - type: string + format: binary + - type: array + maxItems: 16 + items: + type: string + format: binary + description: > + The image(s) to edit. Must be a supported image file or an array of + images. + + + For `gpt-image-1`, each image should be a `png`, `webp`, or `jpg` + file less + + than 50MB. You can provide up to 16 images. + + + For `dall-e-2`, you can only provide one image, and it should be a + square + + `png` file less than 4MB. + prompt: + description: A text description of the desired image(s). The maximum length is + 1000 characters for `dall-e-2`, and 32000 characters for + `gpt-image-1`. + type: string + example: A cute baby sea otter wearing a beret + mask: + description: An additional image whose fully transparent areas (e.g. where alpha + is zero) indicate where `image` should be edited. If there are + multiple images provided, the mask will be applied on the first + image. Must be a valid PNG file, less than 4MB, and have the same + dimensions as `image`. + type: string + format: binary + background: + type: string + enum: + - transparent + - opaque + - auto + default: auto + example: transparent + nullable: true + description: > + Allows to set transparency for the background of the generated + image(s). + + This parameter is only supported for `gpt-image-1`. Must be one of + + `transparent`, `opaque` or `auto` (default value). When `auto` is + used, the + + model will automatically determine the best background for the + image. + + + If `transparent`, the output format needs to support transparency, + so it + + should be set to either `png` (default value) or `webp`. + model: + anyOf: + - type: string + - type: string + enum: + - dall-e-2 + - gpt-image-1 + x-stainless-const: true + x-oaiTypeLabel: string + default: dall-e-2 + example: gpt-image-1 + nullable: true + description: The model to use for image generation. Only `dall-e-2` and + `gpt-image-1` are supported. Defaults to `dall-e-2` unless a + parameter specific to `gpt-image-1` is used. + n: + type: integer + minimum: 1 + maximum: 10 + default: 1 + example: 1 + nullable: true + description: The number of images to generate. Must be between 1 and 10. + size: + type: string + enum: + - 256x256 + - 512x512 + - 1024x1024 + - 1536x1024 + - 1024x1536 + - auto + default: 1024x1024 + example: 1024x1024 + nullable: true + description: The size of the generated images. Must be one of `1024x1024`, + `1536x1024` (landscape), `1024x1536` (portrait), or `auto` (default + value) for `gpt-image-1`, and one of `256x256`, `512x512`, or + `1024x1024` for `dall-e-2`. + response_format: + type: string + enum: + - url + - b64_json + default: url + example: url + nullable: true + description: The format in which the generated images are returned. Must be one + of `url` or `b64_json`. URLs are only valid for 60 minutes after the + image has been generated. This parameter is only supported for + `dall-e-2`, as `gpt-image-1` will always return base64-encoded + images. + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + quality: + type: string + enum: + - standard + - low + - medium + - high + - auto + default: auto + example: high + nullable: true + description: > + The quality of the image that will be generated. `high`, `medium` + and `low` are only supported for `gpt-image-1`. `dall-e-2` only + supports `standard` quality. Defaults to `auto`. + required: + - prompt + - image + CreateImageRequest: + type: object + properties: + prompt: + description: A text description of the desired image(s). The maximum length is + 32000 characters for `gpt-image-1`, 1000 characters for `dall-e-2` + and 4000 characters for `dall-e-3`. + type: string + example: A cute baby sea otter + model: + anyOf: + - type: string + - type: string + enum: + - dall-e-2 + - dall-e-3 + - gpt-image-1 + x-oaiTypeLabel: string + default: dall-e-2 + example: gpt-image-1 + nullable: true + description: The model to use for image generation. One of `dall-e-2`, + `dall-e-3`, or `gpt-image-1`. Defaults to `dall-e-2` unless a + parameter specific to `gpt-image-1` is used. + n: + type: integer + minimum: 1 + maximum: 10 + default: 1 + example: 1 + nullable: true + description: The number of images to generate. Must be between 1 and 10. For + `dall-e-3`, only `n=1` is supported. + quality: + type: string + enum: + - standard + - hd + - low + - medium + - high + - auto + default: auto + example: medium + nullable: true + description: > + The quality of the image that will be generated. + + + - `auto` (default value) will automatically select the best quality + for the given model. + + - `high`, `medium` and `low` are supported for `gpt-image-1`. + + - `hd` and `standard` are supported for `dall-e-3`. + + - `standard` is the only option for `dall-e-2`. + response_format: + type: string + enum: + - url + - b64_json + default: url + example: url + nullable: true + description: The format in which generated images with `dall-e-2` and `dall-e-3` + are returned. Must be one of `url` or `b64_json`. URLs are only + valid for 60 minutes after the image has been generated. This + parameter isn't supported for `gpt-image-1` which will always return + base64-encoded images. + output_format: + type: string + enum: + - png + - jpeg + - webp + default: png + example: png + nullable: true + description: The format in which the generated images are returned. This + parameter is only supported for `gpt-image-1`. Must be one of `png`, + `jpeg`, or `webp`. + output_compression: + type: integer + default: 100 + example: 100 + nullable: true + description: The compression level (0-100%) for the generated images. This + parameter is only supported for `gpt-image-1` with the `webp` or + `jpeg` output formats, and defaults to 100. + size: + type: string + enum: + - auto + - 1024x1024 + - 1536x1024 + - 1024x1536 + - 256x256 + - 512x512 + - 1792x1024 + - 1024x1792 + default: auto + example: 1024x1024 + nullable: true + description: The size of the generated images. Must be one of `1024x1024`, + `1536x1024` (landscape), `1024x1536` (portrait), or `auto` (default + value) for `gpt-image-1`, one of `256x256`, `512x512`, or + `1024x1024` for `dall-e-2`, and one of `1024x1024`, `1792x1024`, or + `1024x1792` for `dall-e-3`. + moderation: + type: string + enum: + - low + - auto + default: auto + example: low + nullable: true + description: Control the content-moderation level for images generated by + `gpt-image-1`. Must be either `low` for less restrictive filtering + or `auto` (default value). + background: + type: string + enum: + - transparent + - opaque + - auto + default: auto + example: transparent + nullable: true + description: > + Allows to set transparency for the background of the generated + image(s). + + This parameter is only supported for `gpt-image-1`. Must be one of + + `transparent`, `opaque` or `auto` (default value). When `auto` is + used, the + + model will automatically determine the best background for the + image. + + + If `transparent`, the output format needs to support transparency, + so it + + should be set to either `png` (default value) or `webp`. + style: + type: string + enum: + - vivid + - natural + default: vivid + example: vivid + nullable: true + description: The style of the generated images. This parameter is only supported + for `dall-e-3`. Must be one of `vivid` or `natural`. Vivid causes + the model to lean towards generating hyper-real and dramatic images. + Natural causes the model to produce more natural, less hyper-real + looking images. + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + required: + - prompt + CreateImageVariationRequest: + type: object + properties: + image: + description: The image to use as the basis for the variation(s). Must be a valid + PNG file, less than 4MB, and square. + type: string + format: binary + model: + anyOf: + - type: string + - type: string + enum: + - dall-e-2 + x-stainless-const: true + x-oaiTypeLabel: string + default: dall-e-2 + example: dall-e-2 + nullable: true + description: The model to use for image generation. Only `dall-e-2` is supported + at this time. + n: + type: integer + minimum: 1 + maximum: 10 + default: 1 + example: 1 + nullable: true + description: The number of images to generate. Must be between 1 and 10. + response_format: + type: string + enum: + - url + - b64_json + default: url + example: url + nullable: true + description: The format in which the generated images are returned. Must be one + of `url` or `b64_json`. URLs are only valid for 60 minutes after the + image has been generated. + size: + type: string + enum: + - 256x256 + - 512x512 + - 1024x1024 + default: 1024x1024 + example: 1024x1024 + nullable: true + description: The size of the generated images. Must be one of `256x256`, + `512x512`, or `1024x1024`. + user: + type: string + example: user-1234 + description: > + A unique identifier representing your end-user, which can help + OpenAI to monitor and detect abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + required: + - image + CreateMessageRequest: + type: object + additionalProperties: false + required: + - role + - content + properties: + role: + type: string + enum: + - user + - assistant + description: > + The role of the entity that is creating the message. Allowed values + include: + + - `user`: Indicates the message is sent by an actual user and should + be used in most cases to represent user-generated messages. + + - `assistant`: Indicates the message is generated by the assistant. + Use this value to insert messages from the assistant into the + conversation. + content: + oneOf: + - type: string + description: The text contents of the message. + title: Text content + - type: array + description: An array of content parts with a defined type, each can be of type + `text` or images can be passed with `image_url` or `image_file`. + Image types are only supported on [Vision-compatible + models](/docs/models). + title: Array of content parts + items: + oneOf: + - $ref: "#/components/schemas/MessageContentImageFileObject" + - $ref: "#/components/schemas/MessageContentImageUrlObject" + - $ref: "#/components/schemas/MessageRequestContentTextObject" + minItems: 1 + attachments: + type: array + items: + type: object + properties: + file_id: + type: string + description: The ID of the file to attach to the message. + tools: + description: The tools to add this file to. + type: array + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearchTypeOnly" + description: A list of files attached to the message, and the tools they should + be added to. + required: + - file_id + - tools + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + CreateModelResponseProperties: + allOf: + - $ref: "#/components/schemas/ModelResponseProperties" + CreateModerationRequest: + type: object + properties: + input: + description: > + Input (or inputs) to classify. Can be a single string, an array of + strings, or + + an array of multi-modal input objects similar to other models. + oneOf: + - type: string + description: A string of text to classify for moderation. + default: "" + example: I want to kill them. + - type: array + description: An array of strings to classify for moderation. + items: + type: string + default: "" + example: I want to kill them. + - type: array + description: An array of multi-modal inputs to the moderation model. + items: + oneOf: + - type: object + description: An object describing an image to classify. + properties: + type: + description: Always `image_url`. + type: string + enum: + - image_url + x-stainless-const: true + image_url: + type: object + description: Contains either an image URL or a data URL for a base64 encoded + image. + properties: + url: + type: string + description: Either a URL of the image or the base64 encoded image data. + format: uri + example: https://example.com/image.jpg + required: + - url + required: + - type + - image_url + - type: object + description: An object describing text to classify. + properties: + type: + description: Always `text`. + type: string + enum: + - text + x-stainless-const: true + text: + description: A string of text to classify. + type: string + example: I want to kill them + required: + - type + - text + model: + description: | + The content moderation model you would like to use. Learn more in + [the moderation guide](/docs/guides/moderation), and learn about + available models [here](/docs/models#moderation). + nullable: false + default: omni-moderation-latest + example: omni-moderation-2024-09-26 + anyOf: + - type: string + - type: string + enum: + - omni-moderation-latest + - omni-moderation-2024-09-26 + - text-moderation-latest + - text-moderation-stable + x-oaiTypeLabel: string + required: + - input + CreateModerationResponse: + type: object + description: Represents if a given text input is potentially harmful. + properties: + id: + type: string + description: The unique identifier for the moderation request. + model: + type: string + description: The model used to generate the moderation results. + results: + type: array + description: A list of moderation objects. + items: + type: object + properties: + flagged: + type: boolean + description: Whether any of the below categories are flagged. + categories: + type: object + description: A list of the categories, and whether they are flagged or not. + properties: + hate: + type: boolean + description: Content that expresses, incites, or promotes hate based on race, + gender, ethnicity, religion, nationality, sexual + orientation, disability status, or caste. Hateful content + aimed at non-protected groups (e.g., chess players) is + harassment. + hate/threatening: + type: boolean + description: Hateful content that also includes violence or serious harm towards + the targeted group based on race, gender, ethnicity, + religion, nationality, sexual orientation, disability + status, or caste. + harassment: + type: boolean + description: Content that expresses, incites, or promotes harassing language + towards any target. + harassment/threatening: + type: boolean + description: Harassment content that also includes violence or serious harm + towards any target. + illicit: + type: boolean + nullable: true + description: Content that includes instructions or advice that facilitate the + planning or execution of wrongdoing, or that gives advice + or instruction on how to commit illicit acts. For example, + "how to shoplift" would fit this category. + illicit/violent: + type: boolean + nullable: true + description: Content that includes instructions or advice that facilitate the + planning or execution of wrongdoing that also includes + violence, or that gives advice or instruction on the + procurement of any weapon. + self-harm: + type: boolean + description: Content that promotes, encourages, or depicts acts of self-harm, + such as suicide, cutting, and eating disorders. + self-harm/intent: + type: boolean + description: Content where the speaker expresses that they are engaging or + intend to engage in acts of self-harm, such as suicide, + cutting, and eating disorders. + self-harm/instructions: + type: boolean + description: Content that encourages performing acts of self-harm, such as + suicide, cutting, and eating disorders, or that gives + instructions or advice on how to commit such acts. + sexual: + type: boolean + description: Content meant to arouse sexual excitement, such as the description + of sexual activity, or that promotes sexual services + (excluding sex education and wellness). + sexual/minors: + type: boolean + description: Sexual content that includes an individual who is under 18 years + old. + violence: + type: boolean + description: Content that depicts death, violence, or physical injury. + violence/graphic: + type: boolean + description: Content that depicts death, violence, or physical injury in graphic + detail. + required: + - hate + - hate/threatening + - harassment + - harassment/threatening + - illicit + - illicit/violent + - self-harm + - self-harm/intent + - self-harm/instructions + - sexual + - sexual/minors + - violence + - violence/graphic + category_scores: + type: object + description: A list of the categories along with their scores as predicted by + model. + properties: + hate: + type: number + description: The score for the category 'hate'. + hate/threatening: + type: number + description: The score for the category 'hate/threatening'. + harassment: + type: number + description: The score for the category 'harassment'. + harassment/threatening: + type: number + description: The score for the category 'harassment/threatening'. + illicit: + type: number + description: The score for the category 'illicit'. + illicit/violent: + type: number + description: The score for the category 'illicit/violent'. + self-harm: + type: number + description: The score for the category 'self-harm'. + self-harm/intent: + type: number + description: The score for the category 'self-harm/intent'. + self-harm/instructions: + type: number + description: The score for the category 'self-harm/instructions'. + sexual: + type: number + description: The score for the category 'sexual'. + sexual/minors: + type: number + description: The score for the category 'sexual/minors'. + violence: + type: number + description: The score for the category 'violence'. + violence/graphic: + type: number + description: The score for the category 'violence/graphic'. + required: + - hate + - hate/threatening + - harassment + - harassment/threatening + - illicit + - illicit/violent + - self-harm + - self-harm/intent + - self-harm/instructions + - sexual + - sexual/minors + - violence + - violence/graphic + category_applied_input_types: + type: object + description: A list of the categories along with the input type(s) that the + score applies to. + properties: + hate: + type: array + description: The applied input type(s) for the category 'hate'. + items: + type: string + enum: + - text + x-stainless-const: true + hate/threatening: + type: array + description: The applied input type(s) for the category 'hate/threatening'. + items: + type: string + enum: + - text + x-stainless-const: true + harassment: + type: array + description: The applied input type(s) for the category 'harassment'. + items: + type: string + enum: + - text + x-stainless-const: true + harassment/threatening: + type: array + description: The applied input type(s) for the category + 'harassment/threatening'. + items: + type: string + enum: + - text + x-stainless-const: true + illicit: + type: array + description: The applied input type(s) for the category 'illicit'. + items: + type: string + enum: + - text + x-stainless-const: true + illicit/violent: + type: array + description: The applied input type(s) for the category 'illicit/violent'. + items: + type: string + enum: + - text + x-stainless-const: true + self-harm: + type: array + description: The applied input type(s) for the category 'self-harm'. + items: + type: string + enum: + - text + - image + self-harm/intent: + type: array + description: The applied input type(s) for the category 'self-harm/intent'. + items: + type: string + enum: + - text + - image + self-harm/instructions: + type: array + description: The applied input type(s) for the category + 'self-harm/instructions'. + items: + type: string + enum: + - text + - image + sexual: + type: array + description: The applied input type(s) for the category 'sexual'. + items: + type: string + enum: + - text + - image + sexual/minors: + type: array + description: The applied input type(s) for the category 'sexual/minors'. + items: + type: string + enum: + - text + x-stainless-const: true + violence: + type: array + description: The applied input type(s) for the category 'violence'. + items: + type: string + enum: + - text + - image + violence/graphic: + type: array + description: The applied input type(s) for the category 'violence/graphic'. + items: + type: string + enum: + - text + - image + required: + - hate + - hate/threatening + - harassment + - harassment/threatening + - illicit + - illicit/violent + - self-harm + - self-harm/intent + - self-harm/instructions + - sexual + - sexual/minors + - violence + - violence/graphic + required: + - flagged + - categories + - category_scores + - category_applied_input_types + required: + - id + - model + - results + x-oaiMeta: + name: The moderation object + example: | + { + "id": "modr-0d9740456c391e43c445bf0f010940c7", + "model": "omni-moderation-latest", + "results": [ + { + "flagged": true, + "categories": { + "harassment": true, + "harassment/threatening": true, + "sexual": false, + "hate": false, + "hate/threatening": false, + "illicit": false, + "illicit/violent": false, + "self-harm/intent": false, + "self-harm/instructions": false, + "self-harm": false, + "sexual/minors": false, + "violence": true, + "violence/graphic": true + }, + "category_scores": { + "harassment": 0.8189693396524255, + "harassment/threatening": 0.804985420696006, + "sexual": 1.573112165348997e-6, + "hate": 0.007562942636942845, + "hate/threatening": 0.004208854591835476, + "illicit": 0.030535955153511665, + "illicit/violent": 0.008925306722380033, + "self-harm/intent": 0.00023023930975076432, + "self-harm/instructions": 0.0002293869201073356, + "self-harm": 0.012598046106750154, + "sexual/minors": 2.212566909570261e-8, + "violence": 0.9999992735124786, + "violence/graphic": 0.843064871157054 + }, + "category_applied_input_types": { + "harassment": [ + "text" + ], + "harassment/threatening": [ + "text" + ], + "sexual": [ + "text", + "image" + ], + "hate": [ + "text" + ], + "hate/threatening": [ + "text" + ], + "illicit": [ + "text" + ], + "illicit/violent": [ + "text" + ], + "self-harm/intent": [ + "text", + "image" + ], + "self-harm/instructions": [ + "text", + "image" + ], + "self-harm": [ + "text", + "image" + ], + "sexual/minors": [ + "text" + ], + "violence": [ + "text", + "image" + ], + "violence/graphic": [ + "text", + "image" + ] + } + } + ] + } + CreateResponse: + allOf: + - $ref: "#/components/schemas/CreateModelResponseProperties" + - $ref: "#/components/schemas/ResponseProperties" + - type: object + properties: + input: + description: > + Text, image, or file inputs to the model, used to generate a + response. + + + Learn more: + + - [Text inputs and outputs](/docs/guides/text) + + - [Image inputs](/docs/guides/images) + + - [File inputs](/docs/guides/pdf-files) + + - [Conversation state](/docs/guides/conversation-state) + + - [Function calling](/docs/guides/function-calling) + oneOf: + - type: string + title: Text input + description: > + A text input to the model, equivalent to a text input with + the + + `user` role. + - type: array + title: Input item list + description: | + A list of one or many input items to the model, containing + different content types. + items: + $ref: "#/components/schemas/InputItem" + include: + type: array + description: > + Specify additional output data to include in the model response. + Currently + + supported values are: + + - `file_search_call.results`: Include the search results of + the file search tool call. + - `message.input_image.image_url`: Include image urls from the + input message. + + - `computer_call_output.output.image_url`: Include image urls + from the computer call output. + + - `reasoning.encrypted_content`: Includes an encrypted version + of reasoning + tokens in reasoning item outputs. This enables reasoning items to be used in + multi-turn conversations when using the Responses API statelessly (like + when the `store` parameter is set to `false`, or when an organization is + enrolled in the zero data retention program). + - `code_interpreter_call.outputs`: Includes the outputs of + python code execution + in code interpreter tool call items. + items: + $ref: "#/components/schemas/Includable" + nullable: true + parallel_tool_calls: + type: boolean + description: | + Whether to allow the model to run tool calls in parallel. + default: true + nullable: true + store: + type: boolean + description: > + Whether to store the generated model response for later + retrieval via + + API. + default: true + nullable: true + stream: + description: | + If set to true, the model response data will be streamed to the client + as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). + See the [Streaming section below](/docs/api-reference/responses-streaming) + for more information. + type: boolean + nullable: true + default: false + required: + - model + - input + CreateRunRequest: + type: object + additionalProperties: false + properties: + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) to use to + execute this run. + type: string + model: + description: The ID of the [Model](/docs/api-reference/models) to be used to + execute this run. If a value is provided here, it will override the + model associated with the assistant. If not, the model associated + with the assistant will be used. + example: gpt-4o + anyOf: + - type: string + - $ref: "#/components/schemas/AssistantSupportedModels" + x-oaiTypeLabel: string + nullable: true + reasoning_effort: + $ref: "#/components/schemas/ReasoningEffort" + instructions: + description: Overrides the + [instructions](/docs/api-reference/assistants/createAssistant) of + the assistant. This is useful for modifying the behavior on a + per-run basis. + type: string + nullable: true + additional_instructions: + description: Appends additional instructions at the end of the instructions for + the run. This is useful for modifying the behavior on a per-run + basis without overriding other instructions. + type: string + nullable: true + additional_messages: + description: Adds additional messages to the thread before creating the run. + type: array + items: + $ref: "#/components/schemas/CreateMessageRequest" + nullable: true + tools: + description: Override the tools the assistant can use for this run. This is + useful for modifying the behavior on a per-run basis. + nullable: true + type: array + maxItems: 20 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + metadata: + $ref: "#/components/schemas/Metadata" + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or temperature but not both. + stream: + type: boolean + nullable: true + description: > + If `true`, returns a stream of events that happen during the Run as + server-sent events, terminating when the Run enters a terminal state + with a `data: [DONE]` message. + max_prompt_tokens: + type: integer + nullable: true + description: > + The maximum number of prompt tokens that may be used over the course + of the run. The run will make a best effort to use only the number + of prompt tokens specified, across multiple turns of the run. If the + run exceeds the number of prompt tokens specified, the run will end + with status `incomplete`. See `incomplete_details` for more info. + minimum: 256 + max_completion_tokens: + type: integer + nullable: true + description: > + The maximum number of completion tokens that may be used over the + course of the run. The run will make a best effort to use only the + number of completion tokens specified, across multiple turns of the + run. If the run exceeds the number of completion tokens specified, + the run will end with status `incomplete`. See `incomplete_details` + for more info. + minimum: 256 + truncation_strategy: + allOf: + - $ref: "#/components/schemas/TruncationObject" + - nullable: true + tool_choice: + allOf: + - $ref: "#/components/schemas/AssistantsApiToolChoiceOption" + - nullable: true + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - assistant_id + CreateSpeechRequest: + type: object + additionalProperties: false + properties: + model: + description: > + One of the available [TTS models](/docs/models#tts): `tts-1`, + `tts-1-hd` or `gpt-4o-mini-tts`. + anyOf: + - type: string + - type: string + enum: + - tts-1 + - tts-1-hd + - gpt-4o-mini-tts + x-oaiTypeLabel: string + input: + type: string + description: The text to generate audio for. The maximum length is 4096 + characters. + maxLength: 4096 + instructions: + type: string + description: Control the voice of your generated audio with additional + instructions. Does not work with `tts-1` or `tts-1-hd`. + maxLength: 4096 + voice: + description: The voice to use when generating the audio. Supported voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, + `sage`, `shimmer`, and `verse`. Previews of the voices are available + in the [Text to speech + guide](/docs/guides/text-to-speech#voice-options). + $ref: "#/components/schemas/VoiceIdsShared" + response_format: + description: The format to audio in. Supported formats are `mp3`, `opus`, `aac`, + `flac`, `wav`, and `pcm`. + default: mp3 + type: string + enum: + - mp3 + - opus + - aac + - flac + - wav + - pcm + speed: + description: The speed of the generated audio. Select a value from `0.25` to + `4.0`. `1.0` is the default. Does not work with `gpt-4o-mini-tts`. + type: number + default: 1 + minimum: 0.25 + maximum: 4 + required: + - model + - input + - voice + CreateThreadAndRunRequest: + type: object + additionalProperties: false + properties: + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) to use to + execute this run. + type: string + thread: + $ref: "#/components/schemas/CreateThreadRequest" + model: + description: The ID of the [Model](/docs/api-reference/models) to be used to + execute this run. If a value is provided here, it will override the + model associated with the assistant. If not, the model associated + with the assistant will be used. + example: gpt-4o + anyOf: + - type: string + - type: string + enum: + - gpt-4.1 + - gpt-4.1-mini + - gpt-4.1-nano + - gpt-4.1-2025-04-14 + - gpt-4.1-mini-2025-04-14 + - gpt-4.1-nano-2025-04-14 + - gpt-4o + - gpt-4o-2024-11-20 + - gpt-4o-2024-08-06 + - gpt-4o-2024-05-13 + - gpt-4o-mini + - gpt-4o-mini-2024-07-18 + - gpt-4.5-preview + - gpt-4.5-preview-2025-02-27 + - gpt-4-turbo + - gpt-4-turbo-2024-04-09 + - gpt-4-0125-preview + - gpt-4-turbo-preview + - gpt-4-1106-preview + - gpt-4-vision-preview + - gpt-4 + - gpt-4-0314 + - gpt-4-0613 + - gpt-4-32k + - gpt-4-32k-0314 + - gpt-4-32k-0613 + - gpt-3.5-turbo + - gpt-3.5-turbo-16k + - gpt-3.5-turbo-0613 + - gpt-3.5-turbo-1106 + - gpt-3.5-turbo-0125 + - gpt-3.5-turbo-16k-0613 + x-oaiTypeLabel: string + nullable: true + instructions: + description: Override the default system message of the assistant. This is + useful for modifying the behavior on a per-run basis. + type: string + nullable: true + tools: + description: Override the tools the assistant can use for this run. This is + useful for modifying the behavior on a per-run basis. + nullable: true + type: array + maxItems: 20 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + tool_resources: + type: object + description: > + A set of resources that are used by the assistant's tools. The + resources are specific to the type of tool. For example, the + `code_interpreter` tool requires a list of file IDs, while the + `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The ID of the [vector + store](/docs/api-reference/vector-stores/object) attached to + this assistant. There can be a maximum of 1 vector store + attached to the assistant. + maxItems: 1 + items: + type: string + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or temperature but not both. + stream: + type: boolean + nullable: true + description: > + If `true`, returns a stream of events that happen during the Run as + server-sent events, terminating when the Run enters a terminal state + with a `data: [DONE]` message. + max_prompt_tokens: + type: integer + nullable: true + description: > + The maximum number of prompt tokens that may be used over the course + of the run. The run will make a best effort to use only the number + of prompt tokens specified, across multiple turns of the run. If the + run exceeds the number of prompt tokens specified, the run will end + with status `incomplete`. See `incomplete_details` for more info. + minimum: 256 + max_completion_tokens: + type: integer + nullable: true + description: > + The maximum number of completion tokens that may be used over the + course of the run. The run will make a best effort to use only the + number of completion tokens specified, across multiple turns of the + run. If the run exceeds the number of completion tokens specified, + the run will end with status `incomplete`. See `incomplete_details` + for more info. + minimum: 256 + truncation_strategy: + allOf: + - $ref: "#/components/schemas/TruncationObject" + - nullable: true + tool_choice: + allOf: + - $ref: "#/components/schemas/AssistantsApiToolChoiceOption" + - nullable: true + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - assistant_id + CreateThreadRequest: + type: object + description: | + Options to create a new thread. If no thread is provided when running a + request, an empty thread will be created. + additionalProperties: false + properties: + messages: + description: A list of [messages](/docs/api-reference/messages) to start the + thread with. + type: array + items: + $ref: "#/components/schemas/CreateMessageRequest" + tool_resources: + type: object + description: > + A set of resources that are made available to the assistant's tools + in this thread. The resources are specific to the type of tool. For + example, the `code_interpreter` tool requires a list of file IDs, + while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The [vector store](/docs/api-reference/vector-stores/object) + attached to this thread. There can be a maximum of 1 vector + store attached to the thread. + maxItems: 1 + items: + type: string + vector_stores: + type: array + description: > + A helper to create a [vector + store](/docs/api-reference/vector-stores/object) with + file_ids and attach it to this thread. There can be a + maximum of 1 vector store attached to the thread. + maxItems: 1 + items: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs to add + to the vector store. There can be a maximum of 10000 + files in a vector store. + maxItems: 10000 + items: + type: string + chunking_strategy: + type: object + description: The chunking strategy used to chunk the file(s). If not set, will + use the `auto` strategy. + oneOf: + - type: object + title: Auto Chunking Strategy + description: The default strategy. This strategy currently uses a + `max_chunk_size_tokens` of `800` and + `chunk_overlap_tokens` of `400`. + additionalProperties: false + properties: + type: + type: string + description: Always `auto`. + enum: + - auto + x-stainless-const: true + required: + - type + - type: object + title: Static Chunking Strategy + additionalProperties: false + properties: + type: + type: string + description: Always `static`. + enum: + - static + x-stainless-const: true + static: + type: object + additionalProperties: false + properties: + max_chunk_size_tokens: + type: integer + minimum: 100 + maximum: 4096 + description: The maximum number of tokens in each chunk. The default value is + `800`. The minimum value is `100` and the + maximum value is `4096`. + chunk_overlap_tokens: + type: integer + description: > + The number of tokens that overlap between + chunks. The default value is `400`. + + + Note that the overlap must not exceed half + of `max_chunk_size_tokens`. + required: + - max_chunk_size_tokens + - chunk_overlap_tokens + required: + - type + - static + metadata: + $ref: "#/components/schemas/Metadata" + oneOf: + - required: + - vector_store_ids + - required: + - vector_stores + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + CreateTranscriptionRequest: + type: object + additionalProperties: false + properties: + file: + description: > + The audio file object (not file name) to transcribe, in one of these + formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. + type: string + x-oaiTypeLabel: file + format: binary + model: + description: > + ID of the model to use. The options are `gpt-4o-transcribe`, + `gpt-4o-mini-transcribe`, and `whisper-1` (which is powered by our + open source Whisper V2 model). + example: gpt-4o-transcribe + anyOf: + - type: string + - type: string + enum: + - whisper-1 + - gpt-4o-transcribe + - gpt-4o-mini-transcribe + x-stainless-const: true + x-oaiTypeLabel: string + language: + description: > + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) + (e.g. `en`) format will improve accuracy and latency. + type: string + prompt: + description: > + An optional text to guide the model's style or continue a previous + audio segment. The [prompt](/docs/guides/speech-to-text#prompting) + should match the audio language. + type: string + response_format: + $ref: "#/components/schemas/AudioResponseFormat" + temperature: + description: > + The sampling temperature, between 0 and 1. Higher values like 0.8 + will make the output more random, while lower values like 0.2 will + make it more focused and deterministic. If set to 0, the model will + use [log probability](https://en.wikipedia.org/wiki/Log_probability) + to automatically increase the temperature until certain thresholds + are hit. + type: number + default: 0 + include[]: + description: > + Additional information to include in the transcription response. + + `logprobs` will return the log probabilities of the tokens in the + + response to understand the model's confidence in the transcription. + + `logprobs` only works with response_format set to `json` and only + with + + the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`. + type: array + items: + $ref: "#/components/schemas/TranscriptionInclude" + timestamp_granularities[]: + description: > + The timestamp granularities to populate for this transcription. + `response_format` must be set `verbose_json` to use timestamp + granularities. Either or both of these options are supported: + `word`, or `segment`. Note: There is no additional latency for + segment timestamps, but generating word timestamps incurs additional + latency. + type: array + items: + type: string + enum: + - word + - segment + default: + - segment + stream: + description: | + If set to true, the model response data will be streamed to the client + as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). + See the [Streaming section of the Speech-to-Text guide](/docs/guides/speech-to-text?lang=curl#streaming-transcriptions) + for more information. + + Note: Streaming is not supported for the `whisper-1` model and will be ignored. + type: boolean + nullable: true + default: false + chunking_strategy: + description: 'Controls how the audio is cut into chunks. When set to `"auto"`, + the server first normalizes loudness and then uses voice activity + detection (VAD) to choose boundaries. `server_vad` object can be + provided to tweak VAD detection parameters manually. If unset, the + audio is transcribed as a single block. ' + anyOf: + - type: string + enum: + - auto + default: + - auto + description: > + Automatically set chunking parameters based on the audio. Must + be set to `"auto"`. + x-stainless-const: true + - $ref: "#/components/schemas/VadConfig" + nullable: true + x-oaiTypeLabel: string + required: + - file + - model + CreateTranscriptionResponseJson: + type: object + description: Represents a transcription response returned by model, based on the + provided input. + properties: + text: + type: string + description: The transcribed text. + logprobs: + type: array + optional: true + description: > + The log probabilities of the tokens in the transcription. Only + returned with the models `gpt-4o-transcribe` and + `gpt-4o-mini-transcribe` if `logprobs` is added to the `include` + array. + items: + type: object + properties: + token: + type: string + description: The token in the transcription. + logprob: + type: number + description: The log probability of the token. + bytes: + type: array + items: + type: number + description: The bytes of the token. + required: + - text + x-oaiMeta: + name: The transcription object (JSON) + group: audio + example: > + { + "text": "Imagine the wildest idea that you've ever had, and you're curious about how it might scale to something that's a 100, a 1,000 times bigger. This is a place where you can get to do that." + } + CreateTranscriptionResponseStreamEvent: + anyOf: + - $ref: "#/components/schemas/TranscriptTextDeltaEvent" + - $ref: "#/components/schemas/TranscriptTextDoneEvent" + discriminator: + propertyName: type + CreateTranscriptionResponseVerboseJson: + type: object + description: Represents a verbose json transcription response returned by model, + based on the provided input. + properties: + language: + type: string + description: The language of the input audio. + duration: + type: number + description: The duration of the input audio. + text: + type: string + description: The transcribed text. + words: + type: array + description: Extracted words and their corresponding timestamps. + items: + $ref: "#/components/schemas/TranscriptionWord" + segments: + type: array + description: Segments of the transcribed text and their corresponding details. + items: + $ref: "#/components/schemas/TranscriptionSegment" + required: + - language + - duration + - text + x-oaiMeta: + name: The transcription object (Verbose JSON) + group: audio + example: > + { + "task": "transcribe", + "language": "english", + "duration": 8.470000267028809, + "text": "The beach was a popular spot on a hot summer day. People were swimming in the ocean, building sandcastles, and playing beach volleyball.", + "segments": [ + { + "id": 0, + "seek": 0, + "start": 0.0, + "end": 3.319999933242798, + "text": " The beach was a popular spot on a hot summer day.", + "tokens": [ + 50364, 440, 7534, 390, 257, 3743, 4008, 322, 257, 2368, 4266, 786, 13, 50530 + ], + "temperature": 0.0, + "avg_logprob": -0.2860786020755768, + "compression_ratio": 1.2363636493682861, + "no_speech_prob": 0.00985979475080967 + }, + ... + ] + } + CreateTranslationRequest: + type: object + additionalProperties: false + properties: + file: + description: > + The audio file object (not file name) translate, in one of these + formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. + type: string + x-oaiTypeLabel: file + format: binary + model: + description: > + ID of the model to use. Only `whisper-1` (which is powered by our + open source Whisper V2 model) is currently available. + example: whisper-1 + anyOf: + - type: string + - type: string + enum: + - whisper-1 + x-stainless-const: true + x-oaiTypeLabel: string + prompt: + description: > + An optional text to guide the model's style or continue a previous + audio segment. The [prompt](/docs/guides/speech-to-text#prompting) + should be in English. + type: string + response_format: + description: > + The format of the output, in one of these options: `json`, `text`, + `srt`, `verbose_json`, or `vtt`. + type: string + enum: + - json + - text + - srt + - verbose_json + - vtt + default: json + temperature: + description: > + The sampling temperature, between 0 and 1. Higher values like 0.8 + will make the output more random, while lower values like 0.2 will + make it more focused and deterministic. If set to 0, the model will + use [log probability](https://en.wikipedia.org/wiki/Log_probability) + to automatically increase the temperature until certain thresholds + are hit. + type: number + default: 0 + required: + - file + - model + CreateTranslationResponseJson: + type: object + properties: + text: + type: string + required: + - text + CreateTranslationResponseVerboseJson: + type: object + properties: + language: + type: string + description: The language of the output translation (always `english`). + duration: + type: number + description: The duration of the input audio. + text: + type: string + description: The translated text. + segments: + type: array + description: Segments of the translated text and their corresponding details. + items: + $ref: "#/components/schemas/TranscriptionSegment" + required: + - language + - duration + - text + CreateUploadRequest: + type: object + additionalProperties: false + properties: + filename: + description: | + The name of the file to upload. + type: string + purpose: + description: > + The intended purpose of the uploaded file. + + + See the [documentation on File + purposes](/docs/api-reference/files/create#files-create-purpose). + type: string + enum: + - assistants + - batch + - fine-tune + - vision + bytes: + description: | + The number of bytes in the file you are uploading. + type: integer + mime_type: + description: > + The MIME type of the file. + + + This must fall within the supported MIME types for your file + purpose. See the supported MIME types for assistants and vision. + type: string + required: + - filename + - purpose + - bytes + - mime_type + CreateVectorStoreFileBatchRequest: + type: object + additionalProperties: false + properties: + file_ids: + description: A list of [File](/docs/api-reference/files) IDs that the vector + store should use. Useful for tools like `file_search` that can + access files. + type: array + minItems: 1 + maxItems: 500 + items: + type: string + chunking_strategy: + $ref: "#/components/schemas/ChunkingStrategyRequestParam" + attributes: + $ref: "#/components/schemas/VectorStoreFileAttributes" + required: + - file_ids + CreateVectorStoreFileRequest: + type: object + additionalProperties: false + properties: + file_id: + description: A [File](/docs/api-reference/files) ID that the vector store should + use. Useful for tools like `file_search` that can access files. + type: string + chunking_strategy: + $ref: "#/components/schemas/ChunkingStrategyRequestParam" + attributes: + $ref: "#/components/schemas/VectorStoreFileAttributes" + required: + - file_id + CreateVectorStoreRequest: + type: object + additionalProperties: false + properties: + file_ids: + description: A list of [File](/docs/api-reference/files) IDs that the vector + store should use. Useful for tools like `file_search` that can + access files. + type: array + maxItems: 500 + items: + type: string + name: + description: The name of the vector store. + type: string + expires_after: + $ref: "#/components/schemas/VectorStoreExpirationAfter" + chunking_strategy: + type: object + description: The chunking strategy used to chunk the file(s). If not set, will + use the `auto` strategy. Only applicable if `file_ids` is non-empty. + oneOf: + - $ref: "#/components/schemas/AutoChunkingStrategyRequestParam" + - $ref: "#/components/schemas/StaticChunkingStrategyRequestParam" + metadata: + $ref: "#/components/schemas/Metadata" + DeleteAssistantResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + enum: + - assistant.deleted + x-stainless-const: true + required: + - id + - object + - deleted + DeleteCertificateResponse: + type: object + properties: + object: + type: string + description: The object type, must be `certificate.deleted`. + enum: + - certificate.deleted + x-stainless-const: true + id: + type: string + description: The ID of the certificate that was deleted. + required: + - object + - id + DeleteFileResponse: + type: object + properties: + id: + type: string + object: + type: string + enum: + - file + x-stainless-const: true + deleted: + type: boolean + required: + - id + - object + - deleted + DeleteFineTuningCheckpointPermissionResponse: + type: object + properties: + id: + type: string + description: The ID of the fine-tuned model checkpoint permission that was + deleted. + object: + type: string + description: The object type, which is always "checkpoint.permission". + enum: + - checkpoint.permission + x-stainless-const: true + deleted: + type: boolean + description: Whether the fine-tuned model checkpoint permission was successfully + deleted. + required: + - id + - object + - deleted + DeleteMessageResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + enum: + - thread.message.deleted + x-stainless-const: true + required: + - id + - object + - deleted + DeleteModelResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + required: + - id + - object + - deleted + DeleteThreadResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + enum: + - thread.deleted + x-stainless-const: true + required: + - id + - object + - deleted + DeleteVectorStoreFileResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + enum: + - vector_store.file.deleted + x-stainless-const: true + required: + - id + - object + - deleted + DeleteVectorStoreResponse: + type: object + properties: + id: + type: string + deleted: + type: boolean + object: + type: string + enum: + - vector_store.deleted + x-stainless-const: true + required: + - id + - object + - deleted + DoneEvent: + type: object + properties: + event: + type: string + enum: + - done + x-stainless-const: true + data: + type: string + enum: + - "[DONE]" + x-stainless-const: true + required: + - event + - data + description: Occurs when a stream ends. + x-oaiMeta: + dataDescription: "`data` is `[DONE]`" + DoubleClick: + type: object + title: DoubleClick + description: | + A double click action. + properties: + type: + type: string + enum: + - double_click + default: double_click + description: > + Specifies the event type. For a double click action, this property + is + + always set to `double_click`. + x-stainless-const: true + x: + type: integer + description: | + The x-coordinate where the double click occurred. + y: + type: integer + description: | + The y-coordinate where the double click occurred. + required: + - type + - x + - y + Drag: + type: object + title: Drag + description: | + A drag action. + properties: + type: + type: string + enum: + - drag + default: drag + description: | + Specifies the event type. For a drag action, this property is + always set to `drag`. + x-stainless-const: true + path: + type: array + description: > + An array of coordinates representing the path of the drag action. + Coordinates will appear as an array + + of objects, eg + + ``` + + [ + { x: 100, y: 200 }, + { x: 200, y: 300 } + ] + + ``` + items: + title: Drag path coordinates + description: | + A series of x/y coordinate pairs in the drag path. + $ref: "#/components/schemas/Coordinate" + required: + - type + - path + EasyInputMessage: + type: object + title: Input message + description: > + A message input to the model with a role indicating instruction + following + + hierarchy. Instructions given with the `developer` or `system` role take + + precedence over instructions given with the `user` role. Messages with + the + + `assistant` role are presumed to have been generated by the model in + previous + + interactions. + properties: + role: + type: string + description: > + The role of the message input. One of `user`, `assistant`, `system`, + or + + `developer`. + enum: + - user + - assistant + - system + - developer + content: + description: > + Text, image, or audio input to the model, used to generate a + response. + + Can also contain previous assistant responses. + oneOf: + - type: string + title: Text input + description: | + A text input to the model. + - $ref: "#/components/schemas/InputMessageContentList" + type: + type: string + description: | + The type of the message input. Always `message`. + enum: + - message + x-stainless-const: true + required: + - role + - content + Embedding: + type: object + description: | + Represents an embedding vector returned by embedding endpoint. + properties: + index: + type: integer + description: The index of the embedding in the list of embeddings. + embedding: + type: array + description: > + The embedding vector, which is a list of floats. The length of + vector depends on the model as listed in the [embedding + guide](/docs/guides/embeddings). + items: + type: number + format: float + object: + type: string + description: The object type, which is always "embedding". + enum: + - embedding + x-stainless-const: true + required: + - index + - object + - embedding + x-oaiMeta: + name: The embedding object + example: | + { + "object": "embedding", + "embedding": [ + 0.0023064255, + -0.009327292, + .... (1536 floats total for ada-002) + -0.0028842222, + ], + "index": 0 + } + Error: + type: object + properties: + code: + type: string + nullable: true + message: + type: string + nullable: false + param: + type: string + nullable: true + type: + type: string + nullable: false + required: + - type + - message + - param + - code + ErrorEvent: + type: object + properties: + event: + type: string + enum: + - error + x-stainless-const: true + data: + $ref: "#/components/schemas/Error" + required: + - event + - data + description: Occurs when an [error](/docs/guides/error-codes#api-errors) occurs. + This can happen due to an internal server error or a timeout. + x-oaiMeta: + dataDescription: "`data` is an [error](/docs/guides/error-codes#api-errors)" + ErrorResponse: + type: object + properties: + error: + $ref: "#/components/schemas/Error" + required: + - error + Eval: + type: object + title: Eval + description: | + An Eval object with a data source config and testing criteria. + An Eval represents a task to be done for your LLM integration. + Like: + - Improve the quality of my chatbot + - See how well my chatbot handles customer support + - Check if o4-mini is better at my usecase than gpt-4o + properties: + object: + type: string + enum: + - eval + default: eval + description: The object type. + x-stainless-const: true + id: + type: string + description: Unique identifier for the evaluation. + name: + type: string + description: The name of the evaluation. + example: Chatbot effectiveness Evaluation + data_source_config: + type: object + description: Configuration of data sources used in runs of the evaluation. + oneOf: + - $ref: "#/components/schemas/EvalCustomDataSourceConfig" + - $ref: "#/components/schemas/EvalLogsDataSourceConfig" + - $ref: "#/components/schemas/EvalStoredCompletionsDataSourceConfig" + testing_criteria: + default: eval + description: A list of testing criteria. + type: array + items: + oneOf: + - $ref: "#/components/schemas/EvalGraderLabelModel" + - $ref: "#/components/schemas/EvalGraderStringCheck" + - $ref: "#/components/schemas/EvalGraderTextSimilarity" + - $ref: "#/components/schemas/EvalGraderPython" + - $ref: "#/components/schemas/EvalGraderScoreModel" + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the eval was created. + metadata: + $ref: "#/components/schemas/Metadata" + required: + - id + - data_source_config + - object + - testing_criteria + - name + - created_at + - metadata + x-oaiMeta: + name: The eval object + group: evals + example: | + { + "object": "eval", + "id": "eval_67abd54d9b0081909a86353f6fb9317a", + "data_source_config": { + "type": "custom", + "item_schema": { + "type": "object", + "properties": { + "label": {"type": "string"}, + }, + "required": ["label"] + }, + "include_sample_schema": true + }, + "testing_criteria": [ + { + "name": "My string check grader", + "type": "string_check", + "input": "{{sample.output_text}}", + "reference": "{{item.label}}", + "operation": "eq", + } + ], + "name": "External Data Eval", + "created_at": 1739314509, + "metadata": { + "test": "synthetics", + } + } + EvalApiError: + type: object + title: EvalApiError + description: | + An object representing an error response from the Eval API. + properties: + code: + type: string + description: The error code. + message: + type: string + description: The error message. + required: + - code + - message + x-oaiMeta: + name: The API error object + group: evals + example: | + { + "code": "internal_error", + "message": "The eval run failed due to an internal error." + } + EvalCustomDataSourceConfig: + type: object + title: CustomDataSourceConfig + description: > + A CustomDataSourceConfig which specifies the schema of your `item` and + optionally `sample` namespaces. + + The response schema defines the shape of the data that will be: + + - Used to define your testing criteria and + + - What data is required when creating a run + properties: + type: + type: string + enum: + - custom + default: custom + description: The type of data source. Always `custom`. + x-stainless-const: true + schema: + type: object + description: | + The json schema for the run data source items. + Learn how to build JSON schemas [here](https://json-schema.org/). + additionalProperties: true + example: | + { + "type": "object", + "properties": { + "item": { + "type": "object", + "properties": { + "label": {"type": "string"}, + }, + "required": ["label"] + } + }, + "required": ["item"] + } + required: + - type + - schema + x-oaiMeta: + name: The eval custom data source config object + group: evals + example: | + { + "type": "custom", + "schema": { + "type": "object", + "properties": { + "item": { + "type": "object", + "properties": { + "label": {"type": "string"}, + }, + "required": ["label"] + } + }, + "required": ["item"] + } + } + EvalGraderLabelModel: + type: object + title: LabelModelGrader + allOf: + - $ref: "#/components/schemas/GraderLabelModel" + EvalGraderPython: + type: object + title: PythonGrader + allOf: + - $ref: "#/components/schemas/GraderPython" + - type: object + properties: + pass_threshold: + type: number + description: The threshold for the score. + x-oaiMeta: + name: Eval Python Grader + group: graders + example: | + { + "type": "python", + "name": "Example python grader", + "image_tag": "2025-05-08", + "source": """ + def grade(sample: dict, item: dict) -> float: + \""" + Returns 1.0 if `output_text` equals `label`, otherwise 0.0. + \""" + output = sample.get("output_text") + label = item.get("label") + return 1.0 if output == label else 0.0 + """, + "pass_threshold": 0.8 + } + EvalGraderScoreModel: + type: object + title: ScoreModelGrader + allOf: + - $ref: "#/components/schemas/GraderScoreModel" + - type: object + properties: + pass_threshold: + type: number + description: The threshold for the score. + EvalGraderStringCheck: + type: object + title: StringCheckGrader + allOf: + - $ref: "#/components/schemas/GraderStringCheck" + EvalGraderTextSimilarity: + type: object + title: TextSimilarityGrader + allOf: + - $ref: "#/components/schemas/GraderTextSimilarity" + - type: object + properties: + pass_threshold: + type: number + description: The threshold for the score. + required: + - pass_threshold + x-oaiMeta: + name: Text Similarity Grader + group: graders + example: | + { + "type": "text_similarity", + "name": "Example text similarity grader", + "input": "{{sample.output_text}}", + "reference": "{{item.label}}", + "pass_threshold": 0.8, + "evaluation_metric": "fuzzy_match" + } + EvalItem: + type: object + title: Eval message object + description: > + A message input to the model with a role indicating instruction + following + + hierarchy. Instructions given with the `developer` or `system` role take + + precedence over instructions given with the `user` role. Messages with + the + + `assistant` role are presumed to have been generated by the model in + previous + + interactions. + properties: + role: + type: string + description: > + The role of the message input. One of `user`, `assistant`, `system`, + or + + `developer`. + enum: + - user + - assistant + - system + - developer + content: + description: | + Text inputs to the model - can contain template strings. + oneOf: + - type: string + title: Text input + description: | + A text input to the model. + - $ref: "#/components/schemas/InputTextContent" + - type: object + title: Output text + description: | + A text output from the model. + properties: + type: + type: string + description: | + The type of the output text. Always `output_text`. + enum: + - output_text + x-stainless-const: true + text: + type: string + description: | + The text output from the model. + required: + - type + - text + type: + type: string + description: | + The type of the message input. Always `message`. + enum: + - message + x-stainless-const: true + required: + - role + - content + EvalJsonlFileContentSource: + type: object + title: EvalJsonlFileContentSource + properties: + type: + type: string + enum: + - file_content + default: file_content + description: The type of jsonl source. Always `file_content`. + x-stainless-const: true + content: + type: array + items: + type: object + properties: + item: + type: object + additionalProperties: true + sample: + type: object + additionalProperties: true + required: + - item + description: The content of the jsonl file. + required: + - type + - content + EvalJsonlFileIdSource: + type: object + title: EvalJsonlFileIdSource + properties: + type: + type: string + enum: + - file_id + default: file_id + description: The type of jsonl source. Always `file_id`. + x-stainless-const: true + id: + type: string + description: The identifier of the file. + required: + - type + - id + EvalList: + type: object + title: EvalList + description: | + An object representing a list of evals. + properties: + object: + type: string + enum: + - list + default: list + description: | + The type of this object. It is always set to "list". + x-stainless-const: true + data: + type: array + description: | + An array of eval objects. + items: + $ref: "#/components/schemas/Eval" + first_id: + type: string + description: The identifier of the first eval in the data array. + last_id: + type: string + description: The identifier of the last eval in the data array. + has_more: + type: boolean + description: Indicates whether there are more evals available. + required: + - object + - data + - first_id + - last_id + - has_more + x-oaiMeta: + name: The eval list object + group: evals + example: | + { + "object": "list", + "data": [ + { + "object": "eval", + "id": "eval_67abd54d9b0081909a86353f6fb9317a", + "data_source_config": { + "type": "custom", + "schema": { + "type": "object", + "properties": { + "item": { + "type": "object", + "properties": { + "input": { + "type": "string" + }, + "ground_truth": { + "type": "string" + } + }, + "required": [ + "input", + "ground_truth" + ] + } + }, + "required": [ + "item" + ] + } + }, + "testing_criteria": [ + { + "name": "String check", + "id": "String check-2eaf2d8d-d649-4335-8148-9535a7ca73c2", + "type": "string_check", + "input": "{{item.input}}", + "reference": "{{item.ground_truth}}", + "operation": "eq" + } + ], + "name": "External Data Eval", + "created_at": 1739314509, + "metadata": {}, + } + ], + "first_id": "eval_67abd54d9b0081909a86353f6fb9317a", + "last_id": "eval_67abd54d9b0081909a86353f6fb9317a", + "has_more": true + } + EvalLogsDataSourceConfig: + type: object + title: LogsDataSourceConfig + description: > + A LogsDataSourceConfig which specifies the metadata property of your + logs query. + + This is usually metadata like `usecase=chatbot` or `prompt-version=v2`, + etc. + + The schema returned by this data source config is used to defined what + variables are available in your evals. + + `item` and `sample` are both defined when using this data source config. + properties: + type: + type: string + enum: + - logs + default: logs + description: The type of data source. Always `logs`. + x-stainless-const: true + metadata: + $ref: "#/components/schemas/Metadata" + schema: + type: object + description: | + The json schema for the run data source items. + Learn how to build JSON schemas [here](https://json-schema.org/). + additionalProperties: true + required: + - type + - schema + x-oaiMeta: + name: The logs data source object for evals + group: evals + example: | + { + "type": "logs", + "metadata": { + "language": "english" + }, + "schema": { + "type": "object", + "properties": { + "item": { + "type": "object" + }, + "sample": { + "type": "object" + } + }, + "required": [ + "item", + "sample" + } + } + EvalResponsesSource: + type: object + title: EvalResponsesSource + description: | + A EvalResponsesSource object describing a run data source configuration. + properties: + type: + type: string + enum: + - responses + description: The type of run data source. Always `responses`. + metadata: + type: object + nullable: true + description: Metadata filter for the responses. This is a query parameter used + to select responses. + model: + type: string + nullable: true + description: The name of the model to find responses for. This is a query + parameter used to select responses. + instructions_search: + type: string + nullable: true + description: Optional string to search the 'instructions' field. This is a query + parameter used to select responses. + created_after: + type: integer + minimum: 0 + nullable: true + description: Only include items created after this timestamp (inclusive). This + is a query parameter used to select responses. + created_before: + type: integer + minimum: 0 + nullable: true + description: Only include items created before this timestamp (inclusive). This + is a query parameter used to select responses. + reasoning_effort: + $ref: "#/components/schemas/ReasoningEffort" + nullable: true + description: Optional reasoning effort parameter. This is a query parameter used + to select responses. + temperature: + type: number + nullable: true + description: Sampling temperature. This is a query parameter used to select + responses. + top_p: + type: number + nullable: true + description: Nucleus sampling parameter. This is a query parameter used to + select responses. + users: + type: array + items: + type: string + nullable: true + description: List of user identifiers. This is a query parameter used to select + responses. + tools: + type: array + items: + type: string + nullable: true + description: List of tool names. This is a query parameter used to select + responses. + required: + - type + x-oaiMeta: + name: The run data source object used to configure an individual run + group: eval runs + example: | + { + "type": "responses", + "model": "gpt-4o-mini-2024-07-18", + "temperature": 0.7, + "top_p": 1.0, + "users": ["user1", "user2"], + "tools": ["tool1", "tool2"], + "instructions_search": "You are a coding assistant" + } + EvalRun: + type: object + title: EvalRun + description: | + A schema representing an evaluation run. + properties: + object: + type: string + enum: + - eval.run + default: eval.run + description: The type of the object. Always "eval.run". + x-stainless-const: true + id: + type: string + description: Unique identifier for the evaluation run. + eval_id: + type: string + description: The identifier of the associated evaluation. + status: + type: string + description: The status of the evaluation run. + model: + type: string + description: The model that is evaluated, if applicable. + name: + type: string + description: The name of the evaluation run. + created_at: + type: integer + description: Unix timestamp (in seconds) when the evaluation run was created. + report_url: + type: string + description: The URL to the rendered evaluation run report on the UI dashboard. + result_counts: + type: object + description: Counters summarizing the outcomes of the evaluation run. + properties: + total: + type: integer + description: Total number of executed output items. + errored: + type: integer + description: Number of output items that resulted in an error. + failed: + type: integer + description: Number of output items that failed to pass the evaluation. + passed: + type: integer + description: Number of output items that passed the evaluation. + required: + - total + - errored + - failed + - passed + per_model_usage: + type: array + description: Usage statistics for each model during the evaluation run. + items: + type: object + properties: + model_name: + type: string + description: The name of the model. + invocation_count: + type: integer + description: The number of invocations. + prompt_tokens: + type: integer + description: The number of prompt tokens used. + completion_tokens: + type: integer + description: The number of completion tokens generated. + total_tokens: + type: integer + description: The total number of tokens used. + cached_tokens: + type: integer + description: The number of tokens retrieved from cache. + required: + - model_name + - invocation_count + - prompt_tokens + - completion_tokens + - total_tokens + - cached_tokens + per_testing_criteria_results: + type: array + description: Results per testing criteria applied during the evaluation run. + items: + type: object + properties: + testing_criteria: + type: string + description: A description of the testing criteria. + passed: + type: integer + description: Number of tests passed for this criteria. + failed: + type: integer + description: Number of tests failed for this criteria. + required: + - testing_criteria + - passed + - failed + data_source: + type: object + description: Information about the run's data source. + oneOf: + - $ref: "#/components/schemas/CreateEvalJsonlRunDataSource" + - $ref: "#/components/schemas/CreateEvalCompletionsRunDataSource" + - $ref: "#/components/schemas/CreateEvalResponsesRunDataSource" + metadata: + $ref: "#/components/schemas/Metadata" + error: + $ref: "#/components/schemas/EvalApiError" + required: + - object + - id + - eval_id + - status + - model + - name + - created_at + - report_url + - result_counts + - per_model_usage + - per_testing_criteria_results + - data_source + - metadata + - error + x-oaiMeta: + name: The eval run object + group: evals + example: > + { + "object": "eval.run", + "id": "evalrun_67e57965b480819094274e3a32235e4c", + "eval_id": "eval_67e579652b548190aaa83ada4b125f47", + "report_url": "https://platform.openai.com/evaluations/eval_67e579652b548190aaa83ada4b125f47?run_id=evalrun_67e57965b480819094274e3a32235e4c", + "status": "queued", + "model": "gpt-4o-mini", + "name": "gpt-4o-mini", + "created_at": 1743092069, + "result_counts": { + "total": 0, + "errored": 0, + "failed": 0, + "passed": 0 + }, + "per_model_usage": null, + "per_testing_criteria_results": null, + "data_source": { + "type": "completions", + "source": { + "type": "file_content", + "content": [ + { + "item": { + "input": "Tech Company Launches Advanced Artificial Intelligence Platform", + "ground_truth": "Technology" + } + }, + { + "item": { + "input": "Central Bank Increases Interest Rates Amid Inflation Concerns", + "ground_truth": "Markets" + } + }, + { + "item": { + "input": "International Summit Addresses Climate Change Strategies", + "ground_truth": "World" + } + }, + { + "item": { + "input": "Major Retailer Reports Record-Breaking Holiday Sales", + "ground_truth": "Business" + } + }, + { + "item": { + "input": "National Team Qualifies for World Championship Finals", + "ground_truth": "Sports" + } + }, + { + "item": { + "input": "Stock Markets Rally After Positive Economic Data Released", + "ground_truth": "Markets" + } + }, + { + "item": { + "input": "Global Manufacturer Announces Merger with Competitor", + "ground_truth": "Business" + } + }, + { + "item": { + "input": "Breakthrough in Renewable Energy Technology Unveiled", + "ground_truth": "Technology" + } + }, + { + "item": { + "input": "World Leaders Sign Historic Climate Agreement", + "ground_truth": "World" + } + }, + { + "item": { + "input": "Professional Athlete Sets New Record in Championship Event", + "ground_truth": "Sports" + } + }, + { + "item": { + "input": "Financial Institutions Adapt to New Regulatory Requirements", + "ground_truth": "Business" + } + }, + { + "item": { + "input": "Tech Conference Showcases Advances in Artificial Intelligence", + "ground_truth": "Technology" + } + }, + { + "item": { + "input": "Global Markets Respond to Oil Price Fluctuations", + "ground_truth": "Markets" + } + }, + { + "item": { + "input": "International Cooperation Strengthened Through New Treaty", + "ground_truth": "World" + } + }, + { + "item": { + "input": "Sports League Announces Revised Schedule for Upcoming Season", + "ground_truth": "Sports" + } + } + ] + }, + "input_messages": { + "type": "template", + "template": [ + { + "type": "message", + "role": "developer", + "content": { + "type": "input_text", + "text": "Categorize a given news headline into one of the following topics: Technology, Markets, World, Business, or Sports.\n\n# Steps\n\n1. Analyze the content of the news headline to understand its primary focus.\n2. Extract the subject matter, identifying any key indicators or keywords.\n3. Use the identified indicators to determine the most suitable category out of the five options: Technology, Markets, World, Business, or Sports.\n4. Ensure only one category is selected per headline.\n\n# Output Format\n\nRespond with the chosen category as a single word. For instance: \"Technology\", \"Markets\", \"World\", \"Business\", or \"Sports\".\n\n# Examples\n\n**Input**: \"Apple Unveils New iPhone Model, Featuring Advanced AI Features\" \n**Output**: \"Technology\"\n\n**Input**: \"Global Stocks Mixed as Investors Await Central Bank Decisions\" \n**Output**: \"Markets\"\n\n**Input**: \"War in Ukraine: Latest Updates on Negotiation Status\" \n**Output**: \"World\"\n\n**Input**: \"Microsoft in Talks to Acquire Gaming Company for $2 Billion\" \n**Output**: \"Business\"\n\n**Input**: \"Manchester United Secures Win in Premier League Football Match\" \n**Output**: \"Sports\" \n\n# Notes\n\n- If the headline appears to fit into more than one category, choose the most dominant theme.\n- Keywords or phrases such as \"stocks\", \"company acquisition\", \"match\", or technological brands can be good indicators for classification.\n" + } + }, + { + "type": "message", + "role": "user", + "content": { + "type": "input_text", + "text": "{{item.input}}" + } + } + ] + }, + "model": "gpt-4o-mini", + "sampling_params": { + "seed": 42, + "temperature": 1.0, + "top_p": 1.0, + "max_completions_tokens": 2048 + } + }, + "error": null, + "metadata": {} + } + EvalRunList: + type: object + title: EvalRunList + description: | + An object representing a list of runs for an evaluation. + properties: + object: + type: string + enum: + - list + default: list + description: | + The type of this object. It is always set to "list". + x-stainless-const: true + data: + type: array + description: | + An array of eval run objects. + items: + $ref: "#/components/schemas/EvalRun" + first_id: + type: string + description: The identifier of the first eval run in the data array. + last_id: + type: string + description: The identifier of the last eval run in the data array. + has_more: + type: boolean + description: Indicates whether there are more evals available. + required: + - object + - data + - first_id + - last_id + - has_more + x-oaiMeta: + name: The eval run list object + group: evals + example: > + { + "object": "list", + "data": [ + { + "object": "eval.run", + "id": "evalrun_67b7fbdad46c819092f6fe7a14189620", + "eval_id": "eval_67b7fa9a81a88190ab4aa417e397ea21", + "report_url": "https://platform.openai.com/evaluations/eval_67b7fa9a81a88190ab4aa417e397ea21?run_id=evalrun_67b7fbdad46c819092f6fe7a14189620", + "status": "completed", + "model": "o3-mini", + "name": "Academic Assistant", + "created_at": 1740110812, + "result_counts": { + "total": 171, + "errored": 0, + "failed": 80, + "passed": 91 + }, + "per_model_usage": null, + "per_testing_criteria_results": [ + { + "testing_criteria": "String check grader", + "passed": 91, + "failed": 80 + } + ], + "run_data_source": { + "type": "completions", + "template_messages": [ + { + "type": "message", + "role": "system", + "content": { + "type": "input_text", + "text": "You are a helpful assistant." + } + }, + { + "type": "message", + "role": "user", + "content": { + "type": "input_text", + "text": "Hello, can you help me with my homework?" + } + } + ], + "datasource_reference": null, + "model": "o3-mini", + "max_completion_tokens": null, + "seed": null, + "temperature": null, + "top_p": null + }, + "error": null, + "metadata": {"test": "synthetics"} + } + ], + "first_id": "evalrun_67abd54d60ec8190832b46859da808f7", + "last_id": "evalrun_67abd54d60ec8190832b46859da808f7", + "has_more": false + } + EvalRunOutputItem: + type: object + title: EvalRunOutputItem + description: | + A schema representing an evaluation run output item. + properties: + object: + type: string + enum: + - eval.run.output_item + default: eval.run.output_item + description: The type of the object. Always "eval.run.output_item". + x-stainless-const: true + id: + type: string + description: Unique identifier for the evaluation run output item. + run_id: + type: string + description: The identifier of the evaluation run associated with this output + item. + eval_id: + type: string + description: The identifier of the evaluation group. + created_at: + type: integer + description: Unix timestamp (in seconds) when the evaluation run was created. + status: + type: string + description: The status of the evaluation run. + datasource_item_id: + type: integer + description: The identifier for the data source item. + datasource_item: + type: object + description: Details of the input data source item. + additionalProperties: true + results: + type: array + description: A list of results from the evaluation run. + items: + type: object + description: A result object. + additionalProperties: true + sample: + type: object + description: A sample containing the input and output of the evaluation run. + properties: + input: + type: array + description: An array of input messages. + items: + type: object + description: An input message. + properties: + role: + type: string + description: The role of the message sender (e.g., system, user, developer). + content: + type: string + description: The content of the message. + required: + - role + - content + output: + type: array + description: An array of output messages. + items: + type: object + properties: + role: + type: string + description: The role of the message (e.g. "system", "assistant", "user"). + content: + type: string + description: The content of the message. + finish_reason: + type: string + description: The reason why the sample generation was finished. + model: + type: string + description: The model used for generating the sample. + usage: + type: object + description: Token usage details for the sample. + properties: + total_tokens: + type: integer + description: The total number of tokens used. + completion_tokens: + type: integer + description: The number of completion tokens generated. + prompt_tokens: + type: integer + description: The number of prompt tokens used. + cached_tokens: + type: integer + description: The number of tokens retrieved from cache. + required: + - total_tokens + - completion_tokens + - prompt_tokens + - cached_tokens + error: + $ref: "#/components/schemas/EvalApiError" + temperature: + type: number + description: The sampling temperature used. + max_completion_tokens: + type: integer + description: The maximum number of tokens allowed for completion. + top_p: + type: number + description: The top_p value used for sampling. + seed: + type: integer + description: The seed used for generating the sample. + required: + - input + - output + - finish_reason + - model + - usage + - error + - temperature + - max_completion_tokens + - top_p + - seed + required: + - object + - id + - run_id + - eval_id + - created_at + - status + - datasource_item_id + - datasource_item + - results + - sample + x-oaiMeta: + name: The eval run output item object + group: evals + example: > + { + "object": "eval.run.output_item", + "id": "outputitem_67abd55eb6548190bb580745d5644a33", + "run_id": "evalrun_67abd54d60ec8190832b46859da808f7", + "eval_id": "eval_67abd54d9b0081909a86353f6fb9317a", + "created_at": 1739314509, + "status": "pass", + "datasource_item_id": 137, + "datasource_item": { + "teacher": "To grade essays, I only check for style, content, and grammar.", + "student": "I am a student who is trying to write the best essay." + }, + "results": [ + { + "name": "String Check Grader", + "type": "string-check-grader", + "score": 1.0, + "passed": true, + } + ], + "sample": { + "input": [ + { + "role": "system", + "content": "You are an evaluator bot..." + }, + { + "role": "user", + "content": "You are assessing..." + } + ], + "output": [ + { + "role": "assistant", + "content": "The rubric is not clear nor concise." + } + ], + "finish_reason": "stop", + "model": "gpt-4o-2024-08-06", + "usage": { + "total_tokens": 521, + "completion_tokens": 2, + "prompt_tokens": 519, + "cached_tokens": 0 + }, + "error": null, + "temperature": 1.0, + "max_completion_tokens": 2048, + "top_p": 1.0, + "seed": 42 + } + } + EvalRunOutputItemList: + type: object + title: EvalRunOutputItemList + description: | + An object representing a list of output items for an evaluation run. + properties: + object: + type: string + enum: + - list + default: list + description: | + The type of this object. It is always set to "list". + x-stainless-const: true + data: + type: array + description: | + An array of eval run output item objects. + items: + $ref: "#/components/schemas/EvalRunOutputItem" + first_id: + type: string + description: The identifier of the first eval run output item in the data array. + last_id: + type: string + description: The identifier of the last eval run output item in the data array. + has_more: + type: boolean + description: Indicates whether there are more eval run output items available. + required: + - object + - data + - first_id + - last_id + - has_more + x-oaiMeta: + name: The eval run output item list object + group: evals + example: > + { + "object": "list", + "data": [ + { + "object": "eval.run.output_item", + "id": "outputitem_67abd55eb6548190bb580745d5644a33", + "run_id": "evalrun_67abd54d60ec8190832b46859da808f7", + "eval_id": "eval_67abd54d9b0081909a86353f6fb9317a", + "created_at": 1739314509, + "status": "pass", + "datasource_item_id": 137, + "datasource_item": { + "teacher": "To grade essays, I only check for style, content, and grammar.", + "student": "I am a student who is trying to write the best essay." + }, + "results": [ + { + "name": "String Check Grader", + "type": "string-check-grader", + "score": 1.0, + "passed": true, + } + ], + "sample": { + "input": [ + { + "role": "system", + "content": "You are an evaluator bot..." + }, + { + "role": "user", + "content": "You are assessing..." + } + ], + "output": [ + { + "role": "assistant", + "content": "The rubric is not clear nor concise." + } + ], + "finish_reason": "stop", + "model": "gpt-4o-2024-08-06", + "usage": { + "total_tokens": 521, + "completion_tokens": 2, + "prompt_tokens": 519, + "cached_tokens": 0 + }, + "error": null, + "temperature": 1.0, + "max_completion_tokens": 2048, + "top_p": 1.0, + "seed": 42 + } + }, + ], + "first_id": "outputitem_67abd55eb6548190bb580745d5644a33", + "last_id": "outputitem_67abd55eb6548190bb580745d5644a33", + "has_more": false + } + EvalStoredCompletionsDataSourceConfig: + type: object + title: StoredCompletionsDataSourceConfig + description: | + Deprecated in favor of LogsDataSourceConfig. + properties: + type: + type: string + enum: + - stored_completions + default: stored_completions + description: The type of data source. Always `stored_completions`. + x-stainless-const: true + metadata: + $ref: "#/components/schemas/Metadata" + schema: + type: object + description: | + The json schema for the run data source items. + Learn how to build JSON schemas [here](https://json-schema.org/). + additionalProperties: true + required: + - type + - schema + deprecated: true + x-oaiMeta: + name: The stored completions data source object for evals + group: evals + example: | + { + "type": "stored_completions", + "metadata": { + "language": "english" + }, + "schema": { + "type": "object", + "properties": { + "item": { + "type": "object" + }, + "sample": { + "type": "object" + } + }, + "required": [ + "item", + "sample" + } + } + EvalStoredCompletionsSource: + type: object + title: StoredCompletionsRunDataSource + description: > + A StoredCompletionsRunDataSource configuration describing a set of + filters + properties: + type: + type: string + enum: + - stored_completions + default: stored_completions + description: The type of source. Always `stored_completions`. + x-stainless-const: true + metadata: + $ref: "#/components/schemas/Metadata" + model: + type: string + nullable: true + description: An optional model to filter by (e.g., 'gpt-4o'). + created_after: + type: integer + nullable: true + description: An optional Unix timestamp to filter items created after this time. + created_before: + type: integer + nullable: true + description: An optional Unix timestamp to filter items created before this time. + limit: + type: integer + nullable: true + description: An optional maximum number of items to return. + required: + - type + x-oaiMeta: + name: The stored completions data source object used to configure an individual + run + group: eval runs + example: | + { + "type": "stored_completions", + "model": "gpt-4o", + "created_after": 1668124800, + "created_before": 1668124900, + "limit": 100, + "metadata": {} + } + FilePath: + type: object + title: File path + description: | + A path to a file. + properties: + type: + type: string + description: | + The type of the file path. Always `file_path`. + enum: + - file_path + x-stainless-const: true + file_id: + type: string + description: | + The ID of the file. + index: + type: integer + description: | + The index of the file in the list of files. + required: + - type + - file_id + - index + FileSearchRanker: + type: string + description: The ranker to use for the file search. If not specified will use + the `auto` ranker. + enum: + - auto + - default_2024_08_21 + FileSearchRankingOptions: + title: File search tool call ranking options + type: object + description: | + The ranking options for the file search. If not specified, the file search tool will use the `auto` ranker and a score_threshold of 0. + + See the [file search tool documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) for more information. + properties: + ranker: + $ref: "#/components/schemas/FileSearchRanker" + score_threshold: + type: number + description: The score threshold for the file search. All values must be a + floating point number between 0 and 1. + minimum: 0 + maximum: 1 + required: + - score_threshold + FileSearchToolCall: + type: object + title: File search tool call + description: > + The results of a file search tool call. See the + + [file search guide](/docs/guides/tools-file-search) for more + information. + properties: + id: + type: string + description: | + The unique ID of the file search tool call. + type: + type: string + enum: + - file_search_call + description: | + The type of the file search tool call. Always `file_search_call`. + x-stainless-const: true + status: + type: string + description: | + The status of the file search tool call. One of `in_progress`, + `searching`, `incomplete` or `failed`, + enum: + - in_progress + - searching + - completed + - incomplete + - failed + queries: + type: array + items: + type: string + description: | + The queries used to search for files. + results: + type: array + description: | + The results of the file search tool call. + items: + type: object + properties: + file_id: + type: string + description: | + The unique ID of the file. + text: + type: string + description: | + The text that was retrieved from the file. + filename: + type: string + description: | + The name of the file. + attributes: + $ref: "#/components/schemas/VectorStoreFileAttributes" + score: + type: number + format: float + description: | + The relevance score of the file - a value between 0 and 1. + nullable: true + required: + - id + - type + - status + - queries + FineTuneChatCompletionRequestAssistantMessage: + allOf: + - type: object + title: Assistant message + deprecated: false + properties: + weight: + type: integer + enum: + - 0 + - 1 + description: Controls whether the assistant message is trained against (0 or 1) + - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" + required: + - role + FineTuneChatRequestInput: + type: object + description: The per-line training example of a fine-tuning input file for chat + models using the supervised method. + properties: + messages: + type: array + minItems: 1 + items: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage" + - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" + - $ref: "#/components/schemas/FineTuneChatCompletionRequestAssistantMessage" + - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" + - $ref: "#/components/schemas/ChatCompletionRequestFunctionMessage" + tools: + type: array + description: A list of tools the model may generate JSON inputs for. + items: + $ref: "#/components/schemas/ChatCompletionTool" + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + functions: + deprecated: true + description: A list of functions the model may generate JSON inputs for. + type: array + minItems: 1 + maxItems: 128 + items: + $ref: "#/components/schemas/ChatCompletionFunctions" + x-oaiMeta: + name: Training format for chat models using the supervised method + example: > + { + "messages": [ + { "role": "user", "content": "What is the weather in San Francisco?" }, + { + "role": "assistant", + "tool_calls": [ + { + "id": "call_id", + "type": "function", + "function": { + "name": "get_current_weather", + "arguments": "{\"location\": \"San Francisco, USA\", \"format\": \"celsius\"}" + } + } + ] + } + ], + "parallel_tool_calls": false, + "tools": [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather", + "parameters": { + "type": "object", + "properties": { + "location": { + "type": "string", + "description": "The city and country, eg. San Francisco, USA" + }, + "format": { "type": "string", "enum": ["celsius", "fahrenheit"] } + }, + "required": ["location", "format"] + } + } + } + ] + } + FineTuneDPOHyperparameters: + type: object + description: The hyperparameters used for the DPO fine-tuning job. + properties: + beta: + description: > + The beta value for the DPO method. A higher beta value will increase + the weight of the penalty between the policy and reference model. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: number + minimum: 0 + maximum: 2 + exclusiveMinimum: true + default: auto + batch_size: + description: > + Number of examples in each batch. A larger batch size means that + model parameters are updated less frequently, but with lower + variance. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + maximum: 256 + default: auto + learning_rate_multiplier: + description: > + Scaling factor for the learning rate. A smaller learning rate may be + useful to avoid overfitting. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: number + minimum: 0 + exclusiveMinimum: true + default: auto + n_epochs: + description: > + The number of epochs to train the model for. An epoch refers to one + full cycle through the training dataset. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + maximum: 50 + default: auto + FineTuneDPOMethod: + type: object + description: Configuration for the DPO fine-tuning method. + properties: + hyperparameters: + $ref: "#/components/schemas/FineTuneDPOHyperparameters" + FineTuneMethod: + type: object + description: The method used for fine-tuning. + properties: + type: + type: string + description: The type of method. Is either `supervised`, `dpo`, or + `reinforcement`. + enum: + - supervised + - dpo + - reinforcement + supervised: + $ref: "#/components/schemas/FineTuneSupervisedMethod" + dpo: + $ref: "#/components/schemas/FineTuneDPOMethod" + reinforcement: + $ref: "#/components/schemas/FineTuneReinforcementMethod" + required: + - type + FineTunePreferenceRequestInput: + type: object + description: The per-line training example of a fine-tuning input file for chat + models using the dpo method. + properties: + input: + type: object + properties: + messages: + type: array + minItems: 1 + items: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestSystemMessage" + - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" + - $ref: "#/components/schemas/FineTuneChatCompletionRequestAssistantMessage" + - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" + - $ref: "#/components/schemas/ChatCompletionRequestFunctionMessage" + tools: + type: array + description: A list of tools the model may generate JSON inputs for. + items: + $ref: "#/components/schemas/ChatCompletionTool" + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + preferred_output: + type: array + description: The preferred completion message for the output. + maxItems: 1 + items: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" + non_preferred_output: + type: array + description: The non-preferred completion message for the output. + maxItems: 1 + items: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestAssistantMessage" + x-oaiMeta: + name: Training format for chat models using the preference method + example: > + { + "input": { + "messages": [ + { "role": "user", "content": "What is the weather in San Francisco?" } + ] + }, + "preferred_output": [ + { + "role": "assistant", + "content": "The weather in San Francisco is 70 degrees Fahrenheit." + } + ], + "non_preferred_output": [ + { + "role": "assistant", + "content": "The weather in San Francisco is 21 degrees Celsius." + } + ] + } + FineTuneReinforcementHyperparameters: + type: object + description: The hyperparameters used for the reinforcement fine-tuning job. + properties: + batch_size: + description: > + Number of examples in each batch. A larger batch size means that + model parameters are updated less frequently, but with lower + variance. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + maximum: 256 + default: auto + learning_rate_multiplier: + description: > + Scaling factor for the learning rate. A smaller learning rate may be + useful to avoid overfitting. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: number + minimum: 0 + exclusiveMinimum: true + default: auto + n_epochs: + description: > + The number of epochs to train the model for. An epoch refers to one + full cycle through the training dataset. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + maximum: 50 + default: auto + reasoning_effort: + description: | + Level of reasoning effort. + type: string + enum: + - default + - low + - medium + - high + default: default + compute_multiplier: + description: > + Multiplier on amount of compute used for exploring search space + during training. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: number + minimum: 0.00001 + maximum: 10 + exclusiveMinimum: true + default: auto + eval_interval: + description: | + The number of training steps between evaluation runs. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + default: auto + eval_samples: + description: | + Number of evaluation samples to generate per training step. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + default: auto + FineTuneReinforcementMethod: + type: object + description: Configuration for the reinforcement fine-tuning method. + properties: + grader: + type: object + description: The grader used for the fine-tuning job. + oneOf: + - $ref: "#/components/schemas/GraderStringCheck" + - $ref: "#/components/schemas/GraderTextSimilarity" + - $ref: "#/components/schemas/GraderPython" + - $ref: "#/components/schemas/GraderScoreModel" + - $ref: "#/components/schemas/GraderMulti" + hyperparameters: + $ref: "#/components/schemas/FineTuneReinforcementHyperparameters" + required: + - grader + FineTuneReinforcementRequestInput: + type: object + unevaluatedProperties: true + description: Per-line training example for reinforcement fine-tuning. Note that + `messages` and `tools` are the only reserved keywords. Any other + arbitrary key-value data can be included on training datapoints and will + be available to reference during grading under the `{{ item.XXX }}` + template variable. + required: + - messages + properties: + messages: + type: array + minItems: 1 + items: + oneOf: + - $ref: "#/components/schemas/ChatCompletionRequestDeveloperMessage" + - $ref: "#/components/schemas/ChatCompletionRequestUserMessage" + - $ref: "#/components/schemas/FineTuneChatCompletionRequestAssistantMessage" + - $ref: "#/components/schemas/ChatCompletionRequestToolMessage" + tools: + type: array + description: A list of tools the model may generate JSON inputs for. + items: + $ref: "#/components/schemas/ChatCompletionTool" + x-oaiMeta: + name: Training format for reasoning models using the reinforcement method + example: > + { + "messages": [ + { + "role": "user", + "content": "Your task is to take a chemical in SMILES format and predict the number of hydrobond bond donors and acceptors according to Lipinkski's rule. CCN(CC)CCC(=O)c1sc(N)nc1C" + }, + ], + # Any other JSON data can be inserted into an example and referenced during RFT grading + "reference_answer": { + "donor_bond_counts": 5, + "acceptor_bond_counts": 7 + } + } + FineTuneSupervisedHyperparameters: + type: object + description: The hyperparameters used for the fine-tuning job. + properties: + batch_size: + description: > + Number of examples in each batch. A larger batch size means that + model parameters are updated less frequently, but with lower + variance. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + maximum: 256 + default: auto + learning_rate_multiplier: + description: > + Scaling factor for the learning rate. A smaller learning rate may be + useful to avoid overfitting. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: number + minimum: 0 + exclusiveMinimum: true + default: auto + n_epochs: + description: > + The number of epochs to train the model for. An epoch refers to one + full cycle through the training dataset. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + maximum: 50 + default: auto + FineTuneSupervisedMethod: + type: object + description: Configuration for the supervised fine-tuning method. + properties: + hyperparameters: + $ref: "#/components/schemas/FineTuneSupervisedHyperparameters" + FineTuningCheckpointPermission: + type: object + title: FineTuningCheckpointPermission + description: > + The `checkpoint.permission` object represents a permission for a + fine-tuned model checkpoint. + properties: + id: + type: string + description: The permission identifier, which can be referenced in the API + endpoints. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the permission was created. + project_id: + type: string + description: The project identifier that the permission is for. + object: + type: string + description: The object type, which is always "checkpoint.permission". + enum: + - checkpoint.permission + x-stainless-const: true + required: + - created_at + - id + - object + - project_id + x-oaiMeta: + name: The fine-tuned model checkpoint permission object + example: | + { + "object": "checkpoint.permission", + "id": "cp_zc4Q7MP6XxulcVzj4MZdwsAB", + "created_at": 1712211699, + "project_id": "proj_abGMw1llN8IrBb6SvvY5A1iH" + } + FineTuningIntegration: + type: object + title: Fine-Tuning Job Integration + required: + - type + - wandb + properties: + type: + type: string + description: The type of the integration being enabled for the fine-tuning job + enum: + - wandb + x-stainless-const: true + wandb: + type: object + description: > + The settings for your integration with Weights and Biases. This + payload specifies the project that + + metrics will be sent to. Optionally, you can set an explicit display + name for your run, add tags + + to your run, and set a default entity (team, username, etc) to be + associated with your run. + required: + - project + properties: + project: + description: | + The name of the project that the new run will be created under. + type: string + example: my-wandb-project + name: + description: > + A display name to set for the run. If not set, we will use the + Job ID as the name. + nullable: true + type: string + entity: + description: > + The entity to use for the run. This allows you to set the team + or username of the WandB user that you would + + like associated with the run. If not set, the default entity for + the registered WandB API key is used. + nullable: true + type: string + tags: + description: > + A list of tags to be attached to the newly created run. These + tags are passed through directly to WandB. Some + + default tags are generated by OpenAI: "openai/finetune", + "openai/{base-model}", "openai/{ftjob-abcdef}". + type: array + items: + type: string + example: custom-tag + FineTuningJob: + type: object + title: FineTuningJob + description: > + The `fine_tuning.job` object represents a fine-tuning job that has been + created through the API. + properties: + id: + type: string + description: The object identifier, which can be referenced in the API endpoints. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the fine-tuning job was + created. + error: + type: object + nullable: true + description: For fine-tuning jobs that have `failed`, this will contain more + information on the cause of the failure. + properties: + code: + type: string + description: A machine-readable error code. + message: + type: string + description: A human-readable error message. + param: + type: string + description: The parameter that was invalid, usually `training_file` or + `validation_file`. This field will be null if the failure was + not parameter-specific. + nullable: true + required: + - code + - message + - param + fine_tuned_model: + type: string + nullable: true + description: The name of the fine-tuned model that is being created. The value + will be null if the fine-tuning job is still running. + finished_at: + type: integer + nullable: true + description: The Unix timestamp (in seconds) for when the fine-tuning job was + finished. The value will be null if the fine-tuning job is still + running. + hyperparameters: + type: object + description: The hyperparameters used for the fine-tuning job. This value will + only be returned when running `supervised` jobs. + properties: + batch_size: + nullable: true + description: > + Number of examples in each batch. A larger batch size means that + model parameters + + are updated less frequently, but with lower variance. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + maximum: 256 + default: auto + learning_rate_multiplier: + description: > + Scaling factor for the learning rate. A smaller learning rate + may be useful to avoid + + overfitting. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: number + minimum: 0 + exclusiveMinimum: true + default: auto + n_epochs: + description: > + The number of epochs to train the model for. An epoch refers to + one full cycle + + through the training dataset. + oneOf: + - type: string + enum: + - auto + x-stainless-const: true + - type: integer + minimum: 1 + maximum: 50 + default: auto + model: + type: string + description: The base model that is being fine-tuned. + object: + type: string + description: The object type, which is always "fine_tuning.job". + enum: + - fine_tuning.job + x-stainless-const: true + organization_id: + type: string + description: The organization that owns the fine-tuning job. + result_files: + type: array + description: The compiled results file ID(s) for the fine-tuning job. You can + retrieve the results with the [Files + API](/docs/api-reference/files/retrieve-contents). + items: + type: string + example: file-abc123 + status: + type: string + description: The current status of the fine-tuning job, which can be either + `validating_files`, `queued`, `running`, `succeeded`, `failed`, or + `cancelled`. + enum: + - validating_files + - queued + - running + - succeeded + - failed + - cancelled + trained_tokens: + type: integer + nullable: true + description: The total number of billable tokens processed by this fine-tuning + job. The value will be null if the fine-tuning job is still running. + training_file: + type: string + description: The file ID used for training. You can retrieve the training data + with the [Files API](/docs/api-reference/files/retrieve-contents). + validation_file: + type: string + nullable: true + description: The file ID used for validation. You can retrieve the validation + results with the [Files + API](/docs/api-reference/files/retrieve-contents). + integrations: + type: array + nullable: true + description: A list of integrations to enable for this fine-tuning job. + maxItems: 5 + items: + oneOf: + - $ref: "#/components/schemas/FineTuningIntegration" + seed: + type: integer + description: The seed used for the fine-tuning job. + estimated_finish: + type: integer + nullable: true + description: The Unix timestamp (in seconds) for when the fine-tuning job is + estimated to finish. The value will be null if the fine-tuning job + is not running. + method: + $ref: "#/components/schemas/FineTuneMethod" + metadata: + $ref: "#/components/schemas/Metadata" + required: + - created_at + - error + - finished_at + - fine_tuned_model + - hyperparameters + - id + - model + - object + - organization_id + - result_files + - status + - trained_tokens + - training_file + - validation_file + - seed + x-oaiMeta: + name: The fine-tuning job object + example: | + { + "object": "fine_tuning.job", + "id": "ftjob-abc123", + "model": "davinci-002", + "created_at": 1692661014, + "finished_at": 1692661190, + "fine_tuned_model": "ft:davinci-002:my-org:custom_suffix:7q8mpxmy", + "organization_id": "org-123", + "result_files": [ + "file-abc123" + ], + "status": "succeeded", + "validation_file": null, + "training_file": "file-abc123", + "hyperparameters": { + "n_epochs": 4, + "batch_size": 1, + "learning_rate_multiplier": 1.0 + }, + "trained_tokens": 5768, + "integrations": [], + "seed": 0, + "estimated_finish": 0, + "method": { + "type": "supervised", + "supervised": { + "hyperparameters": { + "n_epochs": 4, + "batch_size": 1, + "learning_rate_multiplier": 1.0 + } + } + }, + "metadata": { + "key": "value" + } + } + FineTuningJobCheckpoint: + type: object + title: FineTuningJobCheckpoint + description: > + The `fine_tuning.job.checkpoint` object represents a model checkpoint + for a fine-tuning job that is ready to use. + properties: + id: + type: string + description: The checkpoint identifier, which can be referenced in the API + endpoints. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the checkpoint was created. + fine_tuned_model_checkpoint: + type: string + description: The name of the fine-tuned checkpoint model that is created. + step_number: + type: integer + description: The step number that the checkpoint was created at. + metrics: + type: object + description: Metrics at the step number during the fine-tuning job. + properties: + step: + type: number + train_loss: + type: number + train_mean_token_accuracy: + type: number + valid_loss: + type: number + valid_mean_token_accuracy: + type: number + full_valid_loss: + type: number + full_valid_mean_token_accuracy: + type: number + fine_tuning_job_id: + type: string + description: The name of the fine-tuning job that this checkpoint was created + from. + object: + type: string + description: The object type, which is always "fine_tuning.job.checkpoint". + enum: + - fine_tuning.job.checkpoint + x-stainless-const: true + required: + - created_at + - fine_tuning_job_id + - fine_tuned_model_checkpoint + - id + - metrics + - object + - step_number + x-oaiMeta: + name: The fine-tuning job checkpoint object + example: > + { + "object": "fine_tuning.job.checkpoint", + "id": "ftckpt_qtZ5Gyk4BLq1SfLFWp3RtO3P", + "created_at": 1712211699, + "fine_tuned_model_checkpoint": "ft:gpt-4o-mini-2024-07-18:my-org:custom_suffix:9ABel2dg:ckpt-step-88", + "fine_tuning_job_id": "ftjob-fpbNQ3H1GrMehXRf8cO97xTN", + "metrics": { + "step": 88, + "train_loss": 0.478, + "train_mean_token_accuracy": 0.924, + "valid_loss": 10.112, + "valid_mean_token_accuracy": 0.145, + "full_valid_loss": 0.567, + "full_valid_mean_token_accuracy": 0.944 + }, + "step_number": 88 + } + FineTuningJobEvent: + type: object + description: Fine-tuning job event object + properties: + object: + type: string + description: The object type, which is always "fine_tuning.job.event". + enum: + - fine_tuning.job.event + x-stainless-const: true + id: + type: string + description: The object identifier. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the fine-tuning job was + created. + level: + type: string + description: The log level of the event. + enum: + - info + - warn + - error + message: + type: string + description: The message of the event. + type: + type: string + description: The type of event. + enum: + - message + - metrics + data: + type: object + description: The data associated with the event. + required: + - id + - object + - created_at + - level + - message + x-oaiMeta: + name: The fine-tuning job event object + example: | + { + "object": "fine_tuning.job.event", + "id": "ftevent-abc123" + "created_at": 1677610602, + "level": "info", + "message": "Created fine-tuning job", + "data": {}, + "type": "message" + } + FunctionObject: + type: object + properties: + description: + type: string + description: A description of what the function does, used by the model to + choose when and how to call the function. + name: + type: string + description: The name of the function to be called. Must be a-z, A-Z, 0-9, or + contain underscores and dashes, with a maximum length of 64. + parameters: + $ref: "#/components/schemas/FunctionParameters" + strict: + type: boolean + nullable: true + default: false + description: Whether to enable strict schema adherence when generating the + function call. If set to true, the model will follow the exact + schema defined in the `parameters` field. Only a subset of JSON + Schema is supported when `strict` is `true`. Learn more about + Structured Outputs in the [function calling + guide](docs/guides/function-calling). + required: + - name + FunctionParameters: + type: object + description: >- + The parameters the functions accepts, described as a JSON Schema object. + See the [guide](/docs/guides/function-calling) for examples, and the + [JSON Schema + reference](https://json-schema.org/understanding-json-schema/) for + documentation about the format. + + + Omitting `parameters` defines a function with an empty parameter list. + additionalProperties: true + FunctionToolCall: + type: object + title: Function tool call + description: > + A tool call to run a function. See the + + [function calling guide](/docs/guides/function-calling) for more + information. + properties: + id: + type: string + description: | + The unique ID of the function tool call. + type: + type: string + enum: + - function_call + description: | + The type of the function tool call. Always `function_call`. + x-stainless-const: true + call_id: + type: string + description: | + The unique ID of the function tool call generated by the model. + name: + type: string + description: | + The name of the function to run. + arguments: + type: string + description: | + A JSON string of the arguments to pass to the function. + status: + type: string + description: | + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + enum: + - in_progress + - completed + - incomplete + required: + - type + - call_id + - name + - arguments + FunctionToolCallOutput: + type: object + title: Function tool call output + description: | + The output of a function tool call. + properties: + id: + type: string + description: > + The unique ID of the function tool call output. Populated when this + item + + is returned via API. + type: + type: string + enum: + - function_call_output + description: > + The type of the function tool call output. Always + `function_call_output`. + x-stainless-const: true + call_id: + type: string + description: | + The unique ID of the function tool call generated by the model. + output: + type: string + description: | + A JSON string of the output of the function tool call. + status: + type: string + description: | + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + enum: + - in_progress + - completed + - incomplete + required: + - type + - call_id + - output + FunctionToolCallOutputResource: + allOf: + - $ref: "#/components/schemas/FunctionToolCallOutput" + - type: object + properties: + id: + type: string + description: | + The unique ID of the function call tool output. + required: + - id + FunctionToolCallResource: + allOf: + - $ref: "#/components/schemas/FunctionToolCall" + - type: object + properties: + id: + type: string + description: | + The unique ID of the function tool call. + required: + - id + GraderLabelModel: + type: object + title: LabelModelGrader + description: > + A LabelModelGrader object which uses a model to assign labels to each + item + + in the evaluation. + properties: + type: + description: The object type, which is always `label_model`. + type: string + enum: + - label_model + x-stainless-const: true + name: + type: string + description: The name of the grader. + model: + type: string + description: The model to use for the evaluation. Must support structured outputs. + input: + type: array + items: + $ref: "#/components/schemas/EvalItem" + labels: + type: array + items: + type: string + description: The labels to assign to each item in the evaluation. + passing_labels: + type: array + items: + type: string + description: The labels that indicate a passing result. Must be a subset of + labels. + required: + - type + - model + - input + - passing_labels + - labels + - name + x-oaiMeta: + name: Label Model Grader + group: graders + example: > + { + "name": "First label grader", + "type": "label_model", + "model": "gpt-4o-2024-08-06", + "input": [ + { + "type": "message", + "role": "system", + "content": { + "type": "input_text", + "text": "Classify the sentiment of the following statement as one of positive, neutral, or negative" + } + }, + { + "type": "message", + "role": "user", + "content": { + "type": "input_text", + "text": "Statement: {{item.response}}" + } + } + ], + "passing_labels": [ + "positive" + ], + "labels": [ + "positive", + "neutral", + "negative" + ] + } + GraderMulti: + type: object + title: MultiGrader + description: A MultiGrader object combines the output of multiple graders to + produce a single score. + properties: + type: + type: string + enum: + - multi + default: multi + description: The object type, which is always `multi`. + x-stainless-const: true + name: + type: string + description: The name of the grader. + graders: + oneOf: + - $ref: "#/components/schemas/GraderStringCheck" + - $ref: "#/components/schemas/GraderTextSimilarity" + - $ref: "#/components/schemas/GraderPython" + - $ref: "#/components/schemas/GraderScoreModel" + - $ref: "#/components/schemas/GraderLabelModel" + calculate_output: + type: string + description: A formula to calculate the output based on grader results. + required: + - name + - type + - graders + - calculate_output + x-oaiMeta: + name: Multi Grader + group: graders + example: > + { + "type": "multi", + "name": "example multi grader", + "graders": [ + { + "type": "text_similarity", + "name": "example text similarity grader", + "input": "The graded text", + "reference": "The reference text", + "evaluation_metric": "fuzzy_match" + }, + { + "type": "string_check", + "name": "Example string check grader", + "input": "{{sample.output_text}}", + "reference": "{{item.label}}", + "operation": "eq" + } + ], + "calculate_output": "0.5 * text_similarity_score + 0.5 * string_check_score)" + } + GraderPython: + type: object + title: PythonGrader + description: | + A PythonGrader object that runs a python script on the input. + properties: + type: + type: string + enum: + - python + description: The object type, which is always `python`. + x-stainless-const: true + name: + type: string + description: The name of the grader. + source: + type: string + description: The source code of the python script. + image_tag: + type: string + description: The image tag to use for the python script. + required: + - type + - name + - source + x-oaiMeta: + name: Python Grader + group: graders + example: | + { + "type": "python", + "name": "Example python grader", + "image_tag": "2025-05-08", + "source": """ + def grade(sample: dict, item: dict) -> float: + \""" + Returns 1.0 if `output_text` equals `label`, otherwise 0.0. + \""" + output = sample.get("output_text") + label = item.get("label") + return 1.0 if output == label else 0.0 + """, + } + GraderScoreModel: + type: object + title: ScoreModelGrader + description: > + A ScoreModelGrader object that uses a model to assign a score to the + input. + properties: + type: + type: string + enum: + - score_model + description: The object type, which is always `score_model`. + x-stainless-const: true + name: + type: string + description: The name of the grader. + model: + type: string + description: The model to use for the evaluation. + sampling_params: + type: object + description: The sampling parameters for the model. + input: + type: array + items: + $ref: "#/components/schemas/EvalItem" + description: The input text. This may include template strings. + range: + type: array + items: + type: number + min_items: 2 + max_items: 2 + description: The range of the score. Defaults to `[0, 1]`. + required: + - type + - name + - input + - model + x-oaiMeta: + name: Score Model Grader + group: graders + example: > + { + "type": "score_model", + "name": "Example score model grader", + "input": [ + { + "role": "user", + "content": ( + "Score how close the reference answer is to the model answer. Score 1.0 if they are the same and 0.0 if they are different." + " Return just a floating point score\n\n" + " Reference answer: {{item.label}}\n\n" + " Model answer: {{sample.output_text}}" + ), + } + ], + "model": "gpt-4o-2024-08-06", + "sampling_params": { + "temperature": 1, + "top_p": 1, + "seed": 42, + }, + } + GraderStringCheck: + type: object + title: StringCheckGrader + description: > + A StringCheckGrader object that performs a string comparison between + input and reference using a specified operation. + properties: + type: + type: string + enum: + - string_check + description: The object type, which is always `string_check`. + x-stainless-const: true + name: + type: string + description: The name of the grader. + input: + type: string + description: The input text. This may include template strings. + reference: + type: string + description: The reference text. This may include template strings. + operation: + type: string + enum: + - eq + - ne + - like + - ilike + description: The string check operation to perform. One of `eq`, `ne`, `like`, + or `ilike`. + required: + - type + - name + - input + - reference + - operation + x-oaiMeta: + name: String Check Grader + group: graders + example: | + { + "type": "string_check", + "name": "Example string check grader", + "input": "{{sample.output_text}}", + "reference": "{{item.label}}", + "operation": "eq" + } + GraderTextSimilarity: + type: object + title: TextSimilarityGrader + description: > + A TextSimilarityGrader object which grades text based on similarity + metrics. + properties: + type: + type: string + enum: + - text_similarity + default: text_similarity + description: The type of grader. + x-stainless-const: true + name: + type: string + description: The name of the grader. + input: + type: string + description: The text being graded. + reference: + type: string + description: The text being graded against. + evaluation_metric: + type: string + enum: + - fuzzy_match + - bleu + - gleu + - meteor + - rouge_1 + - rouge_2 + - rouge_3 + - rouge_4 + - rouge_5 + - rouge_l + description: The evaluation metric to use. One of `fuzzy_match`, `bleu`, `gleu`, + `meteor`, `rouge_1`, `rouge_2`, `rouge_3`, `rouge_4`, `rouge_5`, or + `rouge_l`. + required: + - type + - name + - input + - reference + - evaluation_metric + x-oaiMeta: + name: Text Similarity Grader + group: graders + example: | + { + "type": "text_similarity", + "name": "Example text similarity grader", + "input": "{{sample.output_text}}", + "reference": "{{item.label}}", + "evaluation_metric": "fuzzy_match" + } + Image: + type: object + description: Represents the content or the URL of an image generated by the + OpenAI API. + properties: + b64_json: + type: string + description: The base64-encoded JSON of the generated image. Default value for + `gpt-image-1`, and only present if `response_format` is set to + `b64_json` for `dall-e-2` and `dall-e-3`. + url: + type: string + description: When using `dall-e-2` or `dall-e-3`, the URL of the generated image + if `response_format` is set to `url` (default value). Unsupported + for `gpt-image-1`. + revised_prompt: + type: string + description: For `dall-e-3` only, the revised prompt that was used to generate + the image. + ImageGenTool: + type: object + title: Image generation tool + description: | + A tool that generates images using a model like `gpt-image-1`. + properties: + type: + type: string + enum: + - image_generation + description: | + The type of the image generation tool. Always `image_generation`. + x-stainless-const: true + model: + type: string + enum: + - gpt-image-1 + description: | + The image generation model to use. Default: `gpt-image-1`. + default: gpt-image-1 + quality: + type: string + enum: + - low + - medium + - high + - auto + description: | + The quality of the generated image. One of `low`, `medium`, `high`, + or `auto`. Default: `auto`. + default: auto + size: + type: string + enum: + - 1024x1024 + - 1024x1536 + - 1536x1024 + - auto + description: | + The size of the generated image. One of `1024x1024`, `1024x1536`, + `1536x1024`, or `auto`. Default: `auto`. + default: auto + output_format: + type: string + enum: + - png + - webp + - jpeg + description: | + The output format of the generated image. One of `png`, `webp`, or + `jpeg`. Default: `png`. + default: png + output_compression: + type: integer + minimum: 0 + maximum: 100 + description: | + Compression level for the output image. Default: 100. + default: 100 + moderation: + type: string + enum: + - auto + - low + description: | + Moderation level for the generated image. Default: `auto`. + default: auto + background: + type: string + enum: + - transparent + - opaque + - auto + description: | + Background type for the generated image. One of `transparent`, + `opaque`, or `auto`. Default: `auto`. + default: auto + input_image_mask: + type: object + description: | + Optional mask for inpainting. Contains `image_url` + (string, optional) and `file_id` (string, optional). + properties: + image_url: + type: string + description: | + Base64-encoded mask image. + file_id: + type: string + description: | + File ID for the mask image. + required: [] + additionalProperties: false + partial_images: + type: integer + minimum: 0 + maximum: 3 + description: > + Number of partial images to generate in streaming mode, from 0 + (default value) to 3. + default: 0 + required: + - type + ImageGenToolCall: + type: object + title: Image generation call + description: | + An image generation request made by the model. + properties: + type: + type: string + enum: + - image_generation_call + description: > + The type of the image generation call. Always + `image_generation_call`. + x-stainless-const: true + id: + type: string + description: | + The unique ID of the image generation call. + status: + type: string + enum: + - in_progress + - completed + - generating + - failed + description: | + The status of the image generation call. + result: + type: string + description: | + The generated image encoded in base64. + nullable: true + required: + - type + - id + - status + - result + ImagesResponse: + type: object + title: Image generation response + description: The response from the image generation endpoint. + properties: + created: + type: integer + description: The Unix timestamp (in seconds) of when the image was created. + data: + type: array + description: The list of generated images. + items: + $ref: "#/components/schemas/Image" + usage: + type: object + description: > + For `gpt-image-1` only, the token usage information for the image + generation. + required: + - total_tokens + - input_tokens + - output_tokens + - input_tokens_details + properties: + total_tokens: + type: integer + description: The total number of tokens (images and text) used for the image + generation. + input_tokens: + type: integer + description: The number of tokens (images and text) in the input prompt. + output_tokens: + type: integer + description: The number of image tokens in the output image. + input_tokens_details: + type: object + description: The input tokens detailed information for the image generation. + required: + - text_tokens + - image_tokens + properties: + text_tokens: + type: integer + description: The number of text tokens in the input prompt. + image_tokens: + type: integer + description: The number of image tokens in the input prompt. + required: + - created + x-oaiMeta: + name: The image generation response + group: images + example: | + { + "created": 1713833628, + "data": [ + { + "b64_json": "..." + } + ], + "usage": { + "total_tokens": 100, + "input_tokens": 50, + "output_tokens": 50, + "input_tokens_details": { + "text_tokens": 10, + "image_tokens": 40 + } + } + } + Includable: + type: string + description: > + Specify additional output data to include in the model response. + Currently + + supported values are: + + - `file_search_call.results`: Include the search results of + the file search tool call. + - `message.input_image.image_url`: Include image urls from the input + message. + + - `computer_call_output.output.image_url`: Include image urls from the + computer call output. + + - `reasoning.encrypted_content`: Includes an encrypted version of + reasoning + tokens in reasoning item outputs. This enables reasoning items to be used in + multi-turn conversations when using the Responses API statelessly (like + when the `store` parameter is set to `false`, or when an organization is + enrolled in the zero data retention program). + - `code_interpreter_call.outputs`: Includes the outputs of python code + execution + in code interpreter tool call items. + enum: + - file_search_call.results + - message.input_image.image_url + - computer_call_output.output.image_url + - reasoning.encrypted_content + - code_interpreter_call.outputs + InputAudio: + type: object + title: Audio input + description: | + An audio input to the model. + properties: + type: + type: string + description: | + The type of the input item. Always `input_audio`. + enum: + - input_audio + x-stainless-const: true + data: + type: string + description: | + Base64-encoded audio data. + format: + type: string + description: > + The format of the audio data. Currently supported formats are `mp3` + and + + `wav`. + enum: + - mp3 + - wav + required: + - type + - data + - format + InputContent: + oneOf: + - $ref: "#/components/schemas/InputTextContent" + - $ref: "#/components/schemas/InputImageContent" + - $ref: "#/components/schemas/InputFileContent" + InputItem: + oneOf: + - $ref: "#/components/schemas/EasyInputMessage" + - type: object + title: Item + description: | + An item representing part of the context for the response to be + generated by the model. Can contain text, images, and audio inputs, + as well as previous assistant responses and tool call outputs. + $ref: "#/components/schemas/Item" + - $ref: "#/components/schemas/ItemReferenceParam" + discriminator: + propertyName: type + InputMessage: + type: object + title: Input message + description: > + A message input to the model with a role indicating instruction + following + + hierarchy. Instructions given with the `developer` or `system` role take + + precedence over instructions given with the `user` role. + properties: + type: + type: string + description: | + The type of the message input. Always set to `message`. + enum: + - message + x-stainless-const: true + role: + type: string + description: > + The role of the message input. One of `user`, `system`, or + `developer`. + enum: + - user + - system + - developer + status: + type: string + description: | + The status of item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + enum: + - in_progress + - completed + - incomplete + content: + $ref: "#/components/schemas/InputMessageContentList" + required: + - role + - content + InputMessageContentList: + type: array + title: Input item content list + description: > + A list of one or many input items to the model, containing different + content + + types. + items: + $ref: "#/components/schemas/InputContent" + InputMessageResource: + allOf: + - $ref: "#/components/schemas/InputMessage" + - type: object + properties: + id: + type: string + description: | + The unique ID of the message input. + required: + - id + Invite: + type: object + description: Represents an individual `invite` to the organization. + properties: + object: + type: string + enum: + - organization.invite + description: The object type, which is always `organization.invite` + x-stainless-const: true + id: + type: string + description: The identifier, which can be referenced in API endpoints + email: + type: string + description: The email address of the individual to whom the invite was sent + role: + type: string + enum: + - owner + - reader + description: "`owner` or `reader`" + status: + type: string + enum: + - accepted + - expired + - pending + description: "`accepted`,`expired`, or `pending`" + invited_at: + type: integer + description: The Unix timestamp (in seconds) of when the invite was sent. + expires_at: + type: integer + description: The Unix timestamp (in seconds) of when the invite expires. + accepted_at: + type: integer + description: The Unix timestamp (in seconds) of when the invite was accepted. + projects: + type: array + description: The projects that were granted membership upon acceptance of the + invite. + items: + type: object + properties: + id: + type: string + description: Project's public ID + role: + type: string + enum: + - member + - owner + description: Project membership role + required: + - object + - id + - email + - role + - status + - invited_at + - expires_at + x-oaiMeta: + name: The invite object + example: | + { + "object": "organization.invite", + "id": "invite-abc", + "email": "user@example.com", + "role": "owner", + "status": "accepted", + "invited_at": 1711471533, + "expires_at": 1711471533, + "accepted_at": 1711471533, + "projects": [ + { + "id": "project-xyz", + "role": "member" + } + ] + } + InviteDeleteResponse: + type: object + properties: + object: + type: string + enum: + - organization.invite.deleted + description: The object type, which is always `organization.invite.deleted` + x-stainless-const: true + id: + type: string + deleted: + type: boolean + required: + - object + - id + - deleted + InviteListResponse: + type: object + properties: + object: + type: string + enum: + - list + description: The object type, which is always `list` + x-stainless-const: true + data: + type: array + items: + $ref: "#/components/schemas/Invite" + first_id: + type: string + description: The first `invite_id` in the retrieved `list` + last_id: + type: string + description: The last `invite_id` in the retrieved `list` + has_more: + type: boolean + description: The `has_more` property is used for pagination to indicate there + are additional results. + required: + - object + - data + InviteRequest: + type: object + properties: + email: + type: string + description: Send an email to this address + role: + type: string + enum: + - reader + - owner + description: "`owner` or `reader`" + projects: + type: array + description: An array of projects to which membership is granted at the same + time the org invite is accepted. If omitted, the user will be + invited to the default project for compatibility with legacy + behavior. + items: + type: object + properties: + id: + type: string + description: Project's public ID + role: + type: string + enum: + - member + - owner + description: Project membership role + required: + - id + - role + required: + - email + - role + Item: + type: object + description: | + Content item used to generate a response. + oneOf: + - $ref: "#/components/schemas/InputMessage" + - $ref: "#/components/schemas/OutputMessage" + - $ref: "#/components/schemas/FileSearchToolCall" + - $ref: "#/components/schemas/ComputerToolCall" + - $ref: "#/components/schemas/ComputerCallOutputItemParam" + - $ref: "#/components/schemas/WebSearchToolCall" + - $ref: "#/components/schemas/FunctionToolCall" + - $ref: "#/components/schemas/FunctionCallOutputItemParam" + - $ref: "#/components/schemas/ReasoningItem" + - $ref: "#/components/schemas/ImageGenToolCall" + - $ref: "#/components/schemas/CodeInterpreterToolCall" + - $ref: "#/components/schemas/LocalShellToolCall" + - $ref: "#/components/schemas/LocalShellToolCallOutput" + - $ref: "#/components/schemas/MCPListTools" + - $ref: "#/components/schemas/MCPApprovalRequest" + - $ref: "#/components/schemas/MCPApprovalResponse" + - $ref: "#/components/schemas/MCPToolCall" + discriminator: + propertyName: type + ItemResource: + description: | + Content item used to generate a response. + oneOf: + - $ref: "#/components/schemas/InputMessageResource" + - $ref: "#/components/schemas/OutputMessage" + - $ref: "#/components/schemas/FileSearchToolCall" + - $ref: "#/components/schemas/ComputerToolCall" + - $ref: "#/components/schemas/ComputerToolCallOutputResource" + - $ref: "#/components/schemas/WebSearchToolCall" + - $ref: "#/components/schemas/FunctionToolCallResource" + - $ref: "#/components/schemas/FunctionToolCallOutputResource" + - $ref: "#/components/schemas/ImageGenToolCall" + - $ref: "#/components/schemas/CodeInterpreterToolCall" + - $ref: "#/components/schemas/LocalShellToolCall" + - $ref: "#/components/schemas/LocalShellToolCallOutput" + - $ref: "#/components/schemas/MCPListTools" + - $ref: "#/components/schemas/MCPApprovalRequest" + - $ref: "#/components/schemas/MCPApprovalResponseResource" + - $ref: "#/components/schemas/MCPToolCall" + discriminator: + propertyName: type + KeyPress: + type: object + title: KeyPress + description: | + A collection of keypresses the model would like to perform. + properties: + type: + type: string + enum: + - keypress + default: keypress + description: | + Specifies the event type. For a keypress action, this property is + always set to `keypress`. + x-stainless-const: true + keys: + type: array + items: + type: string + description: | + One of the keys the model is requesting to be pressed. + description: > + The combination of keys the model is requesting to be pressed. This + is an + + array of strings, each representing a key. + required: + - type + - keys + ListAssistantsResponse: + type: object + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/AssistantObject" + first_id: + type: string + example: asst_abc123 + last_id: + type: string + example: asst_abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + x-oaiMeta: + name: List assistants response object + group: chat + example: > + { + "object": "list", + "data": [ + { + "id": "asst_abc123", + "object": "assistant", + "created_at": 1698982736, + "name": "Coding Tutor", + "description": null, + "model": "gpt-4o", + "instructions": "You are a helpful assistant designed to make me better at coding!", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + }, + { + "id": "asst_abc456", + "object": "assistant", + "created_at": 1698982718, + "name": "My Assistant", + "description": null, + "model": "gpt-4o", + "instructions": "You are a helpful assistant designed to make me better at coding!", + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + }, + { + "id": "asst_abc789", + "object": "assistant", + "created_at": 1698982643, + "name": null, + "description": null, + "model": "gpt-4o", + "instructions": null, + "tools": [], + "tool_resources": {}, + "metadata": {}, + "top_p": 1.0, + "temperature": 1.0, + "response_format": "auto" + } + ], + "first_id": "asst_abc123", + "last_id": "asst_abc789", + "has_more": false + } + ListAuditLogsResponse: + type: object + properties: + object: + type: string + enum: + - list + x-stainless-const: true + data: + type: array + items: + $ref: "#/components/schemas/AuditLog" + first_id: + type: string + example: audit_log-defb456h8dks + last_id: + type: string + example: audit_log-hnbkd8s93s + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ListBatchesResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/Batch" + first_id: + type: string + example: batch_abc123 + last_id: + type: string + example: batch_abc456 + has_more: + type: boolean + object: + type: string + enum: + - list + x-stainless-const: true + required: + - object + - data + - has_more + ListCertificatesResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/Certificate" + first_id: + type: string + example: cert_abc + last_id: + type: string + example: cert_abc + has_more: + type: boolean + object: + type: string + enum: + - list + x-stainless-const: true + required: + - object + - data + - has_more + ListFilesResponse: + type: object + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/OpenAIFile" + first_id: + type: string + example: file-abc123 + last_id: + type: string + example: file-abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListFineTuningCheckpointPermissionResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/FineTuningCheckpointPermission" + object: + type: string + enum: + - list + x-stainless-const: true + first_id: + type: string + nullable: true + last_id: + type: string + nullable: true + has_more: + type: boolean + required: + - object + - data + - has_more + ListFineTuningJobCheckpointsResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/FineTuningJobCheckpoint" + object: + type: string + enum: + - list + x-stainless-const: true + first_id: + type: string + nullable: true + last_id: + type: string + nullable: true + has_more: + type: boolean + required: + - object + - data + - has_more + ListFineTuningJobEventsResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/FineTuningJobEvent" + object: + type: string + enum: + - list + x-stainless-const: true + has_more: + type: boolean + required: + - object + - data + - has_more + ListMessagesResponse: + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/MessageObject" + first_id: + type: string + example: msg_abc123 + last_id: + type: string + example: msg_abc123 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListModelsResponse: + type: object + properties: + object: + type: string + enum: + - list + x-stainless-const: true + data: + type: array + items: + $ref: "#/components/schemas/Model" + required: + - object + - data + ListPaginatedFineTuningJobsResponse: + type: object + properties: + data: + type: array + items: + $ref: "#/components/schemas/FineTuningJob" + has_more: + type: boolean + object: + type: string + enum: + - list + x-stainless-const: true + required: + - object + - data + - has_more + ListRunStepsResponse: + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/RunStepObject" + first_id: + type: string + example: step_abc123 + last_id: + type: string + example: step_abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListRunsResponse: + type: object + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/RunObject" + first_id: + type: string + example: run_abc123 + last_id: + type: string + example: run_abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListVectorStoreFilesResponse: + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/VectorStoreFileObject" + first_id: + type: string + example: file-abc123 + last_id: + type: string + example: file-abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + ListVectorStoresResponse: + properties: + object: + type: string + example: list + data: + type: array + items: + $ref: "#/components/schemas/VectorStoreObject" + first_id: + type: string + example: vs_abc123 + last_id: + type: string + example: vs_abc456 + has_more: + type: boolean + example: false + required: + - object + - data + - first_id + - last_id + - has_more + LocalShellExecAction: + type: object + title: Local shell exec action + description: | + Execute a shell command on the server. + properties: + type: + type: string + enum: + - exec + description: | + The type of the local shell action. Always `exec`. + x-stainless-const: true + command: + type: array + items: + type: string + description: | + The command to run. + timeout_ms: + type: integer + description: | + Optional timeout in milliseconds for the command. + nullable: true + working_directory: + type: string + description: | + Optional working directory to run the command in. + nullable: true + env: + type: object + additionalProperties: + type: string + description: | + Environment variables to set for the command. + user: + type: string + description: | + Optional user to run the command as. + nullable: true + required: + - type + - command + - env + LocalShellTool: + type: object + title: Local shell tool + description: > + A tool that allows the model to execute shell commands in a local + environment. + properties: + type: + type: string + enum: + - local_shell + description: The type of the local shell tool. Always `local_shell`. + x-stainless-const: true + required: + - type + LocalShellToolCall: + type: object + title: Local shell call + description: | + A tool call to run a command on the local shell. + properties: + type: + type: string + enum: + - local_shell_call + description: | + The type of the local shell call. Always `local_shell_call`. + x-stainless-const: true + id: + type: string + description: | + The unique ID of the local shell call. + call_id: + type: string + description: | + The unique ID of the local shell tool call generated by the model. + action: + $ref: "#/components/schemas/LocalShellExecAction" + status: + type: string + enum: + - in_progress + - completed + - incomplete + description: | + The status of the local shell call. + required: + - type + - id + - call_id + - action + - status + LocalShellToolCallOutput: + type: object + title: Local shell call output + description: | + The output of a local shell tool call. + properties: + type: + type: string + enum: + - local_shell_call_output + description: > + The type of the local shell tool call output. Always + `local_shell_call_output`. + x-stainless-const: true + id: + type: string + description: | + The unique ID of the local shell tool call generated by the model. + output: + type: string + description: | + A JSON string of the output of the local shell tool call. + status: + type: string + enum: + - in_progress + - completed + - incomplete + description: > + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. + nullable: true + required: + - id + - type + - call_id + - output + LogProbProperties: + type: object + description: | + A log probability object. + properties: + token: + type: string + description: | + The token that was used to generate the log probability. + logprob: + type: number + description: | + The log probability of the token. + bytes: + type: array + items: + type: integer + description: | + The bytes that were used to generate the log probability. + required: + - token + - logprob + - bytes + MCPApprovalRequest: + type: object + title: MCP approval request + description: | + A request for human approval of a tool invocation. + properties: + type: + type: string + enum: + - mcp_approval_request + description: | + The type of the item. Always `mcp_approval_request`. + x-stainless-const: true + id: + type: string + description: | + The unique ID of the approval request. + server_label: + type: string + description: | + The label of the MCP server making the request. + name: + type: string + description: | + The name of the tool to run. + arguments: + type: string + description: | + A JSON string of arguments for the tool. + required: + - type + - id + - server_label + - name + - arguments + MCPApprovalResponse: + type: object + title: MCP approval response + description: | + A response to an MCP approval request. + properties: + type: + type: string + enum: + - mcp_approval_response + description: | + The type of the item. Always `mcp_approval_response`. + x-stainless-const: true + id: + type: string + description: | + The unique ID of the approval response + nullable: true + approval_request_id: + type: string + description: | + The ID of the approval request being answered. + approve: + type: boolean + description: | + Whether the request was approved. + reason: + type: string + description: | + Optional reason for the decision. + nullable: true + required: + - type + - request_id + - approve + - approval_request_id + MCPApprovalResponseResource: + type: object + title: MCP approval response + description: | + A response to an MCP approval request. + properties: + type: + type: string + enum: + - mcp_approval_response + description: | + The type of the item. Always `mcp_approval_response`. + x-stainless-const: true + id: + type: string + description: | + The unique ID of the approval response + approval_request_id: + type: string + description: | + The ID of the approval request being answered. + approve: + type: boolean + description: | + Whether the request was approved. + reason: + type: string + description: | + Optional reason for the decision. + nullable: true + required: + - type + - id + - request_id + - approve + - approval_request_id + MCPListTools: + type: object + title: MCP list tools + description: | + A list of tools available on an MCP server. + properties: + type: + type: string + enum: + - mcp_list_tools + description: | + The type of the item. Always `mcp_list_tools`. + x-stainless-const: true + id: + type: string + description: | + The unique ID of the list. + server_label: + type: string + description: | + The label of the MCP server. + tools: + type: array + items: + $ref: "#/components/schemas/MCPListToolsTool" + description: | + The tools available on the server. + error: + type: string + description: | + Error message if the server could not list tools. + nullable: true + required: + - type + - id + - server_label + - tools + MCPListToolsTool: + type: object + title: MCP list tools tool + description: | + A tool available on an MCP server. + properties: + name: + type: string + description: | + The name of the tool. + description: + type: string + description: | + The description of the tool. + nullable: true + input_schema: + type: object + description: | + The JSON schema describing the tool's input. + annotations: + type: object + description: | + Additional annotations about the tool. + nullable: true + required: + - name + - input_schema + MCPTool: + type: object + title: MCP tool + description: > + Give the model access to additional tools via remote Model Context + Protocol + + (MCP) servers. [Learn more about MCP](/docs/guides/tools-remote-mcp). + properties: + type: + type: string + enum: + - mcp + description: The type of the MCP tool. Always `mcp`. + x-stainless-const: true + server_label: + type: string + description: | + A label for this MCP server, used to identify it in tool calls. + server_url: + type: string + description: | + The URL for the MCP server. + headers: + type: object + additionalProperties: + type: string + nullable: true + description: > + Optional HTTP headers to send to the MCP server. Use for + authentication + + or other purposes. + allowed_tools: + description: | + List of allowed tool names or a filter object. + oneOf: + - type: array + title: MCP allowed tools + description: A string array of allowed tool names + items: + type: string + - type: object + title: MCP allowed tools filter + description: | + A filter object to specify which tools are allowed. + properties: + tool_names: + type: array + title: MCP allowed tools + items: + type: string + description: List of allowed tool names. + required: [] + additionalProperties: false + nullable: true + require_approval: + description: Specify which of the MCP server's tools require approval. + oneOf: + - type: object + title: MCP tool approval filter + properties: + always: + type: object + description: | + A list of tools that always require approval. + properties: + tool_names: + type: array + items: + type: string + description: List of tools that require approval. + never: + type: object + description: | + A list of tools that never require approval. + properties: + tool_names: + type: array + items: + type: string + description: List of tools that do not require approval. + additionalProperties: false + - type: string + title: MCP tool approval setting + description: > + Specify a single approval policy for all tools. One of `always` + or + + `never`. When set to `always`, all tools will require approval. + When + + set to `never`, all tools will not require approval. + enum: + - always + - never + default: always + nullable: true + required: + - type + - server_label + - server_url + MCPToolCall: + type: object + title: MCP tool call + description: | + An invocation of a tool on an MCP server. + properties: + type: + type: string + enum: + - mcp_call + description: | + The type of the item. Always `mcp_call`. + x-stainless-const: true + id: + type: string + description: | + The unique ID of the tool call. + server_label: + type: string + description: | + The label of the MCP server running the tool. + name: + type: string + description: | + The name of the tool that was run. + arguments: + type: string + description: | + A JSON string of the arguments passed to the tool. + output: + type: string + description: | + The output from the tool call. + nullable: true + error: + type: string + description: | + The error from the tool call, if any. + nullable: true + required: + - type + - id + - server_label + - name + - arguments + MessageContentImageFileObject: + title: Image file + type: object + description: References an image [File](/docs/api-reference/files) in the + content of a message. + properties: + type: + description: Always `image_file`. + type: string + enum: + - image_file + x-stainless-const: true + image_file: + type: object + properties: + file_id: + description: The [File](/docs/api-reference/files) ID of the image in the + message content. Set `purpose="vision"` when uploading the File + if you need to later display the file content. + type: string + detail: + type: string + description: Specifies the detail level of the image if specified by the user. + `low` uses fewer tokens, you can opt in to high resolution using + `high`. + enum: + - auto + - low + - high + default: auto + required: + - file_id + required: + - type + - image_file + MessageContentImageUrlObject: + title: Image URL + type: object + description: References an image URL in the content of a message. + properties: + type: + type: string + enum: + - image_url + description: The type of the content part. + x-stainless-const: true + image_url: + type: object + properties: + url: + type: string + description: "The external URL of the image, must be a supported image types: + jpeg, jpg, png, gif, webp." + format: uri + detail: + type: string + description: Specifies the detail level of the image. `low` uses fewer tokens, + you can opt in to high resolution using `high`. Default value is + `auto` + enum: + - auto + - low + - high + default: auto + required: + - url + required: + - type + - image_url + MessageContentRefusalObject: + title: Refusal + type: object + description: The refusal content generated by the assistant. + properties: + type: + description: Always `refusal`. + type: string + enum: + - refusal + x-stainless-const: true + refusal: + type: string + nullable: false + required: + - type + - refusal + MessageContentTextAnnotationsFileCitationObject: + title: File citation + type: object + description: A citation within the message that points to a specific quote from + a specific File associated with the assistant or the message. Generated + when the assistant uses the "file_search" tool to search files. + properties: + type: + description: Always `file_citation`. + type: string + enum: + - file_citation + x-stainless-const: true + text: + description: The text in the message content that needs to be replaced. + type: string + file_citation: + type: object + properties: + file_id: + description: The ID of the specific File the citation is from. + type: string + required: + - file_id + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 + required: + - type + - text + - file_citation + - start_index + - end_index + MessageContentTextAnnotationsFilePathObject: + title: File path + type: object + description: A URL for the file that's generated when the assistant used the + `code_interpreter` tool to generate a file. + properties: + type: + description: Always `file_path`. + type: string + enum: + - file_path + x-stainless-const: true + text: + description: The text in the message content that needs to be replaced. + type: string + file_path: + type: object + properties: + file_id: + description: The ID of the file that was generated. + type: string + required: + - file_id + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 + required: + - type + - text + - file_path + - start_index + - end_index + MessageContentTextObject: + title: Text + type: object + description: The text content that is part of a message. + properties: + type: + description: Always `text`. + type: string + enum: + - text + x-stainless-const: true + text: + type: object + properties: + value: + description: The data that makes up the text. + type: string + annotations: + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageContentTextAnnotationsFileCitationObject" + - $ref: "#/components/schemas/MessageContentTextAnnotationsFilePathObject" + required: + - value + - annotations + required: + - type + - text + MessageDeltaContentImageFileObject: + title: Image file + type: object + description: References an image [File](/docs/api-reference/files) in the + content of a message. + properties: + index: + type: integer + description: The index of the content part in the message. + type: + description: Always `image_file`. + type: string + enum: + - image_file + x-stainless-const: true + image_file: + type: object + properties: + file_id: + description: The [File](/docs/api-reference/files) ID of the image in the + message content. Set `purpose="vision"` when uploading the File + if you need to later display the file content. + type: string + detail: + type: string + description: Specifies the detail level of the image if specified by the user. + `low` uses fewer tokens, you can opt in to high resolution using + `high`. + enum: + - auto + - low + - high + default: auto + required: + - index + - type + MessageDeltaContentImageUrlObject: + title: Image URL + type: object + description: References an image URL in the content of a message. + properties: + index: + type: integer + description: The index of the content part in the message. + type: + description: Always `image_url`. + type: string + enum: + - image_url + x-stainless-const: true + image_url: + type: object + properties: + url: + description: "The URL of the image, must be a supported image types: jpeg, jpg, + png, gif, webp." + type: string + detail: + type: string + description: Specifies the detail level of the image. `low` uses fewer tokens, + you can opt in to high resolution using `high`. + enum: + - auto + - low + - high + default: auto + required: + - index + - type + MessageDeltaContentRefusalObject: + title: Refusal + type: object + description: The refusal content that is part of a message. + properties: + index: + type: integer + description: The index of the refusal part in the message. + type: + description: Always `refusal`. + type: string + enum: + - refusal + x-stainless-const: true + refusal: + type: string + required: + - index + - type + MessageDeltaContentTextAnnotationsFileCitationObject: + title: File citation + type: object + description: A citation within the message that points to a specific quote from + a specific File associated with the assistant or the message. Generated + when the assistant uses the "file_search" tool to search files. + properties: + index: + type: integer + description: The index of the annotation in the text content part. + type: + description: Always `file_citation`. + type: string + enum: + - file_citation + x-stainless-const: true + text: + description: The text in the message content that needs to be replaced. + type: string + file_citation: + type: object + properties: + file_id: + description: The ID of the specific File the citation is from. + type: string + quote: + description: The specific quote in the file. + type: string + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 + required: + - index + - type + MessageDeltaContentTextAnnotationsFilePathObject: + title: File path + type: object + description: A URL for the file that's generated when the assistant used the + `code_interpreter` tool to generate a file. + properties: + index: + type: integer + description: The index of the annotation in the text content part. + type: + description: Always `file_path`. + type: string + enum: + - file_path + x-stainless-const: true + text: + description: The text in the message content that needs to be replaced. + type: string + file_path: + type: object + properties: + file_id: + description: The ID of the file that was generated. + type: string + start_index: + type: integer + minimum: 0 + end_index: + type: integer + minimum: 0 + required: + - index + - type + MessageDeltaContentTextObject: + title: Text + type: object + description: The text content that is part of a message. + properties: + index: + type: integer + description: The index of the content part in the message. + type: + description: Always `text`. + type: string + enum: + - text + x-stainless-const: true + text: + type: object + properties: + value: + description: The data that makes up the text. + type: string + annotations: + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageDeltaContentTextAnnotationsFileCitationObjec\ + t" + - $ref: "#/components/schemas/MessageDeltaContentTextAnnotationsFilePathObject" + required: + - index + - type + MessageDeltaObject: + type: object + title: Message delta object + description: > + Represents a message delta i.e. any changed fields on a message during + streaming. + properties: + id: + description: The identifier of the message, which can be referenced in API + endpoints. + type: string + object: + description: The object type, which is always `thread.message.delta`. + type: string + enum: + - thread.message.delta + x-stainless-const: true + delta: + description: The delta containing the fields that have changed on the Message. + type: object + properties: + role: + description: The entity that produced the message. One of `user` or `assistant`. + type: string + enum: + - user + - assistant + content: + description: The content of the message in array of text and/or images. + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageDeltaContentImageFileObject" + - $ref: "#/components/schemas/MessageDeltaContentTextObject" + - $ref: "#/components/schemas/MessageDeltaContentRefusalObject" + - $ref: "#/components/schemas/MessageDeltaContentImageUrlObject" + required: + - id + - object + - delta + x-oaiMeta: + name: The message delta object + beta: true + example: | + { + "id": "msg_123", + "object": "thread.message.delta", + "delta": { + "content": [ + { + "index": 0, + "type": "text", + "text": { "value": "Hello", "annotations": [] } + } + ] + } + } + MessageObject: + type: object + title: The message object + description: Represents a message within a [thread](/docs/api-reference/threads). + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `thread.message`. + type: string + enum: + - thread.message + x-stainless-const: true + created_at: + description: The Unix timestamp (in seconds) for when the message was created. + type: integer + thread_id: + description: The [thread](/docs/api-reference/threads) ID that this message + belongs to. + type: string + status: + description: The status of the message, which can be either `in_progress`, + `incomplete`, or `completed`. + type: string + enum: + - in_progress + - incomplete + - completed + incomplete_details: + description: On an incomplete message, details about why the message is + incomplete. + type: object + properties: + reason: + type: string + description: The reason the message is incomplete. + enum: + - content_filter + - max_tokens + - run_cancelled + - run_expired + - run_failed + nullable: true + required: + - reason + completed_at: + description: The Unix timestamp (in seconds) for when the message was completed. + type: integer + nullable: true + incomplete_at: + description: The Unix timestamp (in seconds) for when the message was marked as + incomplete. + type: integer + nullable: true + role: + description: The entity that produced the message. One of `user` or `assistant`. + type: string + enum: + - user + - assistant + content: + description: The content of the message in array of text and/or images. + type: array + items: + oneOf: + - $ref: "#/components/schemas/MessageContentImageFileObject" + - $ref: "#/components/schemas/MessageContentImageUrlObject" + - $ref: "#/components/schemas/MessageContentTextObject" + - $ref: "#/components/schemas/MessageContentRefusalObject" + assistant_id: + description: If applicable, the ID of the + [assistant](/docs/api-reference/assistants) that authored this + message. + type: string + nullable: true + run_id: + description: The ID of the [run](/docs/api-reference/runs) associated with the + creation of this message. Value is `null` when messages are created + manually using the create message or create thread endpoints. + type: string + nullable: true + attachments: + type: array + items: + type: object + properties: + file_id: + type: string + description: The ID of the file to attach to the message. + tools: + description: The tools to add this file to. + type: array + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearchTypeOnly" + description: A list of files attached to the message, and the tools they were + added to. + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + required: + - id + - object + - created_at + - thread_id + - status + - incomplete_details + - completed_at + - incomplete_at + - role + - content + - assistant_id + - run_id + - attachments + - metadata + x-oaiMeta: + name: The message object + beta: true + example: | + { + "id": "msg_abc123", + "object": "thread.message", + "created_at": 1698983503, + "thread_id": "thread_abc123", + "role": "assistant", + "content": [ + { + "type": "text", + "text": { + "value": "Hi! How can I help you today?", + "annotations": [] + } + } + ], + "assistant_id": "asst_abc123", + "run_id": "run_abc123", + "attachments": [], + "metadata": {} + } + MessageRequestContentTextObject: + title: Text + type: object + description: The text content that is part of a message. + properties: + type: + description: Always `text`. + type: string + enum: + - text + x-stainless-const: true + text: + type: string + description: Text content to be sent to the model + required: + - type + - text + MessageStreamEvent: + oneOf: + - type: object + properties: + event: + type: string + enum: + - thread.message.created + x-stainless-const: true + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) is + created. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + - type: object + properties: + event: + type: string + enum: + - thread.message.in_progress + x-stainless-const: true + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) moves + to an `in_progress` state. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + - type: object + properties: + event: + type: string + enum: + - thread.message.delta + x-stainless-const: true + data: + $ref: "#/components/schemas/MessageDeltaObject" + required: + - event + - data + description: Occurs when parts of a + [Message](/docs/api-reference/messages/object) are being streamed. + x-oaiMeta: + dataDescription: "`data` is a [message + delta](/docs/api-reference/assistants-streaming/message-delta-obj\ + ect)" + - type: object + properties: + event: + type: string + enum: + - thread.message.completed + x-stainless-const: true + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) is + completed. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + - type: object + properties: + event: + type: string + enum: + - thread.message.incomplete + x-stainless-const: true + data: + $ref: "#/components/schemas/MessageObject" + required: + - event + - data + description: Occurs when a [message](/docs/api-reference/messages/object) ends + before it is completed. + x-oaiMeta: + dataDescription: "`data` is a [message](/docs/api-reference/messages/object)" + Metadata: + type: object + description: > + Set of 16 key-value pairs that can be attached to an object. This can be + + useful for storing additional information about the object in a + structured + + format, and querying for objects via API or the dashboard. + + + Keys are strings with a maximum length of 64 characters. Values are + strings + + with a maximum length of 512 characters. + additionalProperties: + type: string + x-oaiTypeLabel: map + nullable: true + Model: + title: Model + description: Describes an OpenAI model offering that can be used with the API. + properties: + id: + type: string + description: The model identifier, which can be referenced in the API endpoints. + created: + type: integer + description: The Unix timestamp (in seconds) when the model was created. + object: + type: string + description: The object type, which is always "model". + enum: + - model + x-stainless-const: true + owned_by: + type: string + description: The organization that owns the model. + required: + - id + - object + - created + - owned_by + x-oaiMeta: + name: The model object + example: | + { + "id": "VAR_chat_model_id", + "object": "model", + "created": 1686935002, + "owned_by": "openai" + } + ModelIds: + anyOf: + - $ref: "#/components/schemas/ModelIdsShared" + - $ref: "#/components/schemas/ModelIdsResponses" + ModelIdsResponses: + example: gpt-4o + anyOf: + - $ref: "#/components/schemas/ModelIdsShared" + - type: string + title: ResponsesOnlyModel + enum: + - o1-pro + - o1-pro-2025-03-19 + - o3-pro + - o3-pro-2025-06-10 + - computer-use-preview + - computer-use-preview-2025-03-11 + ModelIdsShared: + example: gpt-4o + anyOf: + - type: string + - type: string + enum: + - gpt-4.1 + - gpt-4.1-mini + - gpt-4.1-nano + - gpt-4.1-2025-04-14 + - gpt-4.1-mini-2025-04-14 + - gpt-4.1-nano-2025-04-14 + - o4-mini + - o4-mini-2025-04-16 + - o3 + - o3-2025-04-16 + - o3-mini + - o3-mini-2025-01-31 + - o1 + - o1-2024-12-17 + - o1-preview + - o1-preview-2024-09-12 + - o1-mini + - o1-mini-2024-09-12 + - gpt-4o + - gpt-4o-2024-11-20 + - gpt-4o-2024-08-06 + - gpt-4o-2024-05-13 + - gpt-4o-audio-preview + - gpt-4o-audio-preview-2024-10-01 + - gpt-4o-audio-preview-2024-12-17 + - gpt-4o-audio-preview-2025-06-03 + - gpt-4o-mini-audio-preview + - gpt-4o-mini-audio-preview-2024-12-17 + - gpt-4o-search-preview + - gpt-4o-mini-search-preview + - gpt-4o-search-preview-2025-03-11 + - gpt-4o-mini-search-preview-2025-03-11 + - chatgpt-4o-latest + - codex-mini-latest + - gpt-4o-mini + - gpt-4o-mini-2024-07-18 + - gpt-4-turbo + - gpt-4-turbo-2024-04-09 + - gpt-4-0125-preview + - gpt-4-turbo-preview + - gpt-4-1106-preview + - gpt-4-vision-preview + - gpt-4 + - gpt-4-0314 + - gpt-4-0613 + - gpt-4-32k + - gpt-4-32k-0314 + - gpt-4-32k-0613 + - gpt-3.5-turbo + - gpt-3.5-turbo-16k + - gpt-3.5-turbo-0301 + - gpt-3.5-turbo-0613 + - gpt-3.5-turbo-1106 + - gpt-3.5-turbo-0125 + - gpt-3.5-turbo-16k-0613 + ModelResponseProperties: + type: object + properties: + metadata: + $ref: "#/components/schemas/Metadata" + temperature: + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + + We generally recommend altering this or `top_p` but not both. + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, + + where the model considers the results of the tokens with top_p + probability + + mass. So 0.1 means only the tokens comprising the top 10% + probability mass + + are considered. + + + We generally recommend altering this or `temperature` but not both. + user: + type: string + example: user-1234 + description: > + A stable identifier for your end-users. + + Used to boost cache hit rates by better bucketing similar requests + and to help OpenAI detect and prevent abuse. [Learn + more](/docs/guides/safety-best-practices#end-user-ids). + service_tier: + $ref: "#/components/schemas/ServiceTier" + ModifyAssistantRequest: + type: object + additionalProperties: false + properties: + model: + description: > + ID of the model to use. You can use the [List + models](/docs/api-reference/models/list) API to see all of your + available models, or see our [Model overview](/docs/models) for + descriptions of them. + anyOf: + - type: string + - $ref: "#/components/schemas/AssistantSupportedModels" + reasoning_effort: + $ref: "#/components/schemas/ReasoningEffort" + name: + description: | + The name of the assistant. The maximum length is 256 characters. + type: string + nullable: true + maxLength: 256 + description: + description: > + The description of the assistant. The maximum length is 512 + characters. + type: string + nullable: true + maxLength: 512 + instructions: + description: > + The system instructions that the assistant uses. The maximum length + is 256,000 characters. + type: string + nullable: true + maxLength: 256000 + tools: + description: > + A list of tool enabled on the assistant. There can be a maximum of + 128 tools per assistant. Tools can be of types `code_interpreter`, + `file_search`, or `function`. + default: [] + type: array + maxItems: 128 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + tool_resources: + type: object + description: > + A set of resources that are used by the assistant's tools. The + resources are specific to the type of tool. For example, the + `code_interpreter` tool requires a list of file IDs, while the + `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + Overrides the list of [file](/docs/api-reference/files) IDs + made available to the `code_interpreter` tool. There can be + a maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + Overrides the [vector + store](/docs/api-reference/vector-stores/object) attached to + this assistant. There can be a maximum of 1 vector store + attached to the assistant. + maxItems: 1 + items: + type: string + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + temperature: + description: > + What sampling temperature to use, between 0 and 2. Higher values + like 0.8 will make the output more random, while lower values like + 0.2 will make it more focused and deterministic. + type: number + minimum: 0 + maximum: 2 + default: 1 + example: 1 + nullable: true + top_p: + type: number + minimum: 0 + maximum: 1 + default: 1 + example: 1 + nullable: true + description: > + An alternative to sampling with temperature, called nucleus + sampling, where the model considers the results of the tokens with + top_p probability mass. So 0.1 means only the tokens comprising the + top 10% probability mass are considered. + + + We generally recommend altering this or temperature but not both. + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + ModifyCertificateRequest: + type: object + properties: + name: + type: string + description: The updated name for the certificate + required: + - name + ModifyMessageRequest: + type: object + additionalProperties: false + properties: + metadata: + $ref: "#/components/schemas/Metadata" + ModifyRunRequest: + type: object + additionalProperties: false + properties: + metadata: + $ref: "#/components/schemas/Metadata" + ModifyThreadRequest: + type: object + additionalProperties: false + properties: + tool_resources: + type: object + description: > + A set of resources that are made available to the assistant's tools + in this thread. The resources are specific to the type of tool. For + example, the `code_interpreter` tool requires a list of file IDs, + while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The [vector store](/docs/api-reference/vector-stores/object) + attached to this thread. There can be a maximum of 1 vector + store attached to the thread. + maxItems: 1 + items: + type: string + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + Move: + type: object + title: Move + description: | + A mouse move action. + properties: + type: + type: string + enum: + - move + default: move + description: | + Specifies the event type. For a move action, this property is + always set to `move`. + x-stainless-const: true + x: + type: integer + description: | + The x-coordinate to move to. + y: + type: integer + description: | + The y-coordinate to move to. + required: + - type + - x + - y + OpenAIFile: + title: OpenAIFile + description: The `File` object represents a document that has been uploaded to OpenAI. + properties: + id: + type: string + description: The file identifier, which can be referenced in the API endpoints. + bytes: + type: integer + description: The size of the file, in bytes. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the file was created. + expires_at: + type: integer + description: The Unix timestamp (in seconds) for when the file will expire. + filename: + type: string + description: The name of the file. + object: + type: string + description: The object type, which is always `file`. + enum: + - file + x-stainless-const: true + purpose: + type: string + description: The intended purpose of the file. Supported values are + `assistants`, `assistants_output`, `batch`, `batch_output`, + `fine-tune`, `fine-tune-results` and `vision`. + enum: + - assistants + - assistants_output + - batch + - batch_output + - fine-tune + - fine-tune-results + - vision + status: + type: string + deprecated: true + description: Deprecated. The current status of the file, which can be either + `uploaded`, `processed`, or `error`. + enum: + - uploaded + - processed + - error + status_details: + type: string + deprecated: true + description: Deprecated. For details on why a fine-tuning training file failed + validation, see the `error` field on `fine_tuning.job`. + required: + - id + - object + - bytes + - created_at + - filename + - purpose + - status + x-oaiMeta: + name: The file object + example: | + { + "id": "file-abc123", + "object": "file", + "bytes": 120000, + "created_at": 1677610602, + "expires_at": 1680202602, + "filename": "salesOverview.pdf", + "purpose": "assistants", + } + OtherChunkingStrategyResponseParam: + type: object + title: Other Chunking Strategy + description: This is returned when the chunking strategy is unknown. Typically, + this is because the file was indexed before the `chunking_strategy` + concept was introduced in the API. + additionalProperties: false + properties: + type: + type: string + description: Always `other`. + enum: + - other + x-stainless-const: true + required: + - type + OutputAudio: + type: object + title: Output audio + description: | + An audio output from the model. + properties: + type: + type: string + description: | + The type of the output audio. Always `output_audio`. + enum: + - output_audio + x-stainless-const: true + data: + type: string + description: | + Base64-encoded audio data from the model. + transcript: + type: string + description: | + The transcript of the audio data from the model. + required: + - type + - data + - transcript + OutputContent: + oneOf: + - $ref: "#/components/schemas/OutputTextContent" + - $ref: "#/components/schemas/RefusalContent" + OutputItem: + anyOf: + - $ref: "#/components/schemas/OutputMessage" + - $ref: "#/components/schemas/FileSearchToolCall" + - $ref: "#/components/schemas/FunctionToolCall" + - $ref: "#/components/schemas/WebSearchToolCall" + - $ref: "#/components/schemas/ComputerToolCall" + - $ref: "#/components/schemas/ReasoningItem" + - $ref: "#/components/schemas/ImageGenToolCall" + - $ref: "#/components/schemas/CodeInterpreterToolCall" + - $ref: "#/components/schemas/LocalShellToolCall" + - $ref: "#/components/schemas/MCPToolCall" + - $ref: "#/components/schemas/MCPListTools" + - $ref: "#/components/schemas/MCPApprovalRequest" + discriminator: + propertyName: type + OutputMessage: + type: object + title: Output message + description: | + An output message from the model. + properties: + id: + type: string + description: | + The unique ID of the output message. + type: + type: string + description: | + The type of the output message. Always `message`. + enum: + - message + x-stainless-const: true + role: + type: string + description: | + The role of the output message. Always `assistant`. + enum: + - assistant + x-stainless-const: true + content: + type: array + description: | + The content of the output message. + items: + $ref: "#/components/schemas/OutputContent" + status: + type: string + description: > + The status of the message input. One of `in_progress`, `completed`, + or + + `incomplete`. Populated when input items are returned via API. + enum: + - in_progress + - completed + - incomplete + required: + - id + - type + - role + - content + - status + ParallelToolCalls: + description: Whether to enable [parallel function + calling](/docs/guides/function-calling#configuring-parallel-function-calling) + during tool use. + type: boolean + default: true + PredictionContent: + type: object + title: Static Content + description: > + Static predicted output content, such as the content of a text file that + is + + being regenerated. + required: + - type + - content + properties: + type: + type: string + enum: + - content + description: | + The type of the predicted content you want to provide. This type is + currently always `content`. + x-stainless-const: true + content: + description: > + The content that should be matched when generating a model response. + + If generated tokens would match this content, the entire model + response + + can be returned much more quickly. + oneOf: + - type: string + title: Text content + description: | + The content used for a Predicted Output. This is often the + text of a file you are regenerating with minor changes. + - type: array + description: An array of content parts with a defined type. Supported options + differ based on the [model](/docs/models) being used to generate + the response. Can contain text inputs. + title: Array of content parts + items: + $ref: "#/components/schemas/ChatCompletionRequestMessageContentPartText" + minItems: 1 + Project: + type: object + description: Represents an individual project. + properties: + id: + type: string + description: The identifier, which can be referenced in API endpoints + object: + type: string + enum: + - organization.project + description: The object type, which is always `organization.project` + x-stainless-const: true + name: + type: string + description: The name of the project. This appears in reporting. + created_at: + type: integer + description: The Unix timestamp (in seconds) of when the project was created. + archived_at: + type: integer + nullable: true + description: The Unix timestamp (in seconds) of when the project was archived or + `null`. + status: + type: string + enum: + - active + - archived + description: "`active` or `archived`" + required: + - id + - object + - name + - created_at + - status + x-oaiMeta: + name: The project object + example: | + { + "id": "proj_abc", + "object": "organization.project", + "name": "Project example", + "created_at": 1711471533, + "archived_at": null, + "status": "active" + } + ProjectApiKey: + type: object + description: Represents an individual API key in a project. + properties: + object: + type: string + enum: + - organization.project.api_key + description: The object type, which is always `organization.project.api_key` + x-stainless-const: true + redacted_value: + type: string + description: The redacted value of the API key + name: + type: string + description: The name of the API key + created_at: + type: integer + description: The Unix timestamp (in seconds) of when the API key was created + last_used_at: + type: integer + description: The Unix timestamp (in seconds) of when the API key was last used. + id: + type: string + description: The identifier, which can be referenced in API endpoints + owner: + type: object + properties: + type: + type: string + enum: + - user + - service_account + description: "`user` or `service_account`" + user: + $ref: "#/components/schemas/ProjectUser" + service_account: + $ref: "#/components/schemas/ProjectServiceAccount" + required: + - object + - redacted_value + - name + - created_at + - last_used_at + - id + - owner + x-oaiMeta: + name: The project API key object + example: | + { + "object": "organization.project.api_key", + "redacted_value": "sk-abc...def", + "name": "My API Key", + "created_at": 1711471533, + "last_used_at": 1711471534, + "id": "key_abc", + "owner": { + "type": "user", + "user": { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "created_at": 1711471533 + } + } + } + ProjectApiKeyDeleteResponse: + type: object + properties: + object: + type: string + enum: + - organization.project.api_key.deleted + x-stainless-const: true + id: + type: string + deleted: + type: boolean + required: + - object + - id + - deleted + ProjectApiKeyListResponse: + type: object + properties: + object: + type: string + enum: + - list + x-stainless-const: true + data: + type: array + items: + $ref: "#/components/schemas/ProjectApiKey" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ProjectCreateRequest: + type: object + properties: + name: + type: string + description: The friendly name of the project, this name appears in reports. + required: + - name + ProjectListResponse: + type: object + properties: + object: + type: string + enum: + - list + x-stainless-const: true + data: + type: array + items: + $ref: "#/components/schemas/Project" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ProjectRateLimit: + type: object + description: Represents a project rate limit config. + properties: + object: + type: string + enum: + - project.rate_limit + description: The object type, which is always `project.rate_limit` + x-stainless-const: true + id: + type: string + description: The identifier, which can be referenced in API endpoints. + model: + type: string + description: The model this rate limit applies to. + max_requests_per_1_minute: + type: integer + description: The maximum requests per minute. + max_tokens_per_1_minute: + type: integer + description: The maximum tokens per minute. + max_images_per_1_minute: + type: integer + description: The maximum images per minute. Only present for relevant models. + max_audio_megabytes_per_1_minute: + type: integer + description: The maximum audio megabytes per minute. Only present for relevant + models. + max_requests_per_1_day: + type: integer + description: The maximum requests per day. Only present for relevant models. + batch_1_day_max_input_tokens: + type: integer + description: The maximum batch input tokens per day. Only present for relevant + models. + required: + - object + - id + - model + - max_requests_per_1_minute + - max_tokens_per_1_minute + x-oaiMeta: + name: The project rate limit object + example: | + { + "object": "project.rate_limit", + "id": "rl_ada", + "model": "ada", + "max_requests_per_1_minute": 600, + "max_tokens_per_1_minute": 150000, + "max_images_per_1_minute": 10 + } + ProjectRateLimitListResponse: + type: object + properties: + object: + type: string + enum: + - list + x-stainless-const: true + data: + type: array + items: + $ref: "#/components/schemas/ProjectRateLimit" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ProjectRateLimitUpdateRequest: + type: object + properties: + max_requests_per_1_minute: + type: integer + description: The maximum requests per minute. + max_tokens_per_1_minute: + type: integer + description: The maximum tokens per minute. + max_images_per_1_minute: + type: integer + description: The maximum images per minute. Only relevant for certain models. + max_audio_megabytes_per_1_minute: + type: integer + description: The maximum audio megabytes per minute. Only relevant for certain + models. + max_requests_per_1_day: + type: integer + description: The maximum requests per day. Only relevant for certain models. + batch_1_day_max_input_tokens: + type: integer + description: The maximum batch input tokens per day. Only relevant for certain + models. + ProjectServiceAccount: + type: object + description: Represents an individual service account in a project. + properties: + object: + type: string + enum: + - organization.project.service_account + description: The object type, which is always + `organization.project.service_account` + x-stainless-const: true + id: + type: string + description: The identifier, which can be referenced in API endpoints + name: + type: string + description: The name of the service account + role: + type: string + enum: + - owner + - member + description: "`owner` or `member`" + created_at: + type: integer + description: The Unix timestamp (in seconds) of when the service account was + created + required: + - object + - id + - name + - role + - created_at + x-oaiMeta: + name: The project service account object + example: | + { + "object": "organization.project.service_account", + "id": "svc_acct_abc", + "name": "Service Account", + "role": "owner", + "created_at": 1711471533 + } + ProjectServiceAccountApiKey: + type: object + properties: + object: + type: string + enum: + - organization.project.service_account.api_key + description: The object type, which is always + `organization.project.service_account.api_key` + x-stainless-const: true + value: + type: string + name: + type: string + created_at: + type: integer + id: + type: string + required: + - object + - value + - name + - created_at + - id + ProjectServiceAccountCreateRequest: + type: object + properties: + name: + type: string + description: The name of the service account being created. + required: + - name + ProjectServiceAccountCreateResponse: + type: object + properties: + object: + type: string + enum: + - organization.project.service_account + x-stainless-const: true + id: + type: string + name: + type: string + role: + type: string + enum: + - member + description: Service accounts can only have one role of type `member` + x-stainless-const: true + created_at: + type: integer + api_key: + $ref: "#/components/schemas/ProjectServiceAccountApiKey" + required: + - object + - id + - name + - role + - created_at + - api_key + ProjectServiceAccountDeleteResponse: + type: object + properties: + object: + type: string + enum: + - organization.project.service_account.deleted + x-stainless-const: true + id: + type: string + deleted: + type: boolean + required: + - object + - id + - deleted + ProjectServiceAccountListResponse: + type: object + properties: + object: + type: string + enum: + - list + x-stainless-const: true + data: + type: array + items: + $ref: "#/components/schemas/ProjectServiceAccount" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ProjectUpdateRequest: + type: object + properties: + name: + type: string + description: The updated name of the project, this name appears in reports. + required: + - name + ProjectUser: + type: object + description: Represents an individual user in a project. + properties: + object: + type: string + enum: + - organization.project.user + description: The object type, which is always `organization.project.user` + x-stainless-const: true + id: + type: string + description: The identifier, which can be referenced in API endpoints + name: + type: string + description: The name of the user + email: + type: string + description: The email address of the user + role: + type: string + enum: + - owner + - member + description: "`owner` or `member`" + added_at: + type: integer + description: The Unix timestamp (in seconds) of when the project was added. + required: + - object + - id + - name + - email + - role + - added_at + x-oaiMeta: + name: The project user object + example: | + { + "object": "organization.project.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + ProjectUserCreateRequest: + type: object + properties: + user_id: + type: string + description: The ID of the user. + role: + type: string + enum: + - owner + - member + description: "`owner` or `member`" + required: + - user_id + - role + ProjectUserDeleteResponse: + type: object + properties: + object: + type: string + enum: + - organization.project.user.deleted + x-stainless-const: true + id: + type: string + deleted: + type: boolean + required: + - object + - id + - deleted + ProjectUserListResponse: + type: object + properties: + object: + type: string + data: + type: array + items: + $ref: "#/components/schemas/ProjectUser" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + ProjectUserUpdateRequest: + type: object + properties: + role: + type: string + enum: + - owner + - member + description: "`owner` or `member`" + required: + - role + RealtimeClientEvent: + discriminator: + propertyName: type + description: | + A realtime client event. + anyOf: + - $ref: "#/components/schemas/RealtimeClientEventConversationItemCreate" + - $ref: "#/components/schemas/RealtimeClientEventConversationItemDelete" + - $ref: "#/components/schemas/RealtimeClientEventConversationItemRetrieve" + - $ref: "#/components/schemas/RealtimeClientEventConversationItemTruncate" + - $ref: "#/components/schemas/RealtimeClientEventInputAudioBufferAppend" + - $ref: "#/components/schemas/RealtimeClientEventInputAudioBufferClear" + - $ref: "#/components/schemas/RealtimeClientEventOutputAudioBufferClear" + - $ref: "#/components/schemas/RealtimeClientEventInputAudioBufferCommit" + - $ref: "#/components/schemas/RealtimeClientEventResponseCancel" + - $ref: "#/components/schemas/RealtimeClientEventResponseCreate" + - $ref: "#/components/schemas/RealtimeClientEventSessionUpdate" + - $ref: "#/components/schemas/RealtimeClientEventTranscriptionSessionUpdate" + RealtimeClientEventConversationItemCreate: + type: object + description: > + Add a new Item to the Conversation's context, including messages, + function + + calls, and function call responses. This event can be used both to + populate a + + "history" of the conversation and to add new items mid-stream, but has + the + + current limitation that it cannot populate assistant audio messages. + + + If successful, the server will respond with a + `conversation.item.created` + + event, otherwise an `error` event will be sent. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - conversation.item.create + description: The event type, must be `conversation.item.create`. + x-stainless-const: true + previous_item_id: + type: string + description: > + The ID of the preceding item after which the new item will be + inserted. + + If not set, the new item will be appended to the end of the + conversation. + + If set to `root`, the new item will be added to the beginning of the + conversation. + + If set to an existing ID, it allows an item to be inserted + mid-conversation. If the + + ID cannot be found, an error will be returned and the item will not + be added. + item: + $ref: "#/components/schemas/RealtimeConversationItem" + required: + - type + - item + x-oaiMeta: + name: conversation.item.create + group: realtime + example: | + { + "event_id": "event_345", + "type": "conversation.item.create", + "previous_item_id": null, + "item": { + "id": "msg_001", + "type": "message", + "role": "user", + "content": [ + { + "type": "input_text", + "text": "Hello, how are you?" + } + ] + } + } + RealtimeClientEventConversationItemDelete: + type: object + description: > + Send this event when you want to remove any item from the conversation + + history. The server will respond with a `conversation.item.deleted` + event, + + unless the item does not exist in the conversation history, in which + case the + + server will respond with an error. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - conversation.item.delete + description: The event type, must be `conversation.item.delete`. + x-stainless-const: true + item_id: + type: string + description: The ID of the item to delete. + required: + - type + - item_id + x-oaiMeta: + name: conversation.item.delete + group: realtime + example: | + { + "event_id": "event_901", + "type": "conversation.item.delete", + "item_id": "msg_003" + } + RealtimeClientEventConversationItemRetrieve: + type: object + description: > + Send this event when you want to retrieve the server's representation of + a specific item in the conversation history. This is useful, for + example, to inspect user audio after noise cancellation and VAD. + + The server will respond with a `conversation.item.retrieved` event, + + unless the item does not exist in the conversation history, in which + case the + + server will respond with an error. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - conversation.item.retrieve + description: The event type, must be `conversation.item.retrieve`. + x-stainless-const: true + item_id: + type: string + description: The ID of the item to retrieve. + required: + - type + - item_id + x-oaiMeta: + name: conversation.item.retrieve + group: realtime + example: | + { + "event_id": "event_901", + "type": "conversation.item.retrieve", + "item_id": "msg_003" + } + RealtimeClientEventConversationItemTruncate: + type: object + description: > + Send this event to truncate a previous assistant message’s audio. The + server + + will produce audio faster than realtime, so this event is useful when + the user + + interrupts to truncate audio that has already been sent to the client + but not + + yet played. This will synchronize the server's understanding of the + audio with + + the client's playback. + + + Truncating audio will delete the server-side text transcript to ensure + there + + is not text in the context that hasn't been heard by the user. + + + If successful, the server will respond with a + `conversation.item.truncated` + + event. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - conversation.item.truncate + description: The event type, must be `conversation.item.truncate`. + x-stainless-const: true + item_id: + type: string + description: > + The ID of the assistant message item to truncate. Only assistant + message + + items can be truncated. + content_index: + type: integer + description: The index of the content part to truncate. Set this to 0. + audio_end_ms: + type: integer + description: > + Inclusive duration up to which audio is truncated, in milliseconds. + If + + the audio_end_ms is greater than the actual audio duration, the + server + + will respond with an error. + required: + - type + - item_id + - content_index + - audio_end_ms + x-oaiMeta: + name: conversation.item.truncate + group: realtime + example: | + { + "event_id": "event_678", + "type": "conversation.item.truncate", + "item_id": "msg_002", + "content_index": 0, + "audio_end_ms": 1500 + } + RealtimeClientEventInputAudioBufferAppend: + type: object + description: > + Send this event to append audio bytes to the input audio buffer. The + audio + + buffer is temporary storage you can write to and later commit. In Server + VAD + + mode, the audio buffer is used to detect speech and the server will + decide + + when to commit. When Server VAD is disabled, you must commit the audio + buffer + + manually. + + + The client may choose how much audio to place in each event up to a + maximum + + of 15 MiB, for example streaming smaller chunks from the client may + allow the + + VAD to be more responsive. Unlike made other client events, the server + will + + not send a confirmation response to this event. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - input_audio_buffer.append + description: The event type, must be `input_audio_buffer.append`. + x-stainless-const: true + audio: + type: string + description: > + Base64-encoded audio bytes. This must be in the format specified by + the + + `input_audio_format` field in the session configuration. + required: + - type + - audio + x-oaiMeta: + name: input_audio_buffer.append + group: realtime + example: | + { + "event_id": "event_456", + "type": "input_audio_buffer.append", + "audio": "Base64EncodedAudioData" + } + RealtimeClientEventInputAudioBufferClear: + type: object + description: | + Send this event to clear the audio bytes in the buffer. The server will + respond with an `input_audio_buffer.cleared` event. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - input_audio_buffer.clear + description: The event type, must be `input_audio_buffer.clear`. + x-stainless-const: true + required: + - type + x-oaiMeta: + name: input_audio_buffer.clear + group: realtime + example: | + { + "event_id": "event_012", + "type": "input_audio_buffer.clear" + } + RealtimeClientEventInputAudioBufferCommit: + type: object + description: > + Send this event to commit the user input audio buffer, which will create + a + + new user message item in the conversation. This event will produce an + error + + if the input audio buffer is empty. When in Server VAD mode, the client + does + + not need to send this event, the server will commit the audio buffer + + automatically. + + + Committing the input audio buffer will trigger input audio + transcription + + (if enabled in session configuration), but it will not create a + response + + from the model. The server will respond with an + `input_audio_buffer.committed` + + event. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - input_audio_buffer.commit + description: The event type, must be `input_audio_buffer.commit`. + x-stainless-const: true + required: + - type + x-oaiMeta: + name: input_audio_buffer.commit + group: realtime + example: | + { + "event_id": "event_789", + "type": "input_audio_buffer.commit" + } + RealtimeClientEventOutputAudioBufferClear: + type: object + description: | + **WebRTC Only:** Emit to cut off the current audio response. This will trigger the server to + stop generating audio and emit a `output_audio_buffer.cleared` event. This + event should be preceded by a `response.cancel` client event to stop the + generation of the current response. + [Learn more](/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc). + properties: + event_id: + type: string + description: The unique ID of the client event used for error handling. + type: + type: string + enum: + - output_audio_buffer.clear + description: The event type, must be `output_audio_buffer.clear`. + x-stainless-const: true + required: + - type + x-oaiMeta: + name: output_audio_buffer.clear + group: realtime + example: | + { + "event_id": "optional_client_event_id", + "type": "output_audio_buffer.clear" + } + RealtimeClientEventResponseCancel: + type: object + description: > + Send this event to cancel an in-progress response. The server will + respond + + with a `response.cancelled` event or an error if there is no response + to + + cancel. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - response.cancel + description: The event type, must be `response.cancel`. + x-stainless-const: true + response_id: + type: string + description: | + A specific response ID to cancel - if not provided, will cancel an + in-progress response in the default conversation. + required: + - type + x-oaiMeta: + name: response.cancel + group: realtime + example: | + { + "event_id": "event_567", + "type": "response.cancel" + } + RealtimeClientEventResponseCreate: + type: object + description: > + This event instructs the server to create a Response, which means + triggering + + model inference. When in Server VAD mode, the server will create + Responses + + automatically. + + + A Response will include at least one Item, and may have two, in which + case + + the second will be a function call. These Items will be appended to the + + conversation history. + + + The server will respond with a `response.created` event, events for + Items + + and content created, and finally a `response.done` event to indicate + the + + Response is complete. + + + The `response.create` event includes inference configuration like + + `instructions`, and `temperature`. These fields will override the + Session's + + configuration for this Response only. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - response.create + description: The event type, must be `response.create`. + x-stainless-const: true + response: + $ref: "#/components/schemas/RealtimeResponseCreateParams" + required: + - type + x-oaiMeta: + name: response.create + group: realtime + example: | + { + "event_id": "event_234", + "type": "response.create", + "response": { + "modalities": ["text", "audio"], + "instructions": "Please assist the user.", + "voice": "sage", + "output_audio_format": "pcm16", + "tools": [ + { + "type": "function", + "name": "calculate_sum", + "description": "Calculates the sum of two numbers.", + "parameters": { + "type": "object", + "properties": { + "a": { "type": "number" }, + "b": { "type": "number" } + }, + "required": ["a", "b"] + } + } + ], + "tool_choice": "auto", + "temperature": 0.8, + "max_output_tokens": 1024 + } + } + RealtimeClientEventSessionUpdate: + type: object + description: > + Send this event to update the session’s default configuration. + + The client may send this event at any time to update any field, + + except for `voice`. However, note that once a session has been + + initialized with a particular `model`, it can’t be changed to + + another model using `session.update`. + + + When the server receives a `session.update`, it will respond + + with a `session.updated` event showing the full, effective + configuration. + + Only the fields that are present are updated. To clear a field like + + `instructions`, pass an empty string. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - session.update + description: The event type, must be `session.update`. + x-stainless-const: true + session: + $ref: "#/components/schemas/RealtimeSessionCreateRequest" + required: + - type + - session + x-oaiMeta: + name: session.update + group: realtime + example: | + { + "event_id": "event_123", + "type": "session.update", + "session": { + "modalities": ["text", "audio"], + "instructions": "You are a helpful assistant.", + "voice": "sage", + "input_audio_format": "pcm16", + "output_audio_format": "pcm16", + "input_audio_transcription": { + "model": "whisper-1" + }, + "turn_detection": { + "type": "server_vad", + "threshold": 0.5, + "prefix_padding_ms": 300, + "silence_duration_ms": 500, + "create_response": true + }, + "tools": [ + { + "type": "function", + "name": "get_weather", + "description": "Get the current weather...", + "parameters": { + "type": "object", + "properties": { + "location": { "type": "string" } + }, + "required": ["location"] + } + } + ], + "tool_choice": "auto", + "temperature": 0.8, + "max_response_output_tokens": "inf", + "speed": 1.1, + "tracing": "auto" + } + } + RealtimeClientEventTranscriptionSessionUpdate: + type: object + description: | + Send this event to update a transcription session. + properties: + event_id: + type: string + description: Optional client-generated ID used to identify this event. + type: + type: string + enum: + - transcription_session.update + description: The event type, must be `transcription_session.update`. + x-stainless-const: true + session: + $ref: "#/components/schemas/RealtimeTranscriptionSessionCreateRequest" + required: + - type + - session + x-oaiMeta: + name: transcription_session.update + group: realtime + example: | + { + "type": "transcription_session.update", + "session": { + "input_audio_format": "pcm16", + "input_audio_transcription": { + "model": "gpt-4o-transcribe", + "prompt": "", + "language": "" + }, + "turn_detection": { + "type": "server_vad", + "threshold": 0.5, + "prefix_padding_ms": 300, + "silence_duration_ms": 500, + "create_response": true, + }, + "input_audio_noise_reduction": { + "type": "near_field" + }, + "include": [ + "item.input_audio_transcription.logprobs", + ] + } + } + RealtimeConversationItem: + type: object + description: The item to add to the conversation. + properties: + id: + type: string + description: > + The unique ID of the item, this can be generated by the client to + help + + manage server-side context, but is not required because the server + will + + generate one if not provided. + type: + type: string + enum: + - message + - function_call + - function_call_output + description: > + The type of the item (`message`, `function_call`, + `function_call_output`). + object: + type: string + enum: + - realtime.item + description: > + Identifier for the API object being returned - always + `realtime.item`. + x-stainless-const: true + status: + type: string + enum: + - completed + - incomplete + description: > + The status of the item (`completed`, `incomplete`). These have no + effect + + on the conversation, but are accepted for consistency with the + + `conversation.item.created` event. + role: + type: string + enum: + - user + - assistant + - system + description: > + The role of the message sender (`user`, `assistant`, `system`), + only + + applicable for `message` items. + content: + type: array + description: > + The content of the message, applicable for `message` items. + + - Message items of role `system` support only `input_text` content + + - Message items of role `user` support `input_text` and + `input_audio` + content + - Message items of role `assistant` support `text` content. + items: + type: object + properties: + type: + type: string + enum: + - input_audio + - input_text + - item_reference + - text + description: > + The content type (`input_text`, `input_audio`, + `item_reference`, `text`). + text: + type: string + description: > + The text content, used for `input_text` and `text` content + types. + id: + type: string + description: > + ID of a previous conversation item to reference (for + `item_reference` + + content types in `response.create` events). These can + reference both + + client and server created items. + audio: + type: string + description: > + Base64-encoded audio bytes, used for `input_audio` content + type. + transcript: + type: string + description: > + The transcript of the audio, used for `input_audio` content + type. + call_id: + type: string + description: > + The ID of the function call (for `function_call` and + + `function_call_output` items). If passed on a + `function_call_output` + + item, the server will check that a `function_call` item with the + same + + ID exists in the conversation history. + name: + type: string + description: | + The name of the function being called (for `function_call` items). + arguments: + type: string + description: | + The arguments of the function call (for `function_call` items). + output: + type: string + description: | + The output of the function call (for `function_call_output` items). + RealtimeConversationItemWithReference: + type: object + description: The item to add to the conversation. + properties: + id: + type: string + description: > + For an item of type (`message` | `function_call` | + `function_call_output`) + + this field allows the client to assign the unique ID of the item. It + is + + not required because the server will generate one if not provided. + + + For an item of type `item_reference`, this field is required and is + a + + reference to any item that has previously existed in the + conversation. + type: + type: string + enum: + - message + - function_call + - function_call_output + description: > + The type of the item (`message`, `function_call`, + `function_call_output`, `item_reference`). + object: + type: string + enum: + - realtime.item + description: > + Identifier for the API object being returned - always + `realtime.item`. + x-stainless-const: true + status: + type: string + enum: + - completed + - incomplete + description: > + The status of the item (`completed`, `incomplete`). These have no + effect + + on the conversation, but are accepted for consistency with the + + `conversation.item.created` event. + role: + type: string + enum: + - user + - assistant + - system + description: > + The role of the message sender (`user`, `assistant`, `system`), + only + + applicable for `message` items. + content: + type: array + description: > + The content of the message, applicable for `message` items. + + - Message items of role `system` support only `input_text` content + + - Message items of role `user` support `input_text` and + `input_audio` + content + - Message items of role `assistant` support `text` content. + items: + type: object + properties: + type: + type: string + enum: + - input_audio + - input_text + - item_reference + - text + description: > + The content type (`input_text`, `input_audio`, + `item_reference`, `text`). + text: + type: string + description: > + The text content, used for `input_text` and `text` content + types. + id: + type: string + description: > + ID of a previous conversation item to reference (for + `item_reference` + + content types in `response.create` events). These can + reference both + + client and server created items. + audio: + type: string + description: > + Base64-encoded audio bytes, used for `input_audio` content + type. + transcript: + type: string + description: > + The transcript of the audio, used for `input_audio` content + type. + call_id: + type: string + description: > + The ID of the function call (for `function_call` and + + `function_call_output` items). If passed on a + `function_call_output` + + item, the server will check that a `function_call` item with the + same + + ID exists in the conversation history. + name: + type: string + description: | + The name of the function being called (for `function_call` items). + arguments: + type: string + description: | + The arguments of the function call (for `function_call` items). + output: + type: string + description: | + The output of the function call (for `function_call_output` items). + RealtimeResponse: + type: object + description: The response resource. + properties: + id: + type: string + description: The unique ID of the response. + object: + type: string + enum: + - realtime.response + description: The object type, must be `realtime.response`. + x-stainless-const: true + status: + type: string + enum: + - completed + - cancelled + - failed + - incomplete + description: > + The final status of the response (`completed`, `cancelled`, + `failed`, or + + `incomplete`). + status_details: + type: object + description: Additional details about the status. + properties: + type: + type: string + enum: + - completed + - cancelled + - failed + - incomplete + description: > + The type of error that caused the response to fail, + corresponding + + with the `status` field (`completed`, `cancelled`, + `incomplete`, + + `failed`). + reason: + type: string + enum: + - turn_detected + - client_cancelled + - max_output_tokens + - content_filter + description: > + The reason the Response did not complete. For a `cancelled` + Response, + + one of `turn_detected` (the server VAD detected a new start of + speech) + + or `client_cancelled` (the client sent a cancel event). For an + + `incomplete` Response, one of `max_output_tokens` or + `content_filter` + + (the server-side safety filter activated and cut off the + response). + error: + type: object + description: | + A description of the error that caused the response to fail, + populated when the `status` is `failed`. + properties: + type: + type: string + description: The type of error. + code: + type: string + description: Error code, if any. + output: + type: array + description: The list of output items generated by the response. + items: + $ref: "#/components/schemas/RealtimeConversationItem" + metadata: + $ref: "#/components/schemas/Metadata" + usage: + type: object + description: > + Usage statistics for the Response, this will correspond to billing. + A + + Realtime API session will maintain a conversation context and append + new + + Items to the Conversation, thus output from previous turns (text + and + + audio tokens) will become the input for later turns. + properties: + total_tokens: + type: integer + description: > + The total number of tokens in the Response including input and + output + + text and audio tokens. + input_tokens: + type: integer + description: > + The number of input tokens used in the Response, including text + and + + audio tokens. + output_tokens: + type: integer + description: > + The number of output tokens sent in the Response, including text + and + + audio tokens. + input_token_details: + type: object + description: Details about the input tokens used in the Response. + properties: + cached_tokens: + type: integer + description: The number of cached tokens used in the Response. + text_tokens: + type: integer + description: The number of text tokens used in the Response. + audio_tokens: + type: integer + description: The number of audio tokens used in the Response. + output_token_details: + type: object + description: Details about the output tokens used in the Response. + properties: + text_tokens: + type: integer + description: The number of text tokens used in the Response. + audio_tokens: + type: integer + description: The number of audio tokens used in the Response. + conversation_id: + description: > + Which conversation the response is added to, determined by the + `conversation` + + field in the `response.create` event. If `auto`, the response will + be added to + + the default conversation and the value of `conversation_id` will be + an id like + + `conv_1234`. If `none`, the response will not be added to any + conversation and + + the value of `conversation_id` will be `null`. If responses are + being triggered + + by server VAD, the response will be added to the default + conversation, thus + + the `conversation_id` will be an id like `conv_1234`. + type: string + voice: + $ref: "#/components/schemas/VoiceIdsShared" + description: > + The voice the model used to respond. + + Current voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, + `fable`, + + `onyx`, `nova`, `sage`, `shimmer`, and `verse`. + modalities: + type: array + description: > + The set of modalities the model used to respond. If there are + multiple modalities, + + the model will pick one, for example if `modalities` is `["text", + "audio"]`, the model + + could be responding in either text or audio. + items: + type: string + enum: + - text + - audio + output_audio_format: + type: string + enum: + - pcm16 + - g711_ulaw + - g711_alaw + description: > + The format of output audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + temperature: + type: number + description: > + Sampling temperature for the model, limited to [0.6, 1.2]. Defaults + to 0.8. + max_output_tokens: + oneOf: + - type: integer + - type: string + enum: + - inf + x-stainless-const: true + description: | + Maximum number of output tokens for a single assistant response, + inclusive of tool calls, that was used in this response. + RealtimeResponseCreateParams: + type: object + description: Create a new Realtime response with these parameters + properties: + modalities: + type: array + description: | + The set of modalities the model can respond with. To disable audio, + set this to ["text"]. + items: + type: string + enum: + - text + - audio + instructions: + type: string + description: > + The default system instructions (i.e. system message) prepended to + model + + calls. This field allows the client to guide the model on desired + + responses. The model can be instructed on response content and + format, + + (e.g. "be extremely succinct", "act friendly", "here are examples of + good + + responses") and on audio behavior (e.g. "talk quickly", "inject + emotion + + into your voice", "laugh frequently"). The instructions are not + guaranteed + + to be followed by the model, but they provide guidance to the model + on the + + desired behavior. + + + Note that the server sets default instructions which will be used if + this + + field is not set and are visible in the `session.created` event at + the + + start of the session. + voice: + $ref: "#/components/schemas/VoiceIdsShared" + description: > + The voice the model uses to respond. Voice cannot be changed during + the + + session once the model has responded with audio at least once. + Current + + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, + `fable`, + + `onyx`, `nova`, `sage`, `shimmer`, and `verse`. + output_audio_format: + type: string + enum: + - pcm16 + - g711_ulaw + - g711_alaw + description: > + The format of output audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + tools: + type: array + description: Tools (functions) available to the model. + items: + type: object + properties: + type: + type: string + enum: + - function + description: The type of the tool, i.e. `function`. + x-stainless-const: true + name: + type: string + description: The name of the function. + description: + type: string + description: > + The description of the function, including guidance on when + and how + + to call it, and guidance about what to tell the user when + calling + + (if anything). + parameters: + type: object + description: Parameters of the function in JSON Schema. + tool_choice: + type: string + description: > + How the model chooses tools. Options are `auto`, `none`, `required`, + or + + specify a function, like `{"type": "function", "function": {"name": + "my_function"}}`. + temperature: + type: number + description: > + Sampling temperature for the model, limited to [0.6, 1.2]. Defaults + to 0.8. + max_response_output_tokens: + oneOf: + - type: integer + - type: string + enum: + - inf + x-stainless-const: true + description: | + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + conversation: + description: > + Controls which conversation the response is added to. Currently + supports + + `auto` and `none`, with `auto` as the default value. The `auto` + value + + means that the contents of the response will be added to the default + + conversation. Set this to `none` to create an out-of-band response + which + + will not add items to default conversation. + oneOf: + - type: string + - type: string + default: auto + enum: + - auto + - none + metadata: + $ref: "#/components/schemas/Metadata" + input: + type: array + description: > + Input items to include in the prompt for the model. Using this field + + creates a new context for this Response instead of using the default + + conversation. An empty array `[]` will clear the context for this + Response. + + Note that this can include references to items from the default + conversation. + items: + $ref: "#/components/schemas/RealtimeConversationItemWithReference" + RealtimeServerEvent: + discriminator: + propertyName: type + description: | + A realtime server event. + anyOf: + - $ref: "#/components/schemas/RealtimeServerEventConversationCreated" + - $ref: "#/components/schemas/RealtimeServerEventConversationItemCreated" + - $ref: "#/components/schemas/RealtimeServerEventConversationItemDeleted" + - $ref: "#/components/schemas/RealtimeServerEventConversationItemInputAudioTransc\ + riptionCompleted" + - $ref: "#/components/schemas/RealtimeServerEventConversationItemInputAudioTransc\ + riptionDelta" + - $ref: "#/components/schemas/RealtimeServerEventConversationItemInputAudioTransc\ + riptionFailed" + - $ref: "#/components/schemas/RealtimeServerEventConversationItemRetrieved" + - $ref: "#/components/schemas/RealtimeServerEventConversationItemTruncated" + - $ref: "#/components/schemas/RealtimeServerEventError" + - $ref: "#/components/schemas/RealtimeServerEventInputAudioBufferCleared" + - $ref: "#/components/schemas/RealtimeServerEventInputAudioBufferCommitted" + - $ref: "#/components/schemas/RealtimeServerEventInputAudioBufferSpeechStarted" + - $ref: "#/components/schemas/RealtimeServerEventInputAudioBufferSpeechStopped" + - $ref: "#/components/schemas/RealtimeServerEventRateLimitsUpdated" + - $ref: "#/components/schemas/RealtimeServerEventResponseAudioDelta" + - $ref: "#/components/schemas/RealtimeServerEventResponseAudioDone" + - $ref: "#/components/schemas/RealtimeServerEventResponseAudioTranscriptDelta" + - $ref: "#/components/schemas/RealtimeServerEventResponseAudioTranscriptDone" + - $ref: "#/components/schemas/RealtimeServerEventResponseContentPartAdded" + - $ref: "#/components/schemas/RealtimeServerEventResponseContentPartDone" + - $ref: "#/components/schemas/RealtimeServerEventResponseCreated" + - $ref: "#/components/schemas/RealtimeServerEventResponseDone" + - $ref: "#/components/schemas/RealtimeServerEventResponseFunctionCallArgumentsDel\ + ta" + - $ref: "#/components/schemas/RealtimeServerEventResponseFunctionCallArgumentsDon\ + e" + - $ref: "#/components/schemas/RealtimeServerEventResponseOutputItemAdded" + - $ref: "#/components/schemas/RealtimeServerEventResponseOutputItemDone" + - $ref: "#/components/schemas/RealtimeServerEventResponseTextDelta" + - $ref: "#/components/schemas/RealtimeServerEventResponseTextDone" + - $ref: "#/components/schemas/RealtimeServerEventSessionCreated" + - $ref: "#/components/schemas/RealtimeServerEventSessionUpdated" + - $ref: "#/components/schemas/RealtimeServerEventTranscriptionSessionUpdated" + - $ref: "#/components/schemas/RealtimeServerEventOutputAudioBufferStarted" + - $ref: "#/components/schemas/RealtimeServerEventOutputAudioBufferStopped" + - $ref: "#/components/schemas/RealtimeServerEventOutputAudioBufferCleared" + RealtimeServerEventConversationCreated: + type: object + description: > + Returned when a conversation is created. Emitted right after session + creation. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.created + description: The event type, must be `conversation.created`. + x-stainless-const: true + conversation: + type: object + description: The conversation resource. + properties: + id: + type: string + description: The unique ID of the conversation. + object: + type: string + description: The object type, must be `realtime.conversation`. + required: + - event_id + - type + - conversation + x-oaiMeta: + name: conversation.created + group: realtime + example: | + { + "event_id": "event_9101", + "type": "conversation.created", + "conversation": { + "id": "conv_001", + "object": "realtime.conversation" + } + } + RealtimeServerEventConversationItemCreated: + type: object + description: > + Returned when a conversation item is created. There are several + scenarios that produce this event: + - The server is generating a Response, which if successful will produce + either one or two Items, which will be of type `message` + (role `assistant`) or type `function_call`. + - The input audio buffer has been committed, either by the client or the + server (in `server_vad` mode). The server will take the content of the + input audio buffer and add it to a new user message Item. + - The client has sent a `conversation.item.create` event to add a new Item + to the Conversation. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.created + description: The event type, must be `conversation.item.created`. + x-stainless-const: true + previous_item_id: + type: string + description: > + The ID of the preceding item in the Conversation context, allows + the + + client to understand the order of the conversation. + item: + $ref: "#/components/schemas/RealtimeConversationItem" + required: + - event_id + - type + - previous_item_id + - item + x-oaiMeta: + name: conversation.item.created + group: realtime + example: | + { + "event_id": "event_1920", + "type": "conversation.item.created", + "previous_item_id": "msg_002", + "item": { + "id": "msg_003", + "object": "realtime.item", + "type": "message", + "status": "completed", + "role": "user", + "content": [] + } + } + RealtimeServerEventConversationItemDeleted: + type: object + description: > + Returned when an item in the conversation is deleted by the client with + a + + `conversation.item.delete` event. This event is used to synchronize the + + server's understanding of the conversation history with the client's + view. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.deleted + description: The event type, must be `conversation.item.deleted`. + x-stainless-const: true + item_id: + type: string + description: The ID of the item that was deleted. + required: + - event_id + - type + - item_id + x-oaiMeta: + name: conversation.item.deleted + group: realtime + example: | + { + "event_id": "event_2728", + "type": "conversation.item.deleted", + "item_id": "msg_005" + } + RealtimeServerEventConversationItemInputAudioTranscriptionCompleted: + type: object + description: > + This event is the output of audio transcription for user audio written + to the + + user audio buffer. Transcription begins when the input audio buffer is + + committed by the client or server (in `server_vad` mode). Transcription + runs + + asynchronously with Response creation, so this event may come before or + after + + the Response events. + + + Realtime API models accept audio natively, and thus input transcription + is a + + separate process run on a separate ASR (Automatic Speech Recognition) + model, + + currently always `whisper-1`. Thus the transcript may diverge somewhat + from + + the model's interpretation, and should be treated as a rough guide. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.input_audio_transcription.completed + description: | + The event type, must be + `conversation.item.input_audio_transcription.completed`. + x-stainless-const: true + item_id: + type: string + description: The ID of the user message item containing the audio. + content_index: + type: integer + description: The index of the content part containing the audio. + transcript: + type: string + description: The transcribed text. + logprobs: + type: array + description: The log probabilities of the transcription. + nullable: true + items: + $ref: "#/components/schemas/LogProbProperties" + required: + - event_id + - type + - item_id + - content_index + - transcript + x-oaiMeta: + name: conversation.item.input_audio_transcription.completed + group: realtime + example: | + { + "event_id": "event_2122", + "type": "conversation.item.input_audio_transcription.completed", + "item_id": "msg_003", + "content_index": 0, + "transcript": "Hello, how are you?" + } + RealtimeServerEventConversationItemInputAudioTranscriptionDelta: + type: object + description: > + Returned when the text value of an input audio transcription content + part is updated. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.input_audio_transcription.delta + description: The event type, must be + `conversation.item.input_audio_transcription.delta`. + x-stainless-const: true + item_id: + type: string + description: The ID of the item. + content_index: + type: integer + description: The index of the content part in the item's content array. + delta: + type: string + description: The text delta. + logprobs: + type: array + description: The log probabilities of the transcription. + nullable: true + items: + $ref: "#/components/schemas/LogProbProperties" + required: + - event_id + - type + - item_id + x-oaiMeta: + name: conversation.item.input_audio_transcription.delta + group: realtime + example: | + { + "type": "conversation.item.input_audio_transcription.delta", + "event_id": "event_001", + "item_id": "item_001", + "content_index": 0, + "delta": "Hello" + } + RealtimeServerEventConversationItemInputAudioTranscriptionFailed: + type: object + description: > + Returned when input audio transcription is configured, and a + transcription + + request for a user message failed. These events are separate from other + + `error` events so that the client can identify the related Item. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.input_audio_transcription.failed + description: | + The event type, must be + `conversation.item.input_audio_transcription.failed`. + x-stainless-const: true + item_id: + type: string + description: The ID of the user message item. + content_index: + type: integer + description: The index of the content part containing the audio. + error: + type: object + description: Details of the transcription error. + properties: + type: + type: string + description: The type of error. + code: + type: string + description: Error code, if any. + message: + type: string + description: A human-readable error message. + param: + type: string + description: Parameter related to the error, if any. + required: + - event_id + - type + - item_id + - content_index + - error + x-oaiMeta: + name: conversation.item.input_audio_transcription.failed + group: realtime + example: | + { + "event_id": "event_2324", + "type": "conversation.item.input_audio_transcription.failed", + "item_id": "msg_003", + "content_index": 0, + "error": { + "type": "transcription_error", + "code": "audio_unintelligible", + "message": "The audio could not be transcribed.", + "param": null + } + } + RealtimeServerEventConversationItemRetrieved: + type: object + description: > + Returned when a conversation item is retrieved with + `conversation.item.retrieve`. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.retrieved + description: The event type, must be `conversation.item.retrieved`. + x-stainless-const: true + item: + $ref: "#/components/schemas/RealtimeConversationItem" + required: + - event_id + - type + - item + x-oaiMeta: + name: conversation.item.retrieved + group: realtime + example: | + { + "event_id": "event_1920", + "type": "conversation.item.created", + "previous_item_id": "msg_002", + "item": { + "id": "msg_003", + "object": "realtime.item", + "type": "message", + "status": "completed", + "role": "user", + "content": [ + { + "type": "input_audio", + "transcript": "hello how are you", + "audio": "base64encodedaudio==" + } + ] + } + } + RealtimeServerEventConversationItemTruncated: + type: object + description: > + Returned when an earlier assistant audio message item is truncated by + the + + client with a `conversation.item.truncate` event. This event is used to + + synchronize the server's understanding of the audio with the client's + playback. + + + This action will truncate the audio and remove the server-side text + transcript + + to ensure there is no text in the context that hasn't been heard by the + user. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - conversation.item.truncated + description: The event type, must be `conversation.item.truncated`. + x-stainless-const: true + item_id: + type: string + description: The ID of the assistant message item that was truncated. + content_index: + type: integer + description: The index of the content part that was truncated. + audio_end_ms: + type: integer + description: | + The duration up to which the audio was truncated, in milliseconds. + required: + - event_id + - type + - item_id + - content_index + - audio_end_ms + x-oaiMeta: + name: conversation.item.truncated + group: realtime + example: | + { + "event_id": "event_2526", + "type": "conversation.item.truncated", + "item_id": "msg_004", + "content_index": 0, + "audio_end_ms": 1500 + } + RealtimeServerEventError: + type: object + description: > + Returned when an error occurs, which could be a client problem or a + server + + problem. Most errors are recoverable and the session will stay open, we + + recommend to implementors to monitor and log error messages by default. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - error + description: The event type, must be `error`. + x-stainless-const: true + error: + type: object + description: Details of the error. + required: + - type + - message + properties: + type: + type: string + description: > + The type of error (e.g., "invalid_request_error", + "server_error"). + code: + type: string + description: Error code, if any. + nullable: true + message: + type: string + description: A human-readable error message. + param: + type: string + description: Parameter related to the error, if any. + nullable: true + event_id: + type: string + description: > + The event_id of the client event that caused the error, if + applicable. + nullable: true + required: + - event_id + - type + - error + x-oaiMeta: + name: error + group: realtime + example: | + { + "event_id": "event_890", + "type": "error", + "error": { + "type": "invalid_request_error", + "code": "invalid_event", + "message": "The 'type' field is missing.", + "param": null, + "event_id": "event_567" + } + } + RealtimeServerEventInputAudioBufferCleared: + type: object + description: | + Returned when the input audio buffer is cleared by the client with a + `input_audio_buffer.clear` event. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - input_audio_buffer.cleared + description: The event type, must be `input_audio_buffer.cleared`. + x-stainless-const: true + required: + - event_id + - type + x-oaiMeta: + name: input_audio_buffer.cleared + group: realtime + example: | + { + "event_id": "event_1314", + "type": "input_audio_buffer.cleared" + } + RealtimeServerEventInputAudioBufferCommitted: + type: object + description: > + Returned when an input audio buffer is committed, either by the client + or + + automatically in server VAD mode. The `item_id` property is the ID of + the user + + message item that will be created, thus a `conversation.item.created` + event + + will also be sent to the client. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - input_audio_buffer.committed + description: The event type, must be `input_audio_buffer.committed`. + x-stainless-const: true + previous_item_id: + type: string + description: > + The ID of the preceding item after which the new item will be + inserted. + item_id: + type: string + description: The ID of the user message item that will be created. + required: + - event_id + - type + - previous_item_id + - item_id + x-oaiMeta: + name: input_audio_buffer.committed + group: realtime + example: | + { + "event_id": "event_1121", + "type": "input_audio_buffer.committed", + "previous_item_id": "msg_001", + "item_id": "msg_002" + } + RealtimeServerEventInputAudioBufferSpeechStarted: + type: object + description: > + Sent by the server when in `server_vad` mode to indicate that speech has + been + + detected in the audio buffer. This can happen any time audio is added to + the + + buffer (unless speech is already detected). The client may want to use + this + + event to interrupt audio playback or provide visual feedback to the + user. + + + The client should expect to receive a + `input_audio_buffer.speech_stopped` event + + when speech stops. The `item_id` property is the ID of the user message + item + + that will be created when speech stops and will also be included in the + + `input_audio_buffer.speech_stopped` event (unless the client manually + commits + + the audio buffer during VAD activation). + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - input_audio_buffer.speech_started + description: The event type, must be `input_audio_buffer.speech_started`. + x-stainless-const: true + audio_start_ms: + type: integer + description: > + Milliseconds from the start of all audio written to the buffer + during the + + session when speech was first detected. This will correspond to the + + beginning of audio sent to the model, and thus includes the + + `prefix_padding_ms` configured in the Session. + item_id: + type: string + description: > + The ID of the user message item that will be created when speech + stops. + required: + - event_id + - type + - audio_start_ms + - item_id + x-oaiMeta: + name: input_audio_buffer.speech_started + group: realtime + example: | + { + "event_id": "event_1516", + "type": "input_audio_buffer.speech_started", + "audio_start_ms": 1000, + "item_id": "msg_003" + } + RealtimeServerEventInputAudioBufferSpeechStopped: + type: object + description: > + Returned in `server_vad` mode when the server detects the end of speech + in + + the audio buffer. The server will also send an + `conversation.item.created` + + event with the user message item that is created from the audio buffer. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - input_audio_buffer.speech_stopped + description: The event type, must be `input_audio_buffer.speech_stopped`. + x-stainless-const: true + audio_end_ms: + type: integer + description: > + Milliseconds since the session started when speech stopped. This + will + + correspond to the end of audio sent to the model, and thus includes + the + + `min_silence_duration_ms` configured in the Session. + item_id: + type: string + description: The ID of the user message item that will be created. + required: + - event_id + - type + - audio_end_ms + - item_id + x-oaiMeta: + name: input_audio_buffer.speech_stopped + group: realtime + example: | + { + "event_id": "event_1718", + "type": "input_audio_buffer.speech_stopped", + "audio_end_ms": 2000, + "item_id": "msg_003" + } + RealtimeServerEventOutputAudioBufferCleared: + type: object + description: | + **WebRTC Only:** Emitted when the output audio buffer is cleared. This happens either in VAD + mode when the user has interrupted (`input_audio_buffer.speech_started`), + or when the client has emitted the `output_audio_buffer.clear` event to manually + cut off the current audio response. + [Learn more](/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc). + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - output_audio_buffer.cleared + description: The event type, must be `output_audio_buffer.cleared`. + x-stainless-const: true + response_id: + type: string + description: The unique ID of the response that produced the audio. + required: + - event_id + - type + - response_id + x-oaiMeta: + name: output_audio_buffer.cleared + group: realtime + example: | + { + "event_id": "event_abc123", + "type": "output_audio_buffer.cleared", + "response_id": "resp_abc123" + } + RealtimeServerEventOutputAudioBufferStarted: + type: object + description: | + **WebRTC Only:** Emitted when the server begins streaming audio to the client. This event is + emitted after an audio content part has been added (`response.content_part.added`) + to the response. + [Learn more](/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc). + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - output_audio_buffer.started + description: The event type, must be `output_audio_buffer.started`. + x-stainless-const: true + response_id: + type: string + description: The unique ID of the response that produced the audio. + required: + - event_id + - type + - response_id + x-oaiMeta: + name: output_audio_buffer.started + group: realtime + example: | + { + "event_id": "event_abc123", + "type": "output_audio_buffer.started", + "response_id": "resp_abc123" + } + RealtimeServerEventOutputAudioBufferStopped: + type: object + description: | + **WebRTC Only:** Emitted when the output audio buffer has been completely drained on the server, + and no more audio is forthcoming. This event is emitted after the full response + data has been sent to the client (`response.done`). + [Learn more](/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc). + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - output_audio_buffer.stopped + description: The event type, must be `output_audio_buffer.stopped`. + x-stainless-const: true + response_id: + type: string + description: The unique ID of the response that produced the audio. + required: + - event_id + - type + - response_id + x-oaiMeta: + name: output_audio_buffer.stopped + group: realtime + example: | + { + "event_id": "event_abc123", + "type": "output_audio_buffer.stopped", + "response_id": "resp_abc123" + } + RealtimeServerEventRateLimitsUpdated: + type: object + description: > + Emitted at the beginning of a Response to indicate the updated rate + limits. + + When a Response is created some tokens will be "reserved" for the + output + + tokens, the rate limits shown here reflect that reservation, which is + then + + adjusted accordingly once the Response is completed. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - rate_limits.updated + description: The event type, must be `rate_limits.updated`. + x-stainless-const: true + rate_limits: + type: array + description: List of rate limit information. + items: + type: object + properties: + name: + type: string + enum: + - requests + - tokens + description: | + The name of the rate limit (`requests`, `tokens`). + limit: + type: integer + description: The maximum allowed value for the rate limit. + remaining: + type: integer + description: The remaining value before the limit is reached. + reset_seconds: + type: number + description: Seconds until the rate limit resets. + required: + - event_id + - type + - rate_limits + x-oaiMeta: + name: rate_limits.updated + group: realtime + example: | + { + "event_id": "event_5758", + "type": "rate_limits.updated", + "rate_limits": [ + { + "name": "requests", + "limit": 1000, + "remaining": 999, + "reset_seconds": 60 + }, + { + "name": "tokens", + "limit": 50000, + "remaining": 49950, + "reset_seconds": 60 + } + ] + } + RealtimeServerEventResponseAudioDelta: + type: object + description: Returned when the model-generated audio is updated. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.audio.delta + description: The event type, must be `response.audio.delta`. + x-stainless-const: true + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + delta: + type: string + description: Base64-encoded audio data delta. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - delta + x-oaiMeta: + name: response.audio.delta + group: realtime + example: | + { + "event_id": "event_4950", + "type": "response.audio.delta", + "response_id": "resp_001", + "item_id": "msg_008", + "output_index": 0, + "content_index": 0, + "delta": "Base64EncodedAudioDelta" + } + RealtimeServerEventResponseAudioDone: + type: object + description: > + Returned when the model-generated audio is done. Also emitted when a + Response + + is interrupted, incomplete, or cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.audio.done + description: The event type, must be `response.audio.done`. + x-stainless-const: true + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + x-oaiMeta: + name: response.audio.done + group: realtime + example: | + { + "event_id": "event_5152", + "type": "response.audio.done", + "response_id": "resp_001", + "item_id": "msg_008", + "output_index": 0, + "content_index": 0 + } + RealtimeServerEventResponseAudioTranscriptDelta: + type: object + description: > + Returned when the model-generated transcription of audio output is + updated. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.audio_transcript.delta + description: The event type, must be `response.audio_transcript.delta`. + x-stainless-const: true + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + delta: + type: string + description: The transcript delta. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - delta + x-oaiMeta: + name: response.audio_transcript.delta + group: realtime + example: | + { + "event_id": "event_4546", + "type": "response.audio_transcript.delta", + "response_id": "resp_001", + "item_id": "msg_008", + "output_index": 0, + "content_index": 0, + "delta": "Hello, how can I a" + } + RealtimeServerEventResponseAudioTranscriptDone: + type: object + description: | + Returned when the model-generated transcription of audio output is done + streaming. Also emitted when a Response is interrupted, incomplete, or + cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.audio_transcript.done + description: The event type, must be `response.audio_transcript.done`. + x-stainless-const: true + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + transcript: + type: string + description: The final transcript of the audio. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - transcript + x-oaiMeta: + name: response.audio_transcript.done + group: realtime + example: | + { + "event_id": "event_4748", + "type": "response.audio_transcript.done", + "response_id": "resp_001", + "item_id": "msg_008", + "output_index": 0, + "content_index": 0, + "transcript": "Hello, how can I assist you today?" + } + RealtimeServerEventResponseContentPartAdded: + type: object + description: > + Returned when a new content part is added to an assistant message item + during + + response generation. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.content_part.added + description: The event type, must be `response.content_part.added`. + x-stainless-const: true + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item to which the content part was added. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + part: + type: object + description: The content part that was added. + properties: + type: + type: string + enum: + - audio + - text + description: The content type ("text", "audio"). + text: + type: string + description: The text content (if type is "text"). + audio: + type: string + description: Base64-encoded audio data (if type is "audio"). + transcript: + type: string + description: The transcript of the audio (if type is "audio"). + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - part + x-oaiMeta: + name: response.content_part.added + group: realtime + example: | + { + "event_id": "event_3738", + "type": "response.content_part.added", + "response_id": "resp_001", + "item_id": "msg_007", + "output_index": 0, + "content_index": 0, + "part": { + "type": "text", + "text": "" + } + } + RealtimeServerEventResponseContentPartDone: + type: object + description: > + Returned when a content part is done streaming in an assistant message + item. + + Also emitted when a Response is interrupted, incomplete, or cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.content_part.done + description: The event type, must be `response.content_part.done`. + x-stainless-const: true + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + part: + type: object + description: The content part that is done. + properties: + type: + type: string + enum: + - audio + - text + description: The content type ("text", "audio"). + text: + type: string + description: The text content (if type is "text"). + audio: + type: string + description: Base64-encoded audio data (if type is "audio"). + transcript: + type: string + description: The transcript of the audio (if type is "audio"). + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - part + x-oaiMeta: + name: response.content_part.done + group: realtime + example: | + { + "event_id": "event_3940", + "type": "response.content_part.done", + "response_id": "resp_001", + "item_id": "msg_007", + "output_index": 0, + "content_index": 0, + "part": { + "type": "text", + "text": "Sure, I can help with that." + } + } + RealtimeServerEventResponseCreated: + type: object + description: > + Returned when a new Response is created. The first event of response + creation, + + where the response is in an initial state of `in_progress`. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.created + description: The event type, must be `response.created`. + x-stainless-const: true + response: + $ref: "#/components/schemas/RealtimeResponse" + required: + - event_id + - type + - response + x-oaiMeta: + name: response.created + group: realtime + example: | + { + "event_id": "event_2930", + "type": "response.created", + "response": { + "id": "resp_001", + "object": "realtime.response", + "status": "in_progress", + "status_details": null, + "output": [], + "usage": null + } + } + RealtimeServerEventResponseDone: + type: object + description: > + Returned when a Response is done streaming. Always emitted, no matter + the + + final state. The Response object included in the `response.done` event + will + + include all output Items in the Response but will omit the raw audio + data. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.done + description: The event type, must be `response.done`. + x-stainless-const: true + response: + $ref: "#/components/schemas/RealtimeResponse" + required: + - event_id + - type + - response + x-oaiMeta: + name: response.done + group: realtime + example: | + { + "event_id": "event_3132", + "type": "response.done", + "response": { + "id": "resp_001", + "object": "realtime.response", + "status": "completed", + "status_details": null, + "output": [ + { + "id": "msg_006", + "object": "realtime.item", + "type": "message", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "text", + "text": "Sure, how can I assist you today?" + } + ] + } + ], + "usage": { + "total_tokens":275, + "input_tokens":127, + "output_tokens":148, + "input_token_details": { + "cached_tokens":384, + "text_tokens":119, + "audio_tokens":8, + "cached_tokens_details": { + "text_tokens": 128, + "audio_tokens": 256 + } + }, + "output_token_details": { + "text_tokens":36, + "audio_tokens":112 + } + } + } + } + RealtimeServerEventResponseFunctionCallArgumentsDelta: + type: object + description: | + Returned when the model-generated function call arguments are updated. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.function_call_arguments.delta + description: | + The event type, must be `response.function_call_arguments.delta`. + x-stainless-const: true + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the function call item. + output_index: + type: integer + description: The index of the output item in the response. + call_id: + type: string + description: The ID of the function call. + delta: + type: string + description: The arguments delta as a JSON string. + required: + - event_id + - type + - response_id + - item_id + - output_index + - call_id + - delta + x-oaiMeta: + name: response.function_call_arguments.delta + group: realtime + example: | + { + "event_id": "event_5354", + "type": "response.function_call_arguments.delta", + "response_id": "resp_002", + "item_id": "fc_001", + "output_index": 0, + "call_id": "call_001", + "delta": "{\"location\": \"San\"" + } + RealtimeServerEventResponseFunctionCallArgumentsDone: + type: object + description: > + Returned when the model-generated function call arguments are done + streaming. + + Also emitted when a Response is interrupted, incomplete, or cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.function_call_arguments.done + description: | + The event type, must be `response.function_call_arguments.done`. + x-stainless-const: true + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the function call item. + output_index: + type: integer + description: The index of the output item in the response. + call_id: + type: string + description: The ID of the function call. + arguments: + type: string + description: The final arguments as a JSON string. + required: + - event_id + - type + - response_id + - item_id + - output_index + - call_id + - arguments + x-oaiMeta: + name: response.function_call_arguments.done + group: realtime + example: | + { + "event_id": "event_5556", + "type": "response.function_call_arguments.done", + "response_id": "resp_002", + "item_id": "fc_001", + "output_index": 0, + "call_id": "call_001", + "arguments": "{\"location\": \"San Francisco\"}" + } + RealtimeServerEventResponseOutputItemAdded: + type: object + description: Returned when a new Item is created during Response generation. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.output_item.added + description: The event type, must be `response.output_item.added`. + x-stainless-const: true + response_id: + type: string + description: The ID of the Response to which the item belongs. + output_index: + type: integer + description: The index of the output item in the Response. + item: + $ref: "#/components/schemas/RealtimeConversationItem" + required: + - event_id + - type + - response_id + - output_index + - item + x-oaiMeta: + name: response.output_item.added + group: realtime + example: | + { + "event_id": "event_3334", + "type": "response.output_item.added", + "response_id": "resp_001", + "output_index": 0, + "item": { + "id": "msg_007", + "object": "realtime.item", + "type": "message", + "status": "in_progress", + "role": "assistant", + "content": [] + } + } + RealtimeServerEventResponseOutputItemDone: + type: object + description: > + Returned when an Item is done streaming. Also emitted when a Response + is + + interrupted, incomplete, or cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.output_item.done + description: The event type, must be `response.output_item.done`. + x-stainless-const: true + response_id: + type: string + description: The ID of the Response to which the item belongs. + output_index: + type: integer + description: The index of the output item in the Response. + item: + $ref: "#/components/schemas/RealtimeConversationItem" + required: + - event_id + - type + - response_id + - output_index + - item + x-oaiMeta: + name: response.output_item.done + group: realtime + example: | + { + "event_id": "event_3536", + "type": "response.output_item.done", + "response_id": "resp_001", + "output_index": 0, + "item": { + "id": "msg_007", + "object": "realtime.item", + "type": "message", + "status": "completed", + "role": "assistant", + "content": [ + { + "type": "text", + "text": "Sure, I can help with that." + } + ] + } + } + RealtimeServerEventResponseTextDelta: + type: object + description: Returned when the text value of a "text" content part is updated. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.text.delta + description: The event type, must be `response.text.delta`. + x-stainless-const: true + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + delta: + type: string + description: The text delta. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - delta + x-oaiMeta: + name: response.text.delta + group: realtime + example: | + { + "event_id": "event_4142", + "type": "response.text.delta", + "response_id": "resp_001", + "item_id": "msg_007", + "output_index": 0, + "content_index": 0, + "delta": "Sure, I can h" + } + RealtimeServerEventResponseTextDone: + type: object + description: > + Returned when the text value of a "text" content part is done streaming. + Also + + emitted when a Response is interrupted, incomplete, or cancelled. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - response.text.done + description: The event type, must be `response.text.done`. + x-stainless-const: true + response_id: + type: string + description: The ID of the response. + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item in the response. + content_index: + type: integer + description: The index of the content part in the item's content array. + text: + type: string + description: The final text content. + required: + - event_id + - type + - response_id + - item_id + - output_index + - content_index + - text + x-oaiMeta: + name: response.text.done + group: realtime + example: | + { + "event_id": "event_4344", + "type": "response.text.done", + "response_id": "resp_001", + "item_id": "msg_007", + "output_index": 0, + "content_index": 0, + "text": "Sure, I can help with that." + } + RealtimeServerEventSessionCreated: + type: object + description: > + Returned when a Session is created. Emitted automatically when a new + + connection is established as the first server event. This event will + contain + + the default Session configuration. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - session.created + description: The event type, must be `session.created`. + x-stainless-const: true + session: + $ref: "#/components/schemas/RealtimeSession" + required: + - event_id + - type + - session + x-oaiMeta: + name: session.created + group: realtime + example: | + { + "event_id": "event_1234", + "type": "session.created", + "session": { + "id": "sess_001", + "object": "realtime.session", + "model": "gpt-4o-realtime-preview", + "modalities": ["text", "audio"], + "instructions": "...model instructions here...", + "voice": "sage", + "input_audio_format": "pcm16", + "output_audio_format": "pcm16", + "input_audio_transcription": null, + "turn_detection": { + "type": "server_vad", + "threshold": 0.5, + "prefix_padding_ms": 300, + "silence_duration_ms": 200 + }, + "tools": [], + "tool_choice": "auto", + "temperature": 0.8, + "max_response_output_tokens": "inf", + "speed": 1.1, + "tracing": "auto" + } + } + RealtimeServerEventSessionUpdated: + type: object + description: > + Returned when a session is updated with a `session.update` event, + unless + + there is an error. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - session.updated + description: The event type, must be `session.updated`. + x-stainless-const: true + session: + $ref: "#/components/schemas/RealtimeSession" + required: + - event_id + - type + - session + x-oaiMeta: + name: session.updated + group: realtime + example: | + { + "event_id": "event_5678", + "type": "session.updated", + "session": { + "id": "sess_001", + "object": "realtime.session", + "model": "gpt-4o-realtime-preview", + "modalities": ["text"], + "instructions": "New instructions", + "voice": "sage", + "input_audio_format": "pcm16", + "output_audio_format": "pcm16", + "input_audio_transcription": { + "model": "whisper-1" + }, + "turn_detection": null, + "tools": [], + "tool_choice": "none", + "temperature": 0.7, + "max_response_output_tokens": 200, + "speed": 1.1, + "tracing": "auto" + } + } + RealtimeServerEventTranscriptionSessionUpdated: + type: object + description: > + Returned when a transcription session is updated with a + `transcription_session.update` event, unless + + there is an error. + properties: + event_id: + type: string + description: The unique ID of the server event. + type: + type: string + enum: + - transcription_session.updated + description: The event type, must be `transcription_session.updated`. + x-stainless-const: true + session: + $ref: "#/components/schemas/RealtimeTranscriptionSessionCreateResponse" + required: + - event_id + - type + - session + x-oaiMeta: + name: transcription_session.updated + group: realtime + example: | + { + "event_id": "event_5678", + "type": "transcription_session.updated", + "session": { + "id": "sess_001", + "object": "realtime.transcription_session", + "input_audio_format": "pcm16", + "input_audio_transcription": { + "model": "gpt-4o-transcribe", + "prompt": "", + "language": "" + }, + "turn_detection": { + "type": "server_vad", + "threshold": 0.5, + "prefix_padding_ms": 300, + "silence_duration_ms": 500, + "create_response": true, + // "interrupt_response": false -- this will NOT be returned + }, + "input_audio_noise_reduction": { + "type": "near_field" + }, + "include": [ + "item.input_audio_transcription.avg_logprob", + ], + } + } + RealtimeSession: + type: object + description: Realtime session object configuration. + properties: + id: + type: string + description: > + Unique identifier for the session that looks like + `sess_1234567890abcdef`. + modalities: + description: | + The set of modalities the model can respond with. To disable audio, + set this to ["text"]. + items: + type: string + default: + - text + - audio + enum: + - text + - audio + model: + type: string + description: | + The Realtime model used for this session. + enum: + - gpt-4o-realtime-preview + - gpt-4o-realtime-preview-2024-10-01 + - gpt-4o-realtime-preview-2024-12-17 + - gpt-4o-realtime-preview-2025-06-03 + - gpt-4o-mini-realtime-preview + - gpt-4o-mini-realtime-preview-2024-12-17 + instructions: + type: string + description: > + The default system instructions (i.e. system message) prepended to + model + + calls. This field allows the client to guide the model on desired + + responses. The model can be instructed on response content and + format, + + (e.g. "be extremely succinct", "act friendly", "here are examples of + good + + responses") and on audio behavior (e.g. "talk quickly", "inject + emotion + + into your voice", "laugh frequently"). The instructions are not + + guaranteed to be followed by the model, but they provide guidance to + the + + model on the desired behavior. + + + + Note that the server sets default instructions which will be used if + this + + field is not set and are visible in the `session.created` event at + the + + start of the session. + voice: + $ref: "#/components/schemas/VoiceIdsShared" + description: > + The voice the model uses to respond. Voice cannot be changed during + the + + session once the model has responded with audio at least once. + Current + + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, + `fable`, + + `onyx`, `nova`, `sage`, `shimmer`, and `verse`. + input_audio_format: + type: string + default: pcm16 + enum: + - pcm16 + - g711_ulaw + - g711_alaw + description: > + The format of input audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + + For `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, + + single channel (mono), and little-endian byte order. + output_audio_format: + type: string + default: pcm16 + enum: + - pcm16 + - g711_ulaw + - g711_alaw + description: > + The format of output audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + + For `pcm16`, output audio is sampled at a rate of 24kHz. + input_audio_transcription: + type: object + description: | + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + properties: + model: + type: string + description: > + The model to use for transcription, current options are + `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `whisper-1`. + language: + type: string + description: | + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + prompt: + type: string + description: > + An optional text to guide the model's style or continue a + previous audio + + segment. + + For `whisper-1`, the [prompt is a list of + keywords](/docs/guides/speech-to-text#prompting). + + For `gpt-4o-transcribe` models, the prompt is a free text + string, for example "expect words related to technology". + turn_detection: + type: object + description: > + Configuration for turn detection, ether Server VAD or Semantic VAD. + This can be set to `null` to turn off, in which case the client must + manually trigger model response. + + Server VAD means that the model will detect the start and end of + speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in + conjuction with VAD) to semantically estimate whether the user has + finished speaking, then dynamically sets a timeout based on this + probability. For example, if user audio trails off with "uhhm", the + model will score a low probability of turn end and wait longer for + the user to continue speaking. This can be useful for more natural + conversations, but may have a higher latency. + properties: + type: + type: string + default: server_vad + enum: + - server_vad + - semantic_vad + description: | + Type of turn detection. + eagerness: + type: string + default: auto + enum: + - low + - medium + - high + - auto + description: > + Used only for `semantic_vad` mode. The eagerness of the model to + respond. `low` will wait longer for the user to continue + speaking, `high` will respond more quickly. `auto` is the + default and is equivalent to `medium`. + threshold: + type: number + description: > + Used only for `server_vad` mode. Activation threshold for VAD + (0.0 to 1.0), this defaults to 0.5. A + + higher threshold will require louder audio to activate the + model, and + + thus might perform better in noisy environments. + prefix_padding_ms: + type: integer + description: > + Used only for `server_vad` mode. Amount of audio to include + before the VAD detected speech (in + + milliseconds). Defaults to 300ms. + silence_duration_ms: + type: integer + description: > + Used only for `server_vad` mode. Duration of silence to detect + speech stop (in milliseconds). Defaults + + to 500ms. With shorter values the model will respond more + quickly, + + but may jump in on short pauses from the user. + create_response: + type: boolean + default: true + description: > + Whether or not to automatically generate a response when a VAD + stop event occurs. + interrupt_response: + type: boolean + default: true + description: > + Whether or not to automatically interrupt any ongoing response + with output to the default + + conversation (i.e. `conversation` of `auto`) when a VAD start + event occurs. + input_audio_noise_reduction: + type: object + default: null + description: > + Configuration for input audio noise reduction. This can be set to + `null` to turn off. + + Noise reduction filters audio added to the input audio buffer before + it is sent to VAD and the model. + + Filtering the audio can improve VAD and turn detection accuracy + (reducing false positives) and model performance by improving + perception of the input audio. + properties: + type: + type: string + enum: + - near_field + - far_field + description: > + Type of noise reduction. `near_field` is for close-talking + microphones such as headphones, `far_field` is for far-field + microphones such as laptop or conference room microphones. + speed: + type: number + default: 1 + maximum: 1.5 + minimum: 0.25 + description: > + The speed of the model's spoken response. 1.0 is the default speed. + 0.25 is + + the minimum speed. 1.5 is the maximum speed. This value can only be + changed + + in between model turns, not while a response is in progress. + tracing: + title: Tracing Configuration + description: > + Configuration options for tracing. Set to null to disable tracing. + Once + + tracing is enabled for a session, the configuration cannot be + modified. + + + `auto` will create a trace for the session with default values for + the + + workflow name, group id, and metadata. + oneOf: + - type: string + default: auto + description: | + Default tracing mode for the session. + enum: + - auto + x-stainless-const: true + - type: object + title: Tracing Configuration + description: | + Granular configuration for tracing. + properties: + workflow_name: + type: string + description: > + The name of the workflow to attach to this trace. This is + used to + + name the trace in the traces dashboard. + group_id: + type: string + description: > + The group id to attach to this trace to enable filtering + and + + grouping in the traces dashboard. + metadata: + type: object + description: | + The arbitrary metadata to attach to this trace to enable + filtering in the traces dashboard. + tools: + type: array + description: Tools (functions) available to the model. + items: + type: object + properties: + type: + type: string + enum: + - function + description: The type of the tool, i.e. `function`. + x-stainless-const: true + name: + type: string + description: The name of the function. + description: + type: string + description: > + The description of the function, including guidance on when + and how + + to call it, and guidance about what to tell the user when + calling + + (if anything). + parameters: + type: object + description: Parameters of the function in JSON Schema. + tool_choice: + type: string + default: auto + description: > + How the model chooses tools. Options are `auto`, `none`, `required`, + or + + specify a function. + temperature: + type: number + default: 0.8 + description: > + Sampling temperature for the model, limited to [0.6, 1.2]. For audio + models a temperature of 0.8 is highly recommended for best + performance. + max_response_output_tokens: + oneOf: + - type: integer + - type: string + enum: + - inf + x-stainless-const: true + description: | + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + RealtimeSessionCreateRequest: + type: object + description: Realtime session object configuration. + properties: + modalities: + description: | + The set of modalities the model can respond with. To disable audio, + set this to ["text"]. + items: + type: string + default: + - text + - audio + enum: + - text + - audio + model: + type: string + description: | + The Realtime model used for this session. + enum: + - gpt-4o-realtime-preview + - gpt-4o-realtime-preview-2024-10-01 + - gpt-4o-realtime-preview-2024-12-17 + - gpt-4o-realtime-preview-2025-06-03 + - gpt-4o-mini-realtime-preview + - gpt-4o-mini-realtime-preview-2024-12-17 + instructions: + type: string + description: > + The default system instructions (i.e. system message) prepended to + model calls. This field allows the client to guide the model on + desired responses. The model can be instructed on response content + and format, (e.g. "be extremely succinct", "act friendly", "here are + examples of good responses") and on audio behavior (e.g. "talk + quickly", "inject emotion into your voice", "laugh frequently"). The + instructions are not guaranteed to be followed by the model, but + they provide guidance to the model on the desired behavior. + + + Note that the server sets default instructions which will be used if + this field is not set and are visible in the `session.created` event + at the start of the session. + voice: + $ref: "#/components/schemas/VoiceIdsShared" + description: > + The voice the model uses to respond. Voice cannot be changed during + the + + session once the model has responded with audio at least once. + Current + + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, + `fable`, + + `onyx`, `nova`, `sage`, `shimmer`, and `verse`. + input_audio_format: + type: string + default: pcm16 + enum: + - pcm16 + - g711_ulaw + - g711_alaw + description: > + The format of input audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + + For `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, + + single channel (mono), and little-endian byte order. + output_audio_format: + type: string + default: pcm16 + enum: + - pcm16 + - g711_ulaw + - g711_alaw + description: > + The format of output audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + + For `pcm16`, output audio is sampled at a rate of 24kHz. + input_audio_transcription: + type: object + description: | + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + properties: + model: + type: string + description: > + The model to use for transcription, current options are + `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `whisper-1`. + language: + type: string + description: | + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + prompt: + type: string + description: > + An optional text to guide the model's style or continue a + previous audio + + segment. + + For `whisper-1`, the [prompt is a list of + keywords](/docs/guides/speech-to-text#prompting). + + For `gpt-4o-transcribe` models, the prompt is a free text + string, for example "expect words related to technology". + turn_detection: + type: object + description: > + Configuration for turn detection, ether Server VAD or Semantic VAD. + This can be set to `null` to turn off, in which case the client must + manually trigger model response. + + Server VAD means that the model will detect the start and end of + speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in + conjuction with VAD) to semantically estimate whether the user has + finished speaking, then dynamically sets a timeout based on this + probability. For example, if user audio trails off with "uhhm", the + model will score a low probability of turn end and wait longer for + the user to continue speaking. This can be useful for more natural + conversations, but may have a higher latency. + properties: + type: + type: string + default: server_vad + enum: + - server_vad + - semantic_vad + description: | + Type of turn detection. + eagerness: + type: string + default: auto + enum: + - low + - medium + - high + - auto + description: > + Used only for `semantic_vad` mode. The eagerness of the model to + respond. `low` will wait longer for the user to continue + speaking, `high` will respond more quickly. `auto` is the + default and is equivalent to `medium`. + threshold: + type: number + description: > + Used only for `server_vad` mode. Activation threshold for VAD + (0.0 to 1.0), this defaults to 0.5. A + + higher threshold will require louder audio to activate the + model, and + + thus might perform better in noisy environments. + prefix_padding_ms: + type: integer + description: > + Used only for `server_vad` mode. Amount of audio to include + before the VAD detected speech (in + + milliseconds). Defaults to 300ms. + silence_duration_ms: + type: integer + description: > + Used only for `server_vad` mode. Duration of silence to detect + speech stop (in milliseconds). Defaults + + to 500ms. With shorter values the model will respond more + quickly, + + but may jump in on short pauses from the user. + create_response: + type: boolean + default: true + description: > + Whether or not to automatically generate a response when a VAD + stop event occurs. + interrupt_response: + type: boolean + default: true + description: > + Whether or not to automatically interrupt any ongoing response + with output to the default + + conversation (i.e. `conversation` of `auto`) when a VAD start + event occurs. + input_audio_noise_reduction: + type: object + default: null + description: > + Configuration for input audio noise reduction. This can be set to + `null` to turn off. + + Noise reduction filters audio added to the input audio buffer before + it is sent to VAD and the model. + + Filtering the audio can improve VAD and turn detection accuracy + (reducing false positives) and model performance by improving + perception of the input audio. + properties: + type: + type: string + enum: + - near_field + - far_field + description: > + Type of noise reduction. `near_field` is for close-talking + microphones such as headphones, `far_field` is for far-field + microphones such as laptop or conference room microphones. + speed: + type: number + default: 1 + maximum: 1.5 + minimum: 0.25 + description: > + The speed of the model's spoken response. 1.0 is the default speed. + 0.25 is + + the minimum speed. 1.5 is the maximum speed. This value can only be + changed + + in between model turns, not while a response is in progress. + tracing: + title: Tracing Configuration + description: > + Configuration options for tracing. Set to null to disable tracing. + Once + + tracing is enabled for a session, the configuration cannot be + modified. + + + `auto` will create a trace for the session with default values for + the + + workflow name, group id, and metadata. + oneOf: + - type: string + default: auto + description: | + Default tracing mode for the session. + enum: + - auto + x-stainless-const: true + - type: object + title: Tracing Configuration + description: | + Granular configuration for tracing. + properties: + workflow_name: + type: string + description: > + The name of the workflow to attach to this trace. This is + used to + + name the trace in the traces dashboard. + group_id: + type: string + description: > + The group id to attach to this trace to enable filtering + and + + grouping in the traces dashboard. + metadata: + type: object + description: | + The arbitrary metadata to attach to this trace to enable + filtering in the traces dashboard. + tools: + type: array + description: Tools (functions) available to the model. + items: + type: object + properties: + type: + type: string + enum: + - function + description: The type of the tool, i.e. `function`. + x-stainless-const: true + name: + type: string + description: The name of the function. + description: + type: string + description: > + The description of the function, including guidance on when + and how + + to call it, and guidance about what to tell the user when + calling + + (if anything). + parameters: + type: object + description: Parameters of the function in JSON Schema. + tool_choice: + type: string + default: auto + description: > + How the model chooses tools. Options are `auto`, `none`, `required`, + or + + specify a function. + temperature: + type: number + default: 0.8 + description: > + Sampling temperature for the model, limited to [0.6, 1.2]. For audio + models a temperature of 0.8 is highly recommended for best + performance. + max_response_output_tokens: + oneOf: + - type: integer + - type: string + enum: + - inf + x-stainless-const: true + description: | + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + client_secret: + type: object + description: | + Configuration options for the generated client secret. + properties: + expires_at: + type: object + description: | + Configuration for the ephemeral token expiration. + properties: + anchor: + default: created_at + type: string + enum: + - created_at + description: > + The anchor point for the ephemeral token expiration. Only + `created_at` is currently supported. + seconds: + default: 600 + type: integer + description: > + The number of seconds from the anchor point to the + expiration. Select a value between `10` and `7200`. + RealtimeSessionCreateResponse: + type: object + description: > + A new Realtime session configuration, with an ephermeral key. Default + TTL + + for keys is one minute. + properties: + client_secret: + type: object + description: Ephemeral key returned by the API. + properties: + value: + type: string + description: > + Ephemeral key usable in client environments to authenticate + connections + + to the Realtime API. Use this in client-side environments rather + than + + a standard API token, which should only be used server-side. + expires_at: + type: integer + description: > + Timestamp for when the token expires. Currently, all tokens + expire + + after one minute. + required: + - value + - expires_at + modalities: + description: | + The set of modalities the model can respond with. To disable audio, + set this to ["text"]. + items: + type: string + enum: + - text + - audio + instructions: + type: string + description: > + The default system instructions (i.e. system message) prepended to + model + + calls. This field allows the client to guide the model on desired + + responses. The model can be instructed on response content and + format, + + (e.g. "be extremely succinct", "act friendly", "here are examples of + good + + responses") and on audio behavior (e.g. "talk quickly", "inject + emotion + + into your voice", "laugh frequently"). The instructions are not + guaranteed + + to be followed by the model, but they provide guidance to the model + on the + + desired behavior. + + + Note that the server sets default instructions which will be used if + this + + field is not set and are visible in the `session.created` event at + the + + start of the session. + voice: + $ref: "#/components/schemas/VoiceIdsShared" + description: > + The voice the model uses to respond. Voice cannot be changed during + the + + session once the model has responded with audio at least once. + Current + + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo` `sage`, + + `shimmer` and `verse`. + input_audio_format: + type: string + description: > + The format of input audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + output_audio_format: + type: string + description: > + The format of output audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + input_audio_transcription: + type: object + description: > + Configuration for input audio transcription, defaults to off and can + be + + set to `null` to turn off once on. Input audio transcription is not + native + + to the model, since the model consumes audio directly. Transcription + runs + + asynchronously through Whisper and should be treated as rough + guidance + + rather than the representation understood by the model. + properties: + model: + type: string + description: > + The model to use for transcription, `whisper-1` is the only + currently + + supported model. + speed: + type: number + default: 1 + maximum: 1.5 + minimum: 0.25 + description: > + The speed of the model's spoken response. 1.0 is the default speed. + 0.25 is + + the minimum speed. 1.5 is the maximum speed. This value can only be + changed + + in between model turns, not while a response is in progress. + tracing: + title: Tracing Configuration + description: > + Configuration options for tracing. Set to null to disable tracing. + Once + + tracing is enabled for a session, the configuration cannot be + modified. + + + `auto` will create a trace for the session with default values for + the + + workflow name, group id, and metadata. + oneOf: + - type: string + default: auto + description: | + Default tracing mode for the session. + enum: + - auto + x-stainless-const: true + - type: object + title: Tracing Configuration + description: | + Granular configuration for tracing. + properties: + workflow_name: + type: string + description: > + The name of the workflow to attach to this trace. This is + used to + + name the trace in the traces dashboard. + group_id: + type: string + description: > + The group id to attach to this trace to enable filtering + and + + grouping in the traces dashboard. + metadata: + type: object + description: | + The arbitrary metadata to attach to this trace to enable + filtering in the traces dashboard. + turn_detection: + type: object + description: > + Configuration for turn detection. Can be set to `null` to turn off. + Server + + VAD means that the model will detect the start and end of speech + based on + + audio volume and respond at the end of user speech. + properties: + type: + type: string + description: > + Type of turn detection, only `server_vad` is currently supported. + threshold: + type: number + description: > + Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. + A + + higher threshold will require louder audio to activate the + model, and + + thus might perform better in noisy environments. + prefix_padding_ms: + type: integer + description: | + Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + silence_duration_ms: + type: integer + description: > + Duration of silence to detect speech stop (in milliseconds). + Defaults + + to 500ms. With shorter values the model will respond more + quickly, + + but may jump in on short pauses from the user. + tools: + type: array + description: Tools (functions) available to the model. + items: + type: object + properties: + type: + type: string + enum: + - function + description: The type of the tool, i.e. `function`. + x-stainless-const: true + name: + type: string + description: The name of the function. + description: + type: string + description: > + The description of the function, including guidance on when + and how + + to call it, and guidance about what to tell the user when + calling + + (if anything). + parameters: + type: object + description: Parameters of the function in JSON Schema. + tool_choice: + type: string + description: > + How the model chooses tools. Options are `auto`, `none`, `required`, + or + + specify a function. + temperature: + type: number + description: > + Sampling temperature for the model, limited to [0.6, 1.2]. Defaults + to 0.8. + max_response_output_tokens: + oneOf: + - type: integer + - type: string + enum: + - inf + x-stainless-const: true + description: | + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + required: + - client_secret + x-oaiMeta: + name: The session object + group: realtime + example: | + { + "id": "sess_001", + "object": "realtime.session", + "model": "gpt-4o-realtime-preview", + "modalities": ["audio", "text"], + "instructions": "You are a friendly assistant.", + "voice": "alloy", + "input_audio_format": "pcm16", + "output_audio_format": "pcm16", + "input_audio_transcription": { + "model": "whisper-1" + }, + "turn_detection": null, + "tools": [], + "tool_choice": "none", + "temperature": 0.7, + "speed": 1.1, + "tracing": "auto", + "max_response_output_tokens": 200, + "client_secret": { + "value": "ek_abc123", + "expires_at": 1234567890 + } + } + RealtimeTranscriptionSessionCreateRequest: + type: object + description: Realtime transcription session object configuration. + properties: + modalities: + description: | + The set of modalities the model can respond with. To disable audio, + set this to ["text"]. + items: + type: string + default: + - text + - audio + enum: + - text + - audio + input_audio_format: + type: string + default: pcm16 + enum: + - pcm16 + - g711_ulaw + - g711_alaw + description: > + The format of input audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + + For `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, + + single channel (mono), and little-endian byte order. + input_audio_transcription: + type: object + description: > + Configuration for input audio transcription. The client can + optionally set the language and prompt for transcription, these + offer additional guidance to the transcription service. + properties: + model: + type: string + description: > + The model to use for transcription, current options are + `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `whisper-1`. + enum: + - gpt-4o-transcribe + - gpt-4o-mini-transcribe + - whisper-1 + language: + type: string + description: | + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + prompt: + type: string + description: > + An optional text to guide the model's style or continue a + previous audio + + segment. + + For `whisper-1`, the [prompt is a list of + keywords](/docs/guides/speech-to-text#prompting). + + For `gpt-4o-transcribe` models, the prompt is a free text + string, for example "expect words related to technology". + turn_detection: + type: object + description: > + Configuration for turn detection, ether Server VAD or Semantic VAD. + This can be set to `null` to turn off, in which case the client must + manually trigger model response. + + Server VAD means that the model will detect the start and end of + speech based on audio volume and respond at the end of user speech. + + Semantic VAD is more advanced and uses a turn detection model (in + conjuction with VAD) to semantically estimate whether the user has + finished speaking, then dynamically sets a timeout based on this + probability. For example, if user audio trails off with "uhhm", the + model will score a low probability of turn end and wait longer for + the user to continue speaking. This can be useful for more natural + conversations, but may have a higher latency. + properties: + type: + type: string + default: server_vad + enum: + - server_vad + - semantic_vad + description: | + Type of turn detection. + eagerness: + type: string + default: auto + enum: + - low + - medium + - high + - auto + description: > + Used only for `semantic_vad` mode. The eagerness of the model to + respond. `low` will wait longer for the user to continue + speaking, `high` will respond more quickly. `auto` is the + default and is equivalent to `medium`. + threshold: + type: number + description: > + Used only for `server_vad` mode. Activation threshold for VAD + (0.0 to 1.0), this defaults to 0.5. A + + higher threshold will require louder audio to activate the + model, and + + thus might perform better in noisy environments. + prefix_padding_ms: + type: integer + description: > + Used only for `server_vad` mode. Amount of audio to include + before the VAD detected speech (in + + milliseconds). Defaults to 300ms. + silence_duration_ms: + type: integer + description: > + Used only for `server_vad` mode. Duration of silence to detect + speech stop (in milliseconds). Defaults + + to 500ms. With shorter values the model will respond more + quickly, + + but may jump in on short pauses from the user. + create_response: + type: boolean + default: true + description: > + Whether or not to automatically generate a response when a VAD + stop event occurs. Not available for transcription sessions. + interrupt_response: + type: boolean + default: true + description: > + Whether or not to automatically interrupt any ongoing response + with output to the default + + conversation (i.e. `conversation` of `auto`) when a VAD start + event occurs. Not available for transcription sessions. + input_audio_noise_reduction: + type: object + default: null + description: > + Configuration for input audio noise reduction. This can be set to + `null` to turn off. + + Noise reduction filters audio added to the input audio buffer before + it is sent to VAD and the model. + + Filtering the audio can improve VAD and turn detection accuracy + (reducing false positives) and model performance by improving + perception of the input audio. + properties: + type: + type: string + enum: + - near_field + - far_field + description: > + Type of noise reduction. `near_field` is for close-talking + microphones such as headphones, `far_field` is for far-field + microphones such as laptop or conference room microphones. + include: + type: array + items: + type: string + description: > + The set of items to include in the transcription. Current available + items are: + + - `item.input_audio_transcription.logprobs` + client_secret: + type: object + description: | + Configuration options for the generated client secret. + properties: + expires_at: + type: object + description: | + Configuration for the ephemeral token expiration. + properties: + anchor: + default: created_at + type: string + enum: + - created_at + description: > + The anchor point for the ephemeral token expiration. Only + `created_at` is currently supported. + seconds: + default: 600 + type: integer + description: > + The number of seconds from the anchor point to the + expiration. Select a value between `10` and `7200`. + RealtimeTranscriptionSessionCreateResponse: + type: object + description: > + A new Realtime transcription session configuration. + + + When a session is created on the server via REST API, the session object + + also contains an ephemeral key. Default TTL for keys is 10 minutes. + This + + property is not present when a session is updated via the WebSocket API. + properties: + client_secret: + type: object + description: | + Ephemeral key returned by the API. Only present when the session is + created on the server via REST API. + properties: + value: + type: string + description: > + Ephemeral key usable in client environments to authenticate + connections + + to the Realtime API. Use this in client-side environments rather + than + + a standard API token, which should only be used server-side. + expires_at: + type: integer + description: > + Timestamp for when the token expires. Currently, all tokens + expire + + after one minute. + required: + - value + - expires_at + modalities: + description: | + The set of modalities the model can respond with. To disable audio, + set this to ["text"]. + items: + type: string + enum: + - text + - audio + input_audio_format: + type: string + description: > + The format of input audio. Options are `pcm16`, `g711_ulaw`, or + `g711_alaw`. + input_audio_transcription: + type: object + description: | + Configuration of the transcription model. + properties: + model: + type: string + description: > + The model to use for transcription. Can be `gpt-4o-transcribe`, + `gpt-4o-mini-transcribe`, or `whisper-1`. + enum: + - gpt-4o-transcribe + - gpt-4o-mini-transcribe + - whisper-1 + language: + type: string + description: | + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + prompt: + type: string + description: > + An optional text to guide the model's style or continue a + previous audio + + segment. The [prompt](/docs/guides/speech-to-text#prompting) + should match + + the audio language. + turn_detection: + type: object + description: > + Configuration for turn detection. Can be set to `null` to turn off. + Server + + VAD means that the model will detect the start and end of speech + based on + + audio volume and respond at the end of user speech. + properties: + type: + type: string + description: > + Type of turn detection, only `server_vad` is currently supported. + threshold: + type: number + description: > + Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. + A + + higher threshold will require louder audio to activate the + model, and + + thus might perform better in noisy environments. + prefix_padding_ms: + type: integer + description: | + Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + silence_duration_ms: + type: integer + description: > + Duration of silence to detect speech stop (in milliseconds). + Defaults + + to 500ms. With shorter values the model will respond more + quickly, + + but may jump in on short pauses from the user. + required: + - client_secret + x-oaiMeta: + name: The transcription session object + group: realtime + example: | + { + "id": "sess_BBwZc7cFV3XizEyKGDCGL", + "object": "realtime.transcription_session", + "expires_at": 1742188264, + "modalities": ["audio", "text"], + "turn_detection": { + "type": "server_vad", + "threshold": 0.5, + "prefix_padding_ms": 300, + "silence_duration_ms": 200 + }, + "input_audio_format": "pcm16", + "input_audio_transcription": { + "model": "gpt-4o-transcribe", + "language": null, + "prompt": "" + }, + "client_secret": null + } + Reasoning: + type: object + description: | + **o-series models only** + + Configuration options for + [reasoning models](https://platform.openai.com/docs/guides/reasoning). + title: Reasoning + properties: + effort: + $ref: "#/components/schemas/ReasoningEffort" + summary: + type: string + description: > + A summary of the reasoning performed by the model. This can be + + useful for debugging and understanding the model's reasoning + process. + + One of `auto`, `concise`, or `detailed`. + enum: + - auto + - concise + - detailed + nullable: true + generate_summary: + type: string + deprecated: true + description: > + **Deprecated:** use `summary` instead. + + + A summary of the reasoning performed by the model. This can be + + useful for debugging and understanding the model's reasoning + process. + + One of `auto`, `concise`, or `detailed`. + enum: + - auto + - concise + - detailed + nullable: true + ReasoningEffort: + type: string + enum: + - low + - medium + - high + default: medium + nullable: true + description: | + **o-series models only** + + Constrains effort on reasoning for + [reasoning models](https://platform.openai.com/docs/guides/reasoning). + Currently supported values are `low`, `medium`, and `high`. Reducing + reasoning effort can result in faster responses and fewer tokens used + on reasoning in a response. + ReasoningItem: + type: object + description: > + A description of the chain of thought used by a reasoning model while + generating + + a response. Be sure to include these items in your `input` to the + Responses API + + for subsequent turns of a conversation if you are manually + + [managing context](/docs/guides/conversation-state). + title: Reasoning + properties: + type: + type: string + description: | + The type of the object. Always `reasoning`. + enum: + - reasoning + x-stainless-const: true + id: + type: string + description: | + The unique identifier of the reasoning content. + encrypted_content: + type: string + description: > + The encrypted content of the reasoning item - populated when a + response is + + generated with `reasoning.encrypted_content` in the `include` + parameter. + nullable: true + summary: + type: array + description: | + Reasoning text contents. + items: + type: object + properties: + type: + type: string + description: | + The type of the object. Always `summary_text`. + enum: + - summary_text + x-stainless-const: true + text: + type: string + description: > + A short summary of the reasoning used by the model when + generating + + the response. + required: + - type + - text + status: + type: string + description: | + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + enum: + - in_progress + - completed + - incomplete + required: + - id + - summary + - type + Response: + title: The response object + allOf: + - $ref: "#/components/schemas/ModelResponseProperties" + - $ref: "#/components/schemas/ResponseProperties" + - type: object + properties: + id: + type: string + description: | + Unique identifier for this Response. + object: + type: string + description: | + The object type of this resource - always set to `response`. + enum: + - response + x-stainless-const: true + status: + type: string + description: > + The status of the response generation. One of `completed`, + `failed`, + + `in_progress`, `cancelled`, `queued`, or `incomplete`. + enum: + - completed + - failed + - in_progress + - cancelled + - queued + - incomplete + created_at: + type: number + description: | + Unix timestamp (in seconds) of when this Response was created. + error: + $ref: "#/components/schemas/ResponseError" + incomplete_details: + type: object + nullable: true + description: | + Details about why the response is incomplete. + properties: + reason: + type: string + description: The reason why the response is incomplete. + enum: + - max_output_tokens + - content_filter + output: + type: array + description: > + An array of content items generated by the model. + + + - The length and order of items in the `output` array is + dependent + on the model's response. + - Rather than accessing the first item in the `output` array + and + assuming it's an `assistant` message with the content generated by + the model, you might consider using the `output_text` property where + supported in SDKs. + items: + $ref: "#/components/schemas/OutputItem" + output_text: + type: string + nullable: true + description: > + SDK-only convenience property that contains the aggregated text + output + + from all `output_text` items in the `output` array, if any are + present. + + Supported in the Python and JavaScript SDKs. + x-oaiSupportedSDKs: + - python + - javascript + usage: + $ref: "#/components/schemas/ResponseUsage" + parallel_tool_calls: + type: boolean + description: | + Whether to allow the model to run tool calls in parallel. + default: true + required: + - id + - object + - created_at + - error + - incomplete_details + - instructions + - model + - tools + - output + - parallel_tool_calls + - metadata + - tool_choice + - temperature + - top_p + example: + id: resp_67ccd3a9da748190baa7f1570fe91ac604becb25c45c1d41 + object: response + created_at: 1741476777 + status: completed + error: null + incomplete_details: null + instructions: null + max_output_tokens: null + model: gpt-4o-2024-08-06 + output: + - type: message + id: msg_67ccd3acc8d48190a77525dc6de64b4104becb25c45c1d41 + status: completed + role: assistant + content: + - type: output_text + text: The image depicts a scenic landscape with a wooden boardwalk or pathway + leading through lush, green grass under a blue sky with some + clouds. The setting suggests a peaceful natural area, possibly + a park or nature reserve. There are trees and shrubs in the + background. + annotations: [] + parallel_tool_calls: true + previous_response_id: null + reasoning: + effort: null + summary: null + store: true + temperature: 1 + text: + format: + type: text + tool_choice: auto + tools: [] + top_p: 1 + truncation: disabled + usage: + input_tokens: 328 + input_tokens_details: + cached_tokens: 0 + output_tokens: 52 + output_tokens_details: + reasoning_tokens: 0 + total_tokens: 380 + user: null + metadata: {} + ResponseAudioDeltaEvent: + type: object + description: Emitted when there is a partial audio response. + properties: + type: + type: string + description: | + The type of the event. Always `response.audio.delta`. + enum: + - response.audio.delta + x-stainless-const: true + sequence_number: + type: integer + description: | + A sequence number for this chunk of the stream response. + delta: + type: string + description: | + A chunk of Base64 encoded response audio bytes. + required: + - type + - delta + - sequence_number + x-oaiMeta: + name: response.audio.delta + group: responses + example: | + { + "type": "response.audio.delta", + "response_id": "resp_123", + "delta": "base64encoded...", + "sequence_number": 1 + } + ResponseAudioDoneEvent: + type: object + description: Emitted when the audio response is complete. + properties: + type: + type: string + description: | + The type of the event. Always `response.audio.done`. + enum: + - response.audio.done + x-stainless-const: true + sequence_number: + type: integer + description: | + The sequence number of the delta. + required: + - type + - sequence_number + - response_id + x-oaiMeta: + name: response.audio.done + group: responses + example: | + { + "type": "response.audio.done", + "response_id": "resp-123", + "sequence_number": 1 + } + ResponseAudioTranscriptDeltaEvent: + type: object + description: Emitted when there is a partial transcript of audio. + properties: + type: + type: string + description: | + The type of the event. Always `response.audio.transcript.delta`. + enum: + - response.audio.transcript.delta + x-stainless-const: true + delta: + type: string + description: | + The partial transcript of the audio response. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - response_id + - delta + - sequence_number + x-oaiMeta: + name: response.audio.transcript.delta + group: responses + example: | + { + "type": "response.audio.transcript.delta", + "response_id": "resp_123", + "delta": " ... partial transcript ... ", + "sequence_number": 1 + } + ResponseAudioTranscriptDoneEvent: + type: object + description: Emitted when the full audio transcript is completed. + properties: + type: + type: string + description: | + The type of the event. Always `response.audio.transcript.done`. + enum: + - response.audio.transcript.done + x-stainless-const: true + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - response_id + - sequence_number + x-oaiMeta: + name: response.audio.transcript.done + group: responses + example: | + { + "type": "response.audio.transcript.done", + "response_id": "resp_123", + "sequence_number": 1 + } + ResponseCodeInterpreterCallCodeDeltaEvent: + type: object + description: Emitted when a partial code snippet is added by the code interpreter. + properties: + type: + type: string + description: > + The type of the event. Always + `response.code_interpreter_call_code.delta`. + enum: + - response.code_interpreter_call_code.delta + x-stainless-const: true + output_index: + type: integer + description: > + The index of the output item that the code interpreter call is in + progress. + delta: + type: string + description: | + The partial code snippet added by the code interpreter. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - response_id + - output_index + - delta + - sequence_number + x-oaiMeta: + name: response.code_interpreter_call_code.delta + group: responses + example: | + { + "type": "response.code_interpreter_call_code.delta", + "response_id": "resp-123", + "output_index": 0, + "delta": "partial code", + "sequence_number": 1 + } + ResponseCodeInterpreterCallCodeDoneEvent: + type: object + description: Emitted when code snippet output is finalized by the code interpreter. + properties: + type: + type: string + description: > + The type of the event. Always + `response.code_interpreter_call_code.done`. + enum: + - response.code_interpreter_call_code.done + x-stainless-const: true + output_index: + type: integer + description: > + The index of the output item that the code interpreter call is in + progress. + code: + type: string + description: | + The final code snippet output by the code interpreter. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - response_id + - output_index + - code + - sequence_number + x-oaiMeta: + name: response.code_interpreter_call_code.done + group: responses + example: | + { + "type": "response.code_interpreter_call_code.done", + "response_id": "resp-123", + "output_index": 3, + "code": "console.log('done');", + "sequence_number": 1 + } + ResponseCodeInterpreterCallCompletedEvent: + type: object + description: Emitted when the code interpreter call is completed. + properties: + type: + type: string + description: > + The type of the event. Always + `response.code_interpreter_call.completed`. + enum: + - response.code_interpreter_call.completed + x-stainless-const: true + output_index: + type: integer + description: > + The index of the output item that the code interpreter call is in + progress. + code_interpreter_call: + $ref: "#/components/schemas/CodeInterpreterToolCall" + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - response_id + - output_index + - code_interpreter_call + - sequence_number + x-oaiMeta: + name: response.code_interpreter_call.completed + group: responses + example: | + { + "type": "response.code_interpreter_call.completed", + "response_id": "resp-123", + "output_index": 5, + "code_interpreter_call": {}, + "sequence_number": 1 + } + ResponseCodeInterpreterCallInProgressEvent: + type: object + description: Emitted when a code interpreter call is in progress. + properties: + type: + type: string + description: > + The type of the event. Always + `response.code_interpreter_call.in_progress`. + enum: + - response.code_interpreter_call.in_progress + x-stainless-const: true + output_index: + type: integer + description: > + The index of the output item that the code interpreter call is in + progress. + code_interpreter_call: + $ref: "#/components/schemas/CodeInterpreterToolCall" + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - response_id + - output_index + - code_interpreter_call + - sequence_number + x-oaiMeta: + name: response.code_interpreter_call.in_progress + group: responses + example: | + { + "type": "response.code_interpreter_call.in.progress", + "response_id": "resp-123", + "output_index": 0, + "code_interpreter_call": {}, + "sequence_number": 1 + } + ResponseCodeInterpreterCallInterpretingEvent: + type: object + description: Emitted when the code interpreter is actively interpreting the code + snippet. + properties: + type: + type: string + description: > + The type of the event. Always + `response.code_interpreter_call.interpreting`. + enum: + - response.code_interpreter_call.interpreting + x-stainless-const: true + sequence_number: + type: integer + description: The sequence number of this event. + output_index: + type: integer + description: > + The index of the output item that the code interpreter call is in + progress. + code_interpreter_call: + $ref: "#/components/schemas/CodeInterpreterToolCall" + required: + - type + - response_id + - output_index + - code_interpreter_call + - sequence_number + x-oaiMeta: + name: response.code_interpreter_call.interpreting + group: responses + example: | + { + "type": "response.code_interpreter_call.interpreting", + "response_id": "resp-123", + "output_index": 4, + "code_interpreter_call": {}, + "sequence_number": 1 + } + ResponseCompletedEvent: + type: object + description: Emitted when the model response is complete. + properties: + type: + type: string + description: | + The type of the event. Always `response.completed`. + enum: + - response.completed + x-stainless-const: true + response: + $ref: "#/components/schemas/Response" + description: | + Properties of the completed response. + sequence_number: + type: integer + description: The sequence number for this event. + required: + - type + - response + - sequence_number + x-oaiMeta: + name: response.completed + group: responses + example: > + { + "type": "response.completed", + "response": { + "id": "resp_123", + "object": "response", + "created_at": 1740855869, + "status": "completed", + "error": null, + "incomplete_details": null, + "input": [], + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4o-mini-2024-07-18", + "output": [ + { + "id": "msg_123", + "type": "message", + "role": "assistant", + "content": [ + { + "type": "output_text", + "text": "In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.", + "annotations": [] + } + ] + } + ], + "previous_response_id": null, + "reasoning_effort": null, + "store": false, + "temperature": 1, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [], + "top_p": 1, + "truncation": "disabled", + "usage": { + "input_tokens": 0, + "output_tokens": 0, + "output_tokens_details": { + "reasoning_tokens": 0 + }, + "total_tokens": 0 + }, + "user": null, + "metadata": {} + }, + "sequence_number": 1 + } + ResponseContentPartAddedEvent: + type: object + description: Emitted when a new content part is added. + properties: + type: + type: string + description: | + The type of the event. Always `response.content_part.added`. + enum: + - response.content_part.added + x-stainless-const: true + item_id: + type: string + description: | + The ID of the output item that the content part was added to. + output_index: + type: integer + description: | + The index of the output item that the content part was added to. + content_index: + type: integer + description: | + The index of the content part that was added. + part: + $ref: "#/components/schemas/OutputContent" + description: | + The content part that was added. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - item_id + - output_index + - content_index + - part + - sequence_number + x-oaiMeta: + name: response.content_part.added + group: responses + example: | + { + "type": "response.content_part.added", + "item_id": "msg_123", + "output_index": 0, + "content_index": 0, + "part": { + "type": "output_text", + "text": "", + "annotations": [] + }, + "sequence_number": 1 + } + ResponseContentPartDoneEvent: + type: object + description: Emitted when a content part is done. + properties: + type: + type: string + description: | + The type of the event. Always `response.content_part.done`. + enum: + - response.content_part.done + x-stainless-const: true + item_id: + type: string + description: | + The ID of the output item that the content part was added to. + output_index: + type: integer + description: | + The index of the output item that the content part was added to. + content_index: + type: integer + description: | + The index of the content part that is done. + sequence_number: + type: integer + description: The sequence number of this event. + part: + $ref: "#/components/schemas/OutputContent" + description: | + The content part that is done. + required: + - type + - item_id + - output_index + - content_index + - part + - sequence_number + x-oaiMeta: + name: response.content_part.done + group: responses + example: > + { + "type": "response.content_part.done", + "item_id": "msg_123", + "output_index": 0, + "content_index": 0, + "sequence_number": 1, + "part": { + "type": "output_text", + "text": "In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.", + "annotations": [] + } + } + ResponseCreatedEvent: + type: object + description: | + An event that is emitted when a response is created. + properties: + type: + type: string + description: | + The type of the event. Always `response.created`. + enum: + - response.created + x-stainless-const: true + response: + $ref: "#/components/schemas/Response" + description: | + The response that was created. + sequence_number: + type: integer + description: The sequence number for this event. + required: + - type + - response + - sequence_number + x-oaiMeta: + name: response.created + group: responses + example: | + { + "type": "response.created", + "response": { + "id": "resp_67ccfcdd16748190a91872c75d38539e09e4d4aac714747c", + "object": "response", + "created_at": 1741487325, + "status": "in_progress", + "error": null, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4o-2024-08-06", + "output": [], + "parallel_tool_calls": true, + "previous_response_id": null, + "reasoning": { + "effort": null, + "summary": null + }, + "store": true, + "temperature": 1, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [], + "top_p": 1, + "truncation": "disabled", + "usage": null, + "user": null, + "metadata": {} + }, + "sequence_number": 1 + } + ResponseError: + type: object + description: | + An error object returned when the model fails to generate a Response. + nullable: true + properties: + code: + $ref: "#/components/schemas/ResponseErrorCode" + message: + type: string + description: | + A human-readable description of the error. + required: + - code + - message + ResponseErrorCode: + type: string + description: | + The error code for the response. + enum: + - server_error + - rate_limit_exceeded + - invalid_prompt + - vector_store_timeout + - invalid_image + - invalid_image_format + - invalid_base64_image + - invalid_image_url + - image_too_large + - image_too_small + - image_parse_error + - image_content_policy_violation + - invalid_image_mode + - image_file_too_large + - unsupported_image_media_type + - empty_image_file + - failed_to_download_image + - image_file_not_found + ResponseErrorEvent: + type: object + description: Emitted when an error occurs. + properties: + type: + type: string + description: | + The type of the event. Always `error`. + enum: + - error + x-stainless-const: true + code: + type: string + description: | + The error code. + nullable: true + message: + type: string + description: | + The error message. + param: + type: string + description: | + The error parameter. + nullable: true + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - code + - message + - param + - sequence_number + x-oaiMeta: + name: error + group: responses + example: | + { + "type": "error", + "code": "ERR_SOMETHING", + "message": "Something went wrong", + "param": null, + "sequence_number": 1 + } + ResponseFailedEvent: + type: object + description: | + An event that is emitted when a response fails. + properties: + type: + type: string + description: | + The type of the event. Always `response.failed`. + enum: + - response.failed + x-stainless-const: true + sequence_number: + type: integer + description: The sequence number of this event. + response: + $ref: "#/components/schemas/Response" + description: | + The response that failed. + required: + - type + - response + - sequence_number + x-oaiMeta: + name: response.failed + group: responses + example: | + { + "type": "response.failed", + "response": { + "id": "resp_123", + "object": "response", + "created_at": 1740855869, + "status": "failed", + "error": { + "code": "server_error", + "message": "The model failed to generate a response." + }, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4o-mini-2024-07-18", + "output": [], + "previous_response_id": null, + "reasoning_effort": null, + "store": false, + "temperature": 1, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [], + "top_p": 1, + "truncation": "disabled", + "usage": null, + "user": null, + "metadata": {} + } + } + ResponseFileSearchCallCompletedEvent: + type: object + description: Emitted when a file search call is completed (results found). + properties: + type: + type: string + description: | + The type of the event. Always `response.file_search_call.completed`. + enum: + - response.file_search_call.completed + x-stainless-const: true + output_index: + type: integer + description: | + The index of the output item that the file search call is initiated. + item_id: + type: string + description: | + The ID of the output item that the file search call is initiated. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - output_index + - item_id + - sequence_number + x-oaiMeta: + name: response.file_search_call.completed + group: responses + example: | + { + "type": "response.file_search_call.completed", + "output_index": 0, + "item_id": "fs_123", + "sequence_number": 1 + } + ResponseFileSearchCallInProgressEvent: + type: object + description: Emitted when a file search call is initiated. + properties: + type: + type: string + description: > + The type of the event. Always + `response.file_search_call.in_progress`. + enum: + - response.file_search_call.in_progress + x-stainless-const: true + output_index: + type: integer + description: | + The index of the output item that the file search call is initiated. + item_id: + type: string + description: | + The ID of the output item that the file search call is initiated. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - output_index + - item_id + - sequence_number + x-oaiMeta: + name: response.file_search_call.in_progress + group: responses + example: | + { + "type": "response.file_search_call.in_progress", + "output_index": 0, + "item_id": "fs_123", + "sequence_number": 1 + } + ResponseFileSearchCallSearchingEvent: + type: object + description: Emitted when a file search is currently searching. + properties: + type: + type: string + description: | + The type of the event. Always `response.file_search_call.searching`. + enum: + - response.file_search_call.searching + x-stainless-const: true + output_index: + type: integer + description: | + The index of the output item that the file search call is searching. + item_id: + type: string + description: | + The ID of the output item that the file search call is initiated. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - output_index + - item_id + - sequence_number + x-oaiMeta: + name: response.file_search_call.searching + group: responses + example: | + { + "type": "response.file_search_call.searching", + "output_index": 0, + "item_id": "fs_123", + "sequence_number": 1 + } + ResponseFormatJsonObject: + type: object + title: JSON object + description: > + JSON object response format. An older method of generating JSON + responses. + + Using `json_schema` is recommended for models that support it. Note that + the + + model will not generate JSON without a system or user message + instructing it + + to do so. + properties: + type: + type: string + description: The type of response format being defined. Always `json_object`. + enum: + - json_object + x-stainless-const: true + required: + - type + ResponseFormatJsonSchema: + type: object + title: JSON schema + description: | + JSON Schema response format. Used to generate structured JSON responses. + Learn more about [Structured Outputs](/docs/guides/structured-outputs). + properties: + type: + type: string + description: The type of response format being defined. Always `json_schema`. + enum: + - json_schema + x-stainless-const: true + json_schema: + type: object + title: JSON schema + description: | + Structured Outputs configuration options, including a JSON Schema. + properties: + description: + type: string + description: > + A description of what the response format is for, used by the + model to + + determine how to respond in the format. + name: + type: string + description: > + The name of the response format. Must be a-z, A-Z, 0-9, or + contain + + underscores and dashes, with a maximum length of 64. + schema: + $ref: "#/components/schemas/ResponseFormatJsonSchemaSchema" + strict: + type: boolean + nullable: true + default: false + description: > + Whether to enable strict schema adherence when generating the + output. + + If set to true, the model will always follow the exact schema + defined + + in the `schema` field. Only a subset of JSON Schema is supported + when + + `strict` is `true`. To learn more, read the [Structured Outputs + + guide](/docs/guides/structured-outputs). + required: + - name + required: + - type + - json_schema + ResponseFormatJsonSchemaSchema: + type: object + title: JSON schema + description: | + The schema for the response format, described as a JSON Schema object. + Learn how to build JSON schemas [here](https://json-schema.org/). + additionalProperties: true + ResponseFormatText: + type: object + title: Text + description: | + Default response format. Used to generate text responses. + properties: + type: + type: string + description: The type of response format being defined. Always `text`. + enum: + - text + x-stainless-const: true + required: + - type + ResponseFunctionCallArgumentsDeltaEvent: + type: object + description: Emitted when there is a partial function-call arguments delta. + properties: + type: + type: string + description: > + The type of the event. Always + `response.function_call_arguments.delta`. + enum: + - response.function_call_arguments.delta + x-stainless-const: true + item_id: + type: string + description: > + The ID of the output item that the function-call arguments delta is + added to. + output_index: + type: integer + description: > + The index of the output item that the function-call arguments delta + is added to. + sequence_number: + type: integer + description: The sequence number of this event. + delta: + type: string + description: | + The function-call arguments delta that is added. + required: + - type + - item_id + - output_index + - delta + - sequence_number + x-oaiMeta: + name: response.function_call_arguments.delta + group: responses + example: | + { + "type": "response.function_call_arguments.delta", + "item_id": "item-abc", + "output_index": 0, + "delta": "{ \"arg\":" + "sequence_number": 1 + } + ResponseFunctionCallArgumentsDoneEvent: + type: object + description: Emitted when function-call arguments are finalized. + properties: + type: + type: string + enum: + - response.function_call_arguments.done + x-stainless-const: true + item_id: + type: string + description: The ID of the item. + output_index: + type: integer + description: The index of the output item. + sequence_number: + type: integer + description: The sequence number of this event. + arguments: + type: string + description: The function-call arguments. + required: + - type + - item_id + - output_index + - arguments + - sequence_number + x-oaiMeta: + name: response.function_call_arguments.done + group: responses + example: | + { + "type": "response.function_call_arguments.done", + "item_id": "item-abc", + "output_index": 1, + "arguments": "{ \"arg\": 123 }", + "sequence_number": 1 + } + ResponseImageGenCallCompletedEvent: + type: object + title: ResponseImageGenCallCompletedEvent + description: > + Emitted when an image generation tool call has completed and the final + image is available. + properties: + type: + type: string + enum: + - response.image_generation_call.completed + description: The type of the event. Always + 'response.image_generation_call.completed'. + x-stainless-const: true + output_index: + type: integer + description: The index of the output item in the response's output array. + sequence_number: + type: integer + description: The sequence number of this event. + item_id: + type: string + description: The unique identifier of the image generation item being processed. + required: + - type + - output_index + - item_id + - sequence_number + x-oaiMeta: + name: response.image_generation_call.completed + group: responses + example: | + { + "type": "response.image_generation_call.completed", + "output_index": 0, + "item_id": "item-123", + "sequence_number": 1 + } + ResponseImageGenCallGeneratingEvent: + type: object + title: ResponseImageGenCallGeneratingEvent + description: > + Emitted when an image generation tool call is actively generating an + image (intermediate state). + properties: + type: + type: string + enum: + - response.image_generation_call.generating + description: The type of the event. Always + 'response.image_generation_call.generating'. + x-stainless-const: true + output_index: + type: integer + description: The index of the output item in the response's output array. + item_id: + type: string + description: The unique identifier of the image generation item being processed. + sequence_number: + type: integer + description: The sequence number of the image generation item being processed. + required: + - type + - output_index + - item_id + - sequence_number + x-oaiMeta: + name: response.image_generation_call.generating + group: responses + example: | + { + "type": "response.image_generation_call.generating", + "output_index": 0, + "item_id": "item-123", + "sequence_number": 0 + } + ResponseImageGenCallInProgressEvent: + type: object + title: ResponseImageGenCallInProgressEvent + description: | + Emitted when an image generation tool call is in progress. + properties: + type: + type: string + enum: + - response.image_generation_call.in_progress + description: The type of the event. Always + 'response.image_generation_call.in_progress'. + x-stainless-const: true + output_index: + type: integer + description: The index of the output item in the response's output array. + item_id: + type: string + description: The unique identifier of the image generation item being processed. + sequence_number: + type: integer + description: The sequence number of the image generation item being processed. + required: + - type + - output_index + - item_id + - sequence_number + x-oaiMeta: + name: response.image_generation_call.in_progress + group: responses + example: | + { + "type": "response.image_generation_call.in_progress", + "output_index": 0, + "item_id": "item-123", + "sequence_number": 0 + } + ResponseImageGenCallPartialImageEvent: + type: object + title: ResponseImageGenCallPartialImageEvent + description: > + Emitted when a partial image is available during image generation + streaming. + properties: + type: + type: string + enum: + - response.image_generation_call.partial_image + description: The type of the event. Always + 'response.image_generation_call.partial_image'. + x-stainless-const: true + output_index: + type: integer + description: The index of the output item in the response's output array. + item_id: + type: string + description: The unique identifier of the image generation item being processed. + sequence_number: + type: integer + description: The sequence number of the image generation item being processed. + partial_image_index: + type: integer + description: 0-based index for the partial image (backend is 1-based, but this + is 0-based for the user). + partial_image_b64: + type: string + description: Base64-encoded partial image data, suitable for rendering as an + image. + required: + - type + - output_index + - item_id + - sequence_number + - partial_image_index + - partial_image_b64 + x-oaiMeta: + name: response.image_generation_call.partial_image + group: responses + example: | + { + "type": "response.image_generation_call.partial_image", + "output_index": 0, + "item_id": "item-123", + "sequence_number": 0, + "partial_image_index": 0, + "partial_image_b64": "..." + } + ResponseInProgressEvent: + type: object + description: Emitted when the response is in progress. + properties: + type: + type: string + description: | + The type of the event. Always `response.in_progress`. + enum: + - response.in_progress + x-stainless-const: true + response: + $ref: "#/components/schemas/Response" + description: | + The response that is in progress. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - response + - sequence_number + x-oaiMeta: + name: response.in_progress + group: responses + example: | + { + "type": "response.in_progress", + "response": { + "id": "resp_67ccfcdd16748190a91872c75d38539e09e4d4aac714747c", + "object": "response", + "created_at": 1741487325, + "status": "in_progress", + "error": null, + "incomplete_details": null, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4o-2024-08-06", + "output": [], + "parallel_tool_calls": true, + "previous_response_id": null, + "reasoning": { + "effort": null, + "summary": null + }, + "store": true, + "temperature": 1, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [], + "top_p": 1, + "truncation": "disabled", + "usage": null, + "user": null, + "metadata": {} + }, + "sequence_number": 1 + } + ResponseIncompleteEvent: + type: object + description: | + An event that is emitted when a response finishes as incomplete. + properties: + type: + type: string + description: | + The type of the event. Always `response.incomplete`. + enum: + - response.incomplete + x-stainless-const: true + response: + $ref: "#/components/schemas/Response" + description: | + The response that was incomplete. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - response + - sequence_number + x-oaiMeta: + name: response.incomplete + group: responses + example: | + { + "type": "response.incomplete", + "response": { + "id": "resp_123", + "object": "response", + "created_at": 1740855869, + "status": "incomplete", + "error": null, + "incomplete_details": { + "reason": "max_tokens" + }, + "instructions": null, + "max_output_tokens": null, + "model": "gpt-4o-mini-2024-07-18", + "output": [], + "previous_response_id": null, + "reasoning_effort": null, + "store": false, + "temperature": 1, + "text": { + "format": { + "type": "text" + } + }, + "tool_choice": "auto", + "tools": [], + "top_p": 1, + "truncation": "disabled", + "usage": null, + "user": null, + "metadata": {} + }, + "sequence_number": 1 + } + ResponseItemList: + type: object + description: A list of Response items. + properties: + object: + type: string + description: The type of object returned, must be `list`. + enum: + - list + x-stainless-const: true + data: + type: array + description: A list of items used to generate this response. + items: + $ref: "#/components/schemas/ItemResource" + has_more: + type: boolean + description: Whether there are more items available. + first_id: + type: string + description: The ID of the first item in the list. + last_id: + type: string + description: The ID of the last item in the list. + required: + - object + - data + - has_more + - first_id + - last_id + x-oaiMeta: + name: The input item list + group: responses + example: > + { + "object": "list", + "data": [ + { + "id": "msg_abc123", + "type": "message", + "role": "user", + "content": [ + { + "type": "input_text", + "text": "Tell me a three sentence bedtime story about a unicorn." + } + ] + } + ], + "first_id": "msg_abc123", + "last_id": "msg_abc123", + "has_more": false + } + ResponseMCPCallArgumentsDeltaEvent: + type: object + title: ResponseMCPCallArgumentsDeltaEvent + description: > + Emitted when there is a delta (partial update) to the arguments of an + MCP tool call. + properties: + type: + type: string + enum: + - response.mcp_call.arguments_delta + description: The type of the event. Always 'response.mcp_call.arguments_delta'. + x-stainless-const: true + output_index: + type: integer + description: The index of the output item in the response's output array. + item_id: + type: string + description: The unique identifier of the MCP tool call item being processed. + delta: + type: object + description: The partial update to the arguments for the MCP tool call. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - output_index + - item_id + - delta + - sequence_number + x-oaiMeta: + name: response.mcp_call.arguments.delta + group: responses + example: | + { + "type": "response.mcp_call.arguments.delta", + "output_index": 0, + "item_id": "item-abc", + "delta": { + "arg1": "new_value1", + "arg2": "new_value2" + }, + "sequence_number": 1 + } + ResponseMCPCallArgumentsDoneEvent: + type: object + title: ResponseMCPCallArgumentsDoneEvent + description: | + Emitted when the arguments for an MCP tool call are finalized. + properties: + type: + type: string + enum: + - response.mcp_call.arguments_done + description: The type of the event. Always 'response.mcp_call.arguments_done'. + x-stainless-const: true + output_index: + type: integer + description: The index of the output item in the response's output array. + item_id: + type: string + description: The unique identifier of the MCP tool call item being processed. + arguments: + type: object + description: The finalized arguments for the MCP tool call. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - output_index + - item_id + - arguments + - sequence_number + x-oaiMeta: + name: response.mcp_call.arguments.done + group: responses + example: | + { + "type": "response.mcp_call.arguments.done", + "output_index": 0, + "item_id": "item-abc", + "arguments": { + "arg1": "value1", + "arg2": "value2" + }, + "sequence_number": 1 + } + ResponseMCPCallCompletedEvent: + type: object + title: ResponseMCPCallCompletedEvent + description: | + Emitted when an MCP tool call has completed successfully. + properties: + type: + type: string + enum: + - response.mcp_call.completed + description: The type of the event. Always 'response.mcp_call.completed'. + x-stainless-const: true + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - sequence_number + x-oaiMeta: + name: response.mcp_call.completed + group: responses + example: | + { + "type": "response.mcp_call.completed", + "sequence_number": 1 + } + ResponseMCPCallFailedEvent: + type: object + title: ResponseMCPCallFailedEvent + description: | + Emitted when an MCP tool call has failed. + properties: + type: + type: string + enum: + - response.mcp_call.failed + description: The type of the event. Always 'response.mcp_call.failed'. + x-stainless-const: true + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - sequence_number + x-oaiMeta: + name: response.mcp_call.failed + group: responses + example: | + { + "type": "response.mcp_call.failed", + "sequence_number": 1 + } + ResponseMCPCallInProgressEvent: + type: object + title: ResponseMCPCallInProgressEvent + description: | + Emitted when an MCP tool call is in progress. + properties: + type: + type: string + enum: + - response.mcp_call.in_progress + description: The type of the event. Always 'response.mcp_call.in_progress'. + x-stainless-const: true + sequence_number: + type: integer + description: The sequence number of this event. + output_index: + type: integer + description: The index of the output item in the response's output array. + item_id: + type: string + description: The unique identifier of the MCP tool call item being processed. + required: + - type + - output_index + - item_id + - sequence_number + x-oaiMeta: + name: response.mcp_call.in_progress + group: responses + example: | + { + "type": "response.mcp_call.in_progress", + "output_index": 0, + "item_id": "item-abc", + "sequence_number": 1 + } + ResponseMCPListToolsCompletedEvent: + type: object + title: ResponseMCPListToolsCompletedEvent + description: > + Emitted when the list of available MCP tools has been successfully + retrieved. + properties: + type: + type: string + enum: + - response.mcp_list_tools.completed + description: The type of the event. Always 'response.mcp_list_tools.completed'. + x-stainless-const: true + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - sequence_number + x-oaiMeta: + name: response.mcp_list_tools.completed + group: responses + example: | + { + "type": "response.mcp_list_tools.completed", + "sequence_number": 1 + } + ResponseMCPListToolsFailedEvent: + type: object + title: ResponseMCPListToolsFailedEvent + description: | + Emitted when the attempt to list available MCP tools has failed. + properties: + type: + type: string + enum: + - response.mcp_list_tools.failed + description: The type of the event. Always 'response.mcp_list_tools.failed'. + x-stainless-const: true + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - sequence_number + x-oaiMeta: + name: response.mcp_list_tools.failed + group: responses + example: | + { + "type": "response.mcp_list_tools.failed", + "sequence_number": 1 + } + ResponseMCPListToolsInProgressEvent: + type: object + title: ResponseMCPListToolsInProgressEvent + description: > + Emitted when the system is in the process of retrieving the list of + available MCP tools. + properties: + type: + type: string + enum: + - response.mcp_list_tools.in_progress + description: The type of the event. Always 'response.mcp_list_tools.in_progress'. + x-stainless-const: true + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - sequence_number + x-oaiMeta: + name: response.mcp_list_tools.in_progress + group: responses + example: | + { + "type": "response.mcp_list_tools.in_progress", + "sequence_number": 1 + } + ResponseModalities: + type: array + nullable: true + description: > + Output types that you would like the model to generate. + + Most models are capable of generating text, which is the default: + + + `["text"]` + + + The `gpt-4o-audio-preview` model can also be used to + + [generate audio](/docs/guides/audio). To request that this model + generate + + both text and audio responses, you can use: + + + `["text", "audio"]` + items: + type: string + enum: + - text + - audio + ResponseOutputItemAddedEvent: + type: object + description: Emitted when a new output item is added. + properties: + type: + type: string + description: | + The type of the event. Always `response.output_item.added`. + enum: + - response.output_item.added + x-stainless-const: true + output_index: + type: integer + description: | + The index of the output item that was added. + sequence_number: + type: integer + description: | + The sequence number of this event. + item: + $ref: "#/components/schemas/OutputItem" + description: | + The output item that was added. + required: + - type + - output_index + - item + - sequence_number + x-oaiMeta: + name: response.output_item.added + group: responses + example: | + { + "type": "response.output_item.added", + "output_index": 0, + "item": { + "id": "msg_123", + "status": "in_progress", + "type": "message", + "role": "assistant", + "content": [] + }, + "sequence_number": 1 + } + ResponseOutputItemDoneEvent: + type: object + description: Emitted when an output item is marked done. + properties: + type: + type: string + description: | + The type of the event. Always `response.output_item.done`. + enum: + - response.output_item.done + x-stainless-const: true + output_index: + type: integer + description: | + The index of the output item that was marked done. + sequence_number: + type: integer + description: | + The sequence number of this event. + item: + $ref: "#/components/schemas/OutputItem" + description: | + The output item that was marked done. + required: + - type + - output_index + - item + - sequence_number + x-oaiMeta: + name: response.output_item.done + group: responses + example: > + { + "type": "response.output_item.done", + "output_index": 0, + "item": { + "id": "msg_123", + "status": "completed", + "type": "message", + "role": "assistant", + "content": [ + { + "type": "output_text", + "text": "In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.", + "annotations": [] + } + ] + }, + "sequence_number": 1 + } + ResponseOutputTextAnnotationAddedEvent: + type: object + title: ResponseOutputTextAnnotationAddedEvent + description: | + Emitted when an annotation is added to output text content. + properties: + type: + type: string + enum: + - response.output_text_annotation.added + description: The type of the event. Always + 'response.output_text_annotation.added'. + x-stainless-const: true + item_id: + type: string + description: The unique identifier of the item to which the annotation is being + added. + output_index: + type: integer + description: The index of the output item in the response's output array. + content_index: + type: integer + description: The index of the content part within the output item. + annotation_index: + type: integer + description: The index of the annotation within the content part. + sequence_number: + type: integer + description: The sequence number of this event. + annotation: + type: object + description: The annotation object being added. (See annotation schema for + details.) + required: + - type + - item_id + - output_index + - content_index + - annotation_index + - annotation + - sequence_number + x-oaiMeta: + name: response.output_text_annotation.added + group: responses + example: | + { + "type": "response.output_text_annotation.added", + "item_id": "item-abc", + "output_index": 0, + "content_index": 0, + "annotation_index": 0, + "annotation": { + "type": "text_annotation", + "text": "This is a test annotation", + "start": 0, + "end": 10 + }, + "sequence_number": 1 + } + ResponseProperties: + type: object + properties: + previous_response_id: + type: string + description: | + The unique ID of the previous response to the model. Use this to + create multi-turn conversations. Learn more about + [conversation state](/docs/guides/conversation-state). + nullable: true + model: + description: > + Model ID used to generate the response, like `gpt-4o` or `o3`. + OpenAI + + offers a wide range of models with different capabilities, + performance + + characteristics, and price points. Refer to the [model + guide](/docs/models) + + to browse and compare available models. + $ref: "#/components/schemas/ModelIdsResponses" + reasoning: + $ref: "#/components/schemas/Reasoning" + nullable: true + background: + type: boolean + description: | + Whether to run the model response in the background. + [Learn more](/docs/guides/background). + default: false + nullable: true + max_output_tokens: + description: > + An upper bound for the number of tokens that can be generated for a + response, including visible output tokens and [reasoning + tokens](/docs/guides/reasoning). + type: integer + nullable: true + instructions: + type: string + description: > + Inserts a system (or developer) message as the first item in the + model's context. + + + When using along with `previous_response_id`, the instructions from + a previous + + response will not be carried over to the next response. This makes + it simple + + to swap out system (or developer) messages in new responses. + nullable: true + text: + type: object + description: > + Configuration options for a text response from the model. Can be + plain + + text or structured JSON data. Learn more: + + - [Text inputs and outputs](/docs/guides/text) + + - [Structured Outputs](/docs/guides/structured-outputs) + properties: + format: + $ref: "#/components/schemas/TextResponseFormatConfiguration" + tools: + type: array + description: > + An array of tools the model may call while generating a response. + You + + can specify which tool to use by setting the `tool_choice` + parameter. + + + The two categories of tools you can provide the model are: + + + - **Built-in tools**: Tools that are provided by OpenAI that extend + the + model's capabilities, like [web search](/docs/guides/tools-web-search) + or [file search](/docs/guides/tools-file-search). Learn more about + [built-in tools](/docs/guides/tools). + - **Function calls (custom tools)**: Functions that are defined by + you, + enabling the model to call your own code. Learn more about + [function calling](/docs/guides/function-calling). + items: + $ref: "#/components/schemas/Tool" + tool_choice: + description: > + How the model should select which tool (or tools) to use when + generating + + a response. See the `tools` parameter to see how to specify which + tools + + the model can call. + oneOf: + - $ref: "#/components/schemas/ToolChoiceOptions" + - $ref: "#/components/schemas/ToolChoiceTypes" + - $ref: "#/components/schemas/ToolChoiceFunction" + truncation: + type: string + description: > + The truncation strategy to use for the model response. + + - `auto`: If the context of this response and previous ones exceeds + the model's context window size, the model will truncate the + response to fit the context window by dropping input items in the + middle of the conversation. + - `disabled` (default): If a model response will exceed the context + window + size for a model, the request will fail with a 400 error. + enum: + - auto + - disabled + nullable: true + default: disabled + ResponseQueuedEvent: + type: object + title: ResponseQueuedEvent + description: | + Emitted when a response is queued and waiting to be processed. + properties: + type: + type: string + enum: + - response.queued + description: The type of the event. Always 'response.queued'. + x-stainless-const: true + response: + $ref: "#/components/schemas/Response" + description: The full response object that is queued. + sequence_number: + type: integer + description: The sequence number for this event. + required: + - type + - response + - sequence_number + x-oaiMeta: + name: response.queued + group: responses + example: | + { + "type": "response.queued", + "response": { + "id": "res_123", + "status": "queued", + "created_at": "2021-01-01T00:00:00Z", + "updated_at": "2021-01-01T00:00:00Z" + }, + "sequence_number": 1 + } + ResponseReasoningDeltaEvent: + type: object + title: ResponseReasoningDeltaEvent + description: | + Emitted when there is a delta (partial update) to the reasoning content. + properties: + type: + type: string + enum: + - response.reasoning.delta + description: The type of the event. Always 'response.reasoning.delta'. + x-stainless-const: true + item_id: + type: string + description: The unique identifier of the item for which reasoning is being + updated. + output_index: + type: integer + description: The index of the output item in the response's output array. + content_index: + type: integer + description: The index of the reasoning content part within the output item. + delta: + type: object + description: The partial update to the reasoning content. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - item_id + - output_index + - content_index + - delta + - sequence_number + x-oaiMeta: + name: response.reasoning.delta + group: responses + example: | + { + "type": "response.reasoning.delta", + "item_id": "item-abc", + "output_index": 0, + "content_index": 0, + "delta": { + "text": "This is a test delta" + }, + "sequence_number": 1 + } + ResponseReasoningDoneEvent: + type: object + title: ResponseReasoningDoneEvent + description: | + Emitted when the reasoning content is finalized for an item. + properties: + type: + type: string + enum: + - response.reasoning.done + description: The type of the event. Always 'response.reasoning.done'. + x-stainless-const: true + item_id: + type: string + description: The unique identifier of the item for which reasoning is finalized. + output_index: + type: integer + description: The index of the output item in the response's output array. + content_index: + type: integer + description: The index of the reasoning content part within the output item. + text: + type: string + description: The finalized reasoning text. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - item_id + - output_index + - content_index + - text + - sequence_number + x-oaiMeta: + name: response.reasoning.done + group: responses + example: | + { + "type": "response.reasoning.done", + "item_id": "item-abc", + "output_index": 0, + "content_index": 0, + "text": "This is a test reasoning", + "sequence_number": 1 + } + ResponseReasoningSummaryDeltaEvent: + type: object + title: ResponseReasoningSummaryDeltaEvent + description: > + Emitted when there is a delta (partial update) to the reasoning summary + content. + properties: + type: + type: string + enum: + - response.reasoning_summary.delta + description: The type of the event. Always 'response.reasoning_summary.delta'. + x-stainless-const: true + item_id: + type: string + description: The unique identifier of the item for which the reasoning summary + is being updated. + output_index: + type: integer + description: The index of the output item in the response's output array. + summary_index: + type: integer + description: The index of the summary part within the output item. + sequence_number: + type: integer + description: The sequence number of this event. + delta: + type: object + description: The partial update to the reasoning summary content. + required: + - type + - item_id + - output_index + - summary_index + - delta + - sequence_number + x-oaiMeta: + name: response.reasoning_summary.delta + group: responses + example: | + { + "type": "response.reasoning_summary.delta", + "item_id": "item-abc", + "output_index": 0, + "summary_index": 0, + "delta": { + "text": "delta text" + }, + "sequence_number": 1 + } + ResponseReasoningSummaryDoneEvent: + type: object + title: ResponseReasoningSummaryDoneEvent + description: | + Emitted when the reasoning summary content is finalized for an item. + properties: + type: + type: string + enum: + - response.reasoning_summary.done + description: The type of the event. Always 'response.reasoning_summary.done'. + x-stainless-const: true + item_id: + type: string + description: The unique identifier of the item for which the reasoning summary + is finalized. + output_index: + type: integer + description: The index of the output item in the response's output array. + summary_index: + type: integer + description: The index of the summary part within the output item. + text: + type: string + description: The finalized reasoning summary text. + sequence_number: + type: integer + description: The sequence number of this event. + required: + - type + - item_id + - output_index + - summary_index + - text + - sequence_number + x-oaiMeta: + name: response.reasoning_summary.done + group: responses + example: | + { + "type": "response.reasoning_summary.done", + "item_id": "item-abc", + "output_index": 0, + "summary_index": 0, + "text": "This is a test reasoning summary", + "sequence_number": 1 + } + ResponseReasoningSummaryPartAddedEvent: + type: object + description: Emitted when a new reasoning summary part is added. + properties: + type: + type: string + description: > + The type of the event. Always + `response.reasoning_summary_part.added`. + enum: + - response.reasoning_summary_part.added + x-stainless-const: true + item_id: + type: string + description: | + The ID of the item this summary part is associated with. + output_index: + type: integer + description: | + The index of the output item this summary part is associated with. + summary_index: + type: integer + description: | + The index of the summary part within the reasoning summary. + sequence_number: + type: integer + description: | + The sequence number of this event. + part: + type: object + description: | + The summary part that was added. + properties: + type: + type: string + description: The type of the summary part. Always `summary_text`. + enum: + - summary_text + x-stainless-const: true + text: + type: string + description: The text of the summary part. + required: + - type + - text + required: + - type + - item_id + - output_index + - summary_index + - part + - sequence_number + x-oaiMeta: + name: response.reasoning_summary_part.added + group: responses + example: | + { + "type": "response.reasoning_summary_part.added", + "item_id": "rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476", + "output_index": 0, + "summary_index": 0, + "part": { + "type": "summary_text", + "text": "" + }, + "sequence_number": 1 + } + ResponseReasoningSummaryPartDoneEvent: + type: object + description: Emitted when a reasoning summary part is completed. + properties: + type: + type: string + description: > + The type of the event. Always `response.reasoning_summary_part.done`. + enum: + - response.reasoning_summary_part.done + x-stainless-const: true + item_id: + type: string + description: | + The ID of the item this summary part is associated with. + output_index: + type: integer + description: | + The index of the output item this summary part is associated with. + summary_index: + type: integer + description: | + The index of the summary part within the reasoning summary. + sequence_number: + type: integer + description: | + The sequence number of this event. + part: + type: object + description: | + The completed summary part. + properties: + type: + type: string + description: The type of the summary part. Always `summary_text`. + enum: + - summary_text + x-stainless-const: true + text: + type: string + description: The text of the summary part. + required: + - type + - text + required: + - type + - item_id + - output_index + - summary_index + - part + - sequence_number + x-oaiMeta: + name: response.reasoning_summary_part.done + group: responses + example: > + { + "type": "response.reasoning_summary_part.done", + "item_id": "rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476", + "output_index": 0, + "summary_index": 0, + "part": { + "type": "summary_text", + "text": "**Responding to a greeting**\n\nThe user just said, \"Hello!\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \"Hello! How can I assist you today?\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!" + }, + "sequence_number": 1 + } + ResponseReasoningSummaryTextDeltaEvent: + type: object + description: Emitted when a delta is added to a reasoning summary text. + properties: + type: + type: string + description: > + The type of the event. Always + `response.reasoning_summary_text.delta`. + enum: + - response.reasoning_summary_text.delta + x-stainless-const: true + item_id: + type: string + description: | + The ID of the item this summary text delta is associated with. + output_index: + type: integer + description: > + The index of the output item this summary text delta is associated + with. + summary_index: + type: integer + description: | + The index of the summary part within the reasoning summary. + delta: + type: string + description: | + The text delta that was added to the summary. + sequence_number: + type: integer + description: | + The sequence number of this event. + required: + - type + - item_id + - output_index + - summary_index + - delta + - sequence_number + x-oaiMeta: + name: response.reasoning_summary_text.delta + group: responses + example: > + { + "type": "response.reasoning_summary_text.delta", + "item_id": "rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476", + "output_index": 0, + "summary_index": 0, + "delta": "**Responding to a greeting**\n\nThe user just said, \"Hello!\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \"Hello! How can I assist you today?\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!", + "sequence_number": 1 + } + ResponseReasoningSummaryTextDoneEvent: + type: object + description: Emitted when a reasoning summary text is completed. + properties: + type: + type: string + description: > + The type of the event. Always `response.reasoning_summary_text.done`. + enum: + - response.reasoning_summary_text.done + x-stainless-const: true + item_id: + type: string + description: | + The ID of the item this summary text is associated with. + output_index: + type: integer + description: | + The index of the output item this summary text is associated with. + summary_index: + type: integer + description: | + The index of the summary part within the reasoning summary. + text: + type: string + description: | + The full text of the completed reasoning summary. + sequence_number: + type: integer + description: | + The sequence number of this event. + required: + - type + - item_id + - output_index + - summary_index + - text + - sequence_number + x-oaiMeta: + name: response.reasoning_summary_text.done + group: responses + example: > + { + "type": "response.reasoning_summary_text.done", + "item_id": "rs_6806bfca0b2481918a5748308061a2600d3ce51bdffd5476", + "output_index": 0, + "summary_index": 0, + "text": "**Responding to a greeting**\n\nThe user just said, \"Hello!\" So, it seems I need to engage. I'll greet them back and offer help since they're looking to chat. I could say something like, \"Hello! How can I assist you today?\" That feels friendly and open. They didn't ask a specific question, so this approach will work well for starting a conversation. Let's see where it goes from there!", + "sequence_number": 1 + } + ResponseRefusalDeltaEvent: + type: object + description: Emitted when there is a partial refusal text. + properties: + type: + type: string + description: | + The type of the event. Always `response.refusal.delta`. + enum: + - response.refusal.delta + x-stainless-const: true + item_id: + type: string + description: | + The ID of the output item that the refusal text is added to. + output_index: + type: integer + description: | + The index of the output item that the refusal text is added to. + content_index: + type: integer + description: | + The index of the content part that the refusal text is added to. + delta: + type: string + description: | + The refusal text that is added. + sequence_number: + type: integer + description: | + The sequence number of this event. + required: + - type + - item_id + - output_index + - content_index + - delta + - sequence_number + x-oaiMeta: + name: response.refusal.delta + group: responses + example: | + { + "type": "response.refusal.delta", + "item_id": "msg_123", + "output_index": 0, + "content_index": 0, + "delta": "refusal text so far", + "sequence_number": 1 + } + ResponseRefusalDoneEvent: + type: object + description: Emitted when refusal text is finalized. + properties: + type: + type: string + description: | + The type of the event. Always `response.refusal.done`. + enum: + - response.refusal.done + x-stainless-const: true + item_id: + type: string + description: | + The ID of the output item that the refusal text is finalized. + output_index: + type: integer + description: | + The index of the output item that the refusal text is finalized. + content_index: + type: integer + description: | + The index of the content part that the refusal text is finalized. + refusal: + type: string + description: | + The refusal text that is finalized. + sequence_number: + type: integer + description: | + The sequence number of this event. + required: + - type + - item_id + - output_index + - content_index + - refusal + - sequence_number + x-oaiMeta: + name: response.refusal.done + group: responses + example: | + { + "type": "response.refusal.done", + "item_id": "item-abc", + "output_index": 1, + "content_index": 2, + "refusal": "final refusal text", + "sequence_number": 1 + } + ResponseStreamEvent: + anyOf: + - $ref: "#/components/schemas/ResponseAudioDeltaEvent" + - $ref: "#/components/schemas/ResponseAudioDoneEvent" + - $ref: "#/components/schemas/ResponseAudioTranscriptDeltaEvent" + - $ref: "#/components/schemas/ResponseAudioTranscriptDoneEvent" + - $ref: "#/components/schemas/ResponseCodeInterpreterCallCodeDeltaEvent" + - $ref: "#/components/schemas/ResponseCodeInterpreterCallCodeDoneEvent" + - $ref: "#/components/schemas/ResponseCodeInterpreterCallCompletedEvent" + - $ref: "#/components/schemas/ResponseCodeInterpreterCallInProgressEvent" + - $ref: "#/components/schemas/ResponseCodeInterpreterCallInterpretingEvent" + - $ref: "#/components/schemas/ResponseCompletedEvent" + - $ref: "#/components/schemas/ResponseContentPartAddedEvent" + - $ref: "#/components/schemas/ResponseContentPartDoneEvent" + - $ref: "#/components/schemas/ResponseCreatedEvent" + - $ref: "#/components/schemas/ResponseErrorEvent" + - $ref: "#/components/schemas/ResponseFileSearchCallCompletedEvent" + - $ref: "#/components/schemas/ResponseFileSearchCallInProgressEvent" + - $ref: "#/components/schemas/ResponseFileSearchCallSearchingEvent" + - $ref: "#/components/schemas/ResponseFunctionCallArgumentsDeltaEvent" + - $ref: "#/components/schemas/ResponseFunctionCallArgumentsDoneEvent" + - $ref: "#/components/schemas/ResponseInProgressEvent" + - $ref: "#/components/schemas/ResponseFailedEvent" + - $ref: "#/components/schemas/ResponseIncompleteEvent" + - $ref: "#/components/schemas/ResponseOutputItemAddedEvent" + - $ref: "#/components/schemas/ResponseOutputItemDoneEvent" + - $ref: "#/components/schemas/ResponseReasoningSummaryPartAddedEvent" + - $ref: "#/components/schemas/ResponseReasoningSummaryPartDoneEvent" + - $ref: "#/components/schemas/ResponseReasoningSummaryTextDeltaEvent" + - $ref: "#/components/schemas/ResponseReasoningSummaryTextDoneEvent" + - $ref: "#/components/schemas/ResponseRefusalDeltaEvent" + - $ref: "#/components/schemas/ResponseRefusalDoneEvent" + - $ref: "#/components/schemas/ResponseTextDeltaEvent" + - $ref: "#/components/schemas/ResponseTextDoneEvent" + - $ref: "#/components/schemas/ResponseWebSearchCallCompletedEvent" + - $ref: "#/components/schemas/ResponseWebSearchCallInProgressEvent" + - $ref: "#/components/schemas/ResponseWebSearchCallSearchingEvent" + - $ref: "#/components/schemas/ResponseImageGenCallCompletedEvent" + - $ref: "#/components/schemas/ResponseImageGenCallGeneratingEvent" + - $ref: "#/components/schemas/ResponseImageGenCallInProgressEvent" + - $ref: "#/components/schemas/ResponseImageGenCallPartialImageEvent" + - $ref: "#/components/schemas/ResponseMCPCallArgumentsDeltaEvent" + - $ref: "#/components/schemas/ResponseMCPCallArgumentsDoneEvent" + - $ref: "#/components/schemas/ResponseMCPCallCompletedEvent" + - $ref: "#/components/schemas/ResponseMCPCallFailedEvent" + - $ref: "#/components/schemas/ResponseMCPCallInProgressEvent" + - $ref: "#/components/schemas/ResponseMCPListToolsCompletedEvent" + - $ref: "#/components/schemas/ResponseMCPListToolsFailedEvent" + - $ref: "#/components/schemas/ResponseMCPListToolsInProgressEvent" + - $ref: "#/components/schemas/ResponseOutputTextAnnotationAddedEvent" + - $ref: "#/components/schemas/ResponseQueuedEvent" + - $ref: "#/components/schemas/ResponseReasoningDeltaEvent" + - $ref: "#/components/schemas/ResponseReasoningDoneEvent" + - $ref: "#/components/schemas/ResponseReasoningSummaryDeltaEvent" + - $ref: "#/components/schemas/ResponseReasoningSummaryDoneEvent" + discriminator: + propertyName: type + ResponseTextDeltaEvent: + type: object + description: Emitted when there is an additional text delta. + properties: + type: + type: string + description: | + The type of the event. Always `response.output_text.delta`. + enum: + - response.output_text.delta + x-stainless-const: true + item_id: + type: string + description: | + The ID of the output item that the text delta was added to. + output_index: + type: integer + description: | + The index of the output item that the text delta was added to. + content_index: + type: integer + description: | + The index of the content part that the text delta was added to. + delta: + type: string + description: | + The text delta that was added. + sequence_number: + type: integer + description: The sequence number for this event. + required: + - type + - item_id + - output_index + - content_index + - delta + - sequence_number + x-oaiMeta: + name: response.output_text.delta + group: responses + example: | + { + "type": "response.output_text.delta", + "item_id": "msg_123", + "output_index": 0, + "content_index": 0, + "delta": "In", + "sequence_number": 1 + } + ResponseTextDoneEvent: + type: object + description: Emitted when text content is finalized. + properties: + type: + type: string + description: | + The type of the event. Always `response.output_text.done`. + enum: + - response.output_text.done + x-stainless-const: true + item_id: + type: string + description: | + The ID of the output item that the text content is finalized. + output_index: + type: integer + description: | + The index of the output item that the text content is finalized. + content_index: + type: integer + description: | + The index of the content part that the text content is finalized. + text: + type: string + description: | + The text content that is finalized. + sequence_number: + type: integer + description: The sequence number for this event. + required: + - type + - item_id + - output_index + - content_index + - text + - sequence_number + x-oaiMeta: + name: response.output_text.done + group: responses + example: > + { + "type": "response.output_text.done", + "item_id": "msg_123", + "output_index": 0, + "content_index": 0, + "text": "In a shimmering forest under a sky full of stars, a lonely unicorn named Lila discovered a hidden pond that glowed with moonlight. Every night, she would leave sparkling, magical flowers by the water's edge, hoping to share her beauty with others. One enchanting evening, she woke to find a group of friendly animals gathered around, eager to be friends and share in her magic.", + "sequence_number": 1 + } + ResponseUsage: + type: object + description: | + Represents token usage details including input tokens, output tokens, + a breakdown of output tokens, and the total tokens used. + properties: + input_tokens: + type: integer + description: The number of input tokens. + input_tokens_details: + type: object + description: A detailed breakdown of the input tokens. + properties: + cached_tokens: + type: integer + description: | + The number of tokens that were retrieved from the cache. + [More on prompt caching](/docs/guides/prompt-caching). + required: + - cached_tokens + output_tokens: + type: integer + description: The number of output tokens. + output_tokens_details: + type: object + description: A detailed breakdown of the output tokens. + properties: + reasoning_tokens: + type: integer + description: The number of reasoning tokens. + required: + - reasoning_tokens + total_tokens: + type: integer + description: The total number of tokens used. + required: + - input_tokens + - input_tokens_details + - output_tokens + - output_tokens_details + - total_tokens + ResponseWebSearchCallCompletedEvent: + type: object + description: Emitted when a web search call is completed. + properties: + type: + type: string + description: | + The type of the event. Always `response.web_search_call.completed`. + enum: + - response.web_search_call.completed + x-stainless-const: true + output_index: + type: integer + description: > + The index of the output item that the web search call is associated + with. + item_id: + type: string + description: | + Unique ID for the output item associated with the web search call. + sequence_number: + type: integer + description: The sequence number of the web search call being processed. + required: + - type + - output_index + - item_id + - sequence_number + x-oaiMeta: + name: response.web_search_call.completed + group: responses + example: | + { + "type": "response.web_search_call.completed", + "output_index": 0, + "item_id": "ws_123", + "sequence_number": 0 + } + ResponseWebSearchCallInProgressEvent: + type: object + description: Emitted when a web search call is initiated. + properties: + type: + type: string + description: > + The type of the event. Always `response.web_search_call.in_progress`. + enum: + - response.web_search_call.in_progress + x-stainless-const: true + output_index: + type: integer + description: > + The index of the output item that the web search call is associated + with. + item_id: + type: string + description: | + Unique ID for the output item associated with the web search call. + sequence_number: + type: integer + description: The sequence number of the web search call being processed. + required: + - type + - output_index + - item_id + - sequence_number + x-oaiMeta: + name: response.web_search_call.in_progress + group: responses + example: | + { + "type": "response.web_search_call.in_progress", + "output_index": 0, + "item_id": "ws_123", + "sequence_number": 0 + } + ResponseWebSearchCallSearchingEvent: + type: object + description: Emitted when a web search call is executing. + properties: + type: + type: string + description: | + The type of the event. Always `response.web_search_call.searching`. + enum: + - response.web_search_call.searching + x-stainless-const: true + output_index: + type: integer + description: > + The index of the output item that the web search call is associated + with. + item_id: + type: string + description: | + Unique ID for the output item associated with the web search call. + sequence_number: + type: integer + description: The sequence number of the web search call being processed. + required: + - type + - output_index + - item_id + - sequence_number + x-oaiMeta: + name: response.web_search_call.searching + group: responses + example: | + { + "type": "response.web_search_call.searching", + "output_index": 0, + "item_id": "ws_123", + "sequence_number": 0 + } + RunCompletionUsage: + type: object + description: Usage statistics related to the run. This value will be `null` if + the run is not in a terminal state (i.e. `in_progress`, `queued`, etc.). + properties: + completion_tokens: + type: integer + description: Number of completion tokens used over the course of the run. + prompt_tokens: + type: integer + description: Number of prompt tokens used over the course of the run. + total_tokens: + type: integer + description: Total number of tokens used (prompt + completion). + required: + - prompt_tokens + - completion_tokens + - total_tokens + nullable: true + RunGraderRequest: + type: object + title: RunGraderRequest + properties: + grader: + type: object + description: The grader used for the fine-tuning job. + oneOf: + - $ref: "#/components/schemas/GraderStringCheck" + - $ref: "#/components/schemas/GraderTextSimilarity" + - $ref: "#/components/schemas/GraderPython" + - $ref: "#/components/schemas/GraderScoreModel" + - $ref: "#/components/schemas/GraderMulti" + item: + type: object + description: > + The dataset item provided to the grader. This will be used to + populate + + the `item` namespace. See [the guide](/docs/guides/graders) for more + details. + model_sample: + type: string + description: > + The model sample to be evaluated. This value will be used to + populate + + the `sample` namespace. See [the guide](/docs/guides/graders) for + more details. + + The `output_json` variable will be populated if the model sample is + a + + valid JSON string. + required: + - grader + - model_sample + RunGraderResponse: + type: object + properties: + reward: + type: number + metadata: + type: object + properties: + name: + type: string + type: + type: string + errors: + type: object + properties: + formula_parse_error: + type: boolean + sample_parse_error: + type: boolean + truncated_observation_error: + type: boolean + unresponsive_reward_error: + type: boolean + invalid_variable_error: + type: boolean + other_error: + type: boolean + python_grader_server_error: + type: boolean + python_grader_server_error_type: + type: string + nullable: true + python_grader_runtime_error: + type: boolean + python_grader_runtime_error_details: + type: string + nullable: true + model_grader_server_error: + type: boolean + model_grader_refusal_error: + type: boolean + model_grader_parse_error: + type: boolean + model_grader_server_error_details: + type: string + nullable: true + required: + - formula_parse_error + - sample_parse_error + - truncated_observation_error + - unresponsive_reward_error + - invalid_variable_error + - other_error + - python_grader_server_error + - python_grader_server_error_type + - python_grader_runtime_error + - python_grader_runtime_error_details + - model_grader_server_error + - model_grader_refusal_error + - model_grader_parse_error + - model_grader_server_error_details + execution_time: + type: number + scores: + type: object + additionalProperties: {} + token_usage: + type: integer + nullable: true + sampled_model_name: + type: string + nullable: true + required: + - name + - type + - errors + - execution_time + - scores + - token_usage + - sampled_model_name + sub_rewards: + type: object + additionalProperties: {} + model_grader_token_usage_per_model: + type: object + additionalProperties: {} + required: + - reward + - metadata + - sub_rewards + - model_grader_token_usage_per_model + RunObject: + type: object + title: A run on a thread + description: Represents an execution run on a [thread](/docs/api-reference/threads). + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `thread.run`. + type: string + enum: + - thread.run + x-stainless-const: true + created_at: + description: The Unix timestamp (in seconds) for when the run was created. + type: integer + thread_id: + description: The ID of the [thread](/docs/api-reference/threads) that was + executed on as a part of this run. + type: string + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) used for + execution of this run. + type: string + status: + description: The status of the run, which can be either `queued`, `in_progress`, + `requires_action`, `cancelling`, `cancelled`, `failed`, `completed`, + `incomplete`, or `expired`. + type: string + enum: + - queued + - in_progress + - requires_action + - cancelling + - cancelled + - failed + - completed + - incomplete + - expired + required_action: + type: object + description: Details on the action required to continue the run. Will be `null` + if no action is required. + nullable: true + properties: + type: + description: For now, this is always `submit_tool_outputs`. + type: string + enum: + - submit_tool_outputs + x-stainless-const: true + submit_tool_outputs: + type: object + description: Details on the tool outputs needed for this run to continue. + properties: + tool_calls: + type: array + description: A list of the relevant tool calls. + items: + $ref: "#/components/schemas/RunToolCallObject" + required: + - tool_calls + required: + - type + - submit_tool_outputs + last_error: + type: object + description: The last error associated with this run. Will be `null` if there + are no errors. + nullable: true + properties: + code: + type: string + description: One of `server_error`, `rate_limit_exceeded`, or `invalid_prompt`. + enum: + - server_error + - rate_limit_exceeded + - invalid_prompt + message: + type: string + description: A human-readable description of the error. + required: + - code + - message + expires_at: + description: The Unix timestamp (in seconds) for when the run will expire. + type: integer + nullable: true + started_at: + description: The Unix timestamp (in seconds) for when the run was started. + type: integer + nullable: true + cancelled_at: + description: The Unix timestamp (in seconds) for when the run was cancelled. + type: integer + nullable: true + failed_at: + description: The Unix timestamp (in seconds) for when the run failed. + type: integer + nullable: true + completed_at: + description: The Unix timestamp (in seconds) for when the run was completed. + type: integer + nullable: true + incomplete_details: + description: Details on why the run is incomplete. Will be `null` if the run is + not incomplete. + type: object + nullable: true + properties: + reason: + description: The reason why the run is incomplete. This will point to which + specific token limit was reached over the course of the run. + type: string + enum: + - max_completion_tokens + - max_prompt_tokens + model: + description: The model that the [assistant](/docs/api-reference/assistants) used + for this run. + type: string + instructions: + description: The instructions that the + [assistant](/docs/api-reference/assistants) used for this run. + type: string + tools: + description: The list of tools that the + [assistant](/docs/api-reference/assistants) used for this run. + default: [] + type: array + maxItems: 20 + items: + oneOf: + - $ref: "#/components/schemas/AssistantToolsCode" + - $ref: "#/components/schemas/AssistantToolsFileSearch" + - $ref: "#/components/schemas/AssistantToolsFunction" + metadata: + $ref: "#/components/schemas/Metadata" + usage: + $ref: "#/components/schemas/RunCompletionUsage" + temperature: + description: The sampling temperature used for this run. If not set, defaults to + 1. + type: number + nullable: true + top_p: + description: The nucleus sampling value used for this run. If not set, defaults + to 1. + type: number + nullable: true + max_prompt_tokens: + type: integer + nullable: true + description: > + The maximum number of prompt tokens specified to have been used over + the course of the run. + minimum: 256 + max_completion_tokens: + type: integer + nullable: true + description: > + The maximum number of completion tokens specified to have been used + over the course of the run. + minimum: 256 + truncation_strategy: + allOf: + - $ref: "#/components/schemas/TruncationObject" + - nullable: true + tool_choice: + allOf: + - $ref: "#/components/schemas/AssistantsApiToolChoiceOption" + - nullable: true + parallel_tool_calls: + $ref: "#/components/schemas/ParallelToolCalls" + response_format: + $ref: "#/components/schemas/AssistantsApiResponseFormatOption" + nullable: true + required: + - id + - object + - created_at + - thread_id + - assistant_id + - status + - required_action + - last_error + - expires_at + - started_at + - cancelled_at + - failed_at + - completed_at + - model + - instructions + - tools + - metadata + - usage + - incomplete_details + - max_prompt_tokens + - max_completion_tokens + - truncation_strategy + - tool_choice + - parallel_tool_calls + - response_format + x-oaiMeta: + name: The run object + beta: true + example: | + { + "id": "run_abc123", + "object": "thread.run", + "created_at": 1698107661, + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "status": "completed", + "started_at": 1699073476, + "expires_at": null, + "cancelled_at": null, + "failed_at": null, + "completed_at": 1699073498, + "last_error": null, + "model": "gpt-4o", + "instructions": null, + "tools": [{"type": "file_search"}, {"type": "code_interpreter"}], + "metadata": {}, + "incomplete_details": null, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + }, + "temperature": 1.0, + "top_p": 1.0, + "max_prompt_tokens": 1000, + "max_completion_tokens": 1000, + "truncation_strategy": { + "type": "auto", + "last_messages": null + }, + "response_format": "auto", + "tool_choice": "auto", + "parallel_tool_calls": true + } + RunStepCompletionUsage: + type: object + description: Usage statistics related to the run step. This value will be `null` + while the run step's status is `in_progress`. + properties: + completion_tokens: + type: integer + description: Number of completion tokens used over the course of the run step. + prompt_tokens: + type: integer + description: Number of prompt tokens used over the course of the run step. + total_tokens: + type: integer + description: Total number of tokens used (prompt + completion). + required: + - prompt_tokens + - completion_tokens + - total_tokens + nullable: true + RunStepDeltaObject: + type: object + title: Run step delta object + description: > + Represents a run step delta i.e. any changed fields on a run step during + streaming. + properties: + id: + description: The identifier of the run step, which can be referenced in API + endpoints. + type: string + object: + description: The object type, which is always `thread.run.step.delta`. + type: string + enum: + - thread.run.step.delta + x-stainless-const: true + delta: + description: The delta containing the fields that have changed on the run step. + type: object + properties: + step_details: + type: object + description: The details of the run step. + oneOf: + - $ref: "#/components/schemas/RunStepDeltaStepDetailsMessageCreationObject" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsObject" + required: + - id + - object + - delta + x-oaiMeta: + name: The run step delta object + beta: true + example: | + { + "id": "step_123", + "object": "thread.run.step.delta", + "delta": { + "step_details": { + "type": "tool_calls", + "tool_calls": [ + { + "index": 0, + "id": "call_123", + "type": "code_interpreter", + "code_interpreter": { "input": "", "outputs": [] } + } + ] + } + } + } + RunStepDeltaStepDetailsMessageCreationObject: + title: Message creation + type: object + description: Details of the message creation by the run step. + properties: + type: + description: Always `message_creation`. + type: string + enum: + - message_creation + x-stainless-const: true + message_creation: + type: object + properties: + message_id: + type: string + description: The ID of the message that was created by this run step. + required: + - type + RunStepDeltaStepDetailsToolCallsCodeObject: + title: Code interpreter tool call + type: object + description: Details of the Code Interpreter tool call the run step was involved in. + properties: + index: + type: integer + description: The index of the tool call in the tool calls array. + id: + type: string + description: The ID of the tool call. + type: + type: string + description: The type of tool call. This is always going to be + `code_interpreter` for this type of tool call. + enum: + - code_interpreter + x-stainless-const: true + code_interpreter: + type: object + description: The Code Interpreter tool call definition. + properties: + input: + type: string + description: The input to the Code Interpreter tool call. + outputs: + type: array + description: The outputs from the Code Interpreter tool call. Code Interpreter + can output one or more items, including text (`logs`) or images + (`image`). Each of these are represented by a different object + type. + items: + type: object + oneOf: + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeOutputLogsObjec\ + t" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeOutputImageObje\ + ct" + required: + - index + - type + RunStepDeltaStepDetailsToolCallsCodeOutputImageObject: + title: Code interpreter image output + type: object + properties: + index: + type: integer + description: The index of the output in the outputs array. + type: + description: Always `image`. + type: string + enum: + - image + x-stainless-const: true + image: + type: object + properties: + file_id: + description: The [file](/docs/api-reference/files) ID of the image. + type: string + required: + - index + - type + RunStepDeltaStepDetailsToolCallsCodeOutputLogsObject: + title: Code interpreter log output + type: object + description: Text output from the Code Interpreter tool call as part of a run step. + properties: + index: + type: integer + description: The index of the output in the outputs array. + type: + description: Always `logs`. + type: string + enum: + - logs + x-stainless-const: true + logs: + type: string + description: The text output from the Code Interpreter tool call. + required: + - index + - type + RunStepDeltaStepDetailsToolCallsFileSearchObject: + title: File search tool call + type: object + properties: + index: + type: integer + description: The index of the tool call in the tool calls array. + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `file_search` for + this type of tool call. + enum: + - file_search + x-stainless-const: true + file_search: + type: object + description: For now, this is always going to be an empty object. + x-oaiTypeLabel: map + required: + - index + - type + - file_search + RunStepDeltaStepDetailsToolCallsFunctionObject: + type: object + title: Function tool call + properties: + index: + type: integer + description: The index of the tool call in the tool calls array. + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `function` for + this type of tool call. + enum: + - function + x-stainless-const: true + function: + type: object + description: The definition of the function that was called. + properties: + name: + type: string + description: The name of the function. + arguments: + type: string + description: The arguments passed to the function. + output: + type: string + description: The output of the function. This will be `null` if the outputs have + not been [submitted](/docs/api-reference/runs/submitToolOutputs) + yet. + nullable: true + required: + - index + - type + RunStepDeltaStepDetailsToolCallsObject: + title: Tool calls + type: object + description: Details of the tool call. + properties: + type: + description: Always `tool_calls`. + type: string + enum: + - tool_calls + x-stainless-const: true + tool_calls: + type: array + description: > + An array of tool calls the run step was involved in. These can be + associated with one of three types of tools: `code_interpreter`, + `file_search`, or `function`. + items: + oneOf: + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsCodeObject" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsFileSearchObject" + - $ref: "#/components/schemas/RunStepDeltaStepDetailsToolCallsFunctionObject" + required: + - type + RunStepDetailsMessageCreationObject: + title: Message creation + type: object + description: Details of the message creation by the run step. + properties: + type: + description: Always `message_creation`. + type: string + enum: + - message_creation + x-stainless-const: true + message_creation: + type: object + properties: + message_id: + type: string + description: The ID of the message that was created by this run step. + required: + - message_id + required: + - type + - message_creation + RunStepDetailsToolCallsCodeObject: + title: Code Interpreter tool call + type: object + description: Details of the Code Interpreter tool call the run step was involved in. + properties: + id: + type: string + description: The ID of the tool call. + type: + type: string + description: The type of tool call. This is always going to be + `code_interpreter` for this type of tool call. + enum: + - code_interpreter + x-stainless-const: true + code_interpreter: + type: object + description: The Code Interpreter tool call definition. + required: + - input + - outputs + properties: + input: + type: string + description: The input to the Code Interpreter tool call. + outputs: + type: array + description: The outputs from the Code Interpreter tool call. Code Interpreter + can output one or more items, including text (`logs`) or images + (`image`). Each of these are represented by a different object + type. + items: + type: object + oneOf: + - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeOutputLogsObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeOutputImageObject" + required: + - id + - type + - code_interpreter + RunStepDetailsToolCallsCodeOutputImageObject: + title: Code Interpreter image output + type: object + properties: + type: + description: Always `image`. + type: string + enum: + - image + x-stainless-const: true + image: + type: object + properties: + file_id: + description: The [file](/docs/api-reference/files) ID of the image. + type: string + required: + - file_id + required: + - type + - image + RunStepDetailsToolCallsCodeOutputLogsObject: + title: Code Interpreter log output + type: object + description: Text output from the Code Interpreter tool call as part of a run step. + properties: + type: + description: Always `logs`. + type: string + enum: + - logs + x-stainless-const: true + logs: + type: string + description: The text output from the Code Interpreter tool call. + required: + - type + - logs + RunStepDetailsToolCallsFileSearchObject: + title: File search tool call + type: object + properties: + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `file_search` for + this type of tool call. + enum: + - file_search + x-stainless-const: true + file_search: + type: object + description: For now, this is always going to be an empty object. + x-oaiTypeLabel: map + properties: + ranking_options: + $ref: "#/components/schemas/RunStepDetailsToolCallsFileSearchRankingOptionsObje\ + ct" + results: + type: array + description: The results of the file search. + items: + $ref: "#/components/schemas/RunStepDetailsToolCallsFileSearchResultObject" + required: + - id + - type + - file_search + RunStepDetailsToolCallsFileSearchRankingOptionsObject: + title: File search tool call ranking options + type: object + description: The ranking options for the file search. + properties: + ranker: + $ref: "#/components/schemas/FileSearchRanker" + score_threshold: + type: number + description: The score threshold for the file search. All values must be a + floating point number between 0 and 1. + minimum: 0 + maximum: 1 + required: + - ranker + - score_threshold + RunStepDetailsToolCallsFileSearchResultObject: + title: File search tool call result + type: object + description: A result instance of the file search. + x-oaiTypeLabel: map + properties: + file_id: + type: string + description: The ID of the file that result was found in. + file_name: + type: string + description: The name of the file that result was found in. + score: + type: number + description: The score of the result. All values must be a floating point number + between 0 and 1. + minimum: 0 + maximum: 1 + content: + type: array + description: The content of the result that was found. The content is only + included if requested via the include query parameter. + items: + type: object + properties: + type: + type: string + description: The type of the content. + enum: + - text + x-stainless-const: true + text: + type: string + description: The text content of the file. + required: + - file_id + - file_name + - score + RunStepDetailsToolCallsFunctionObject: + type: object + title: Function tool call + properties: + id: + type: string + description: The ID of the tool call object. + type: + type: string + description: The type of tool call. This is always going to be `function` for + this type of tool call. + enum: + - function + x-stainless-const: true + function: + type: object + description: The definition of the function that was called. + properties: + name: + type: string + description: The name of the function. + arguments: + type: string + description: The arguments passed to the function. + output: + type: string + description: The output of the function. This will be `null` if the outputs have + not been [submitted](/docs/api-reference/runs/submitToolOutputs) + yet. + nullable: true + required: + - name + - arguments + - output + required: + - id + - type + - function + RunStepDetailsToolCallsObject: + title: Tool calls + type: object + description: Details of the tool call. + properties: + type: + description: Always `tool_calls`. + type: string + enum: + - tool_calls + x-stainless-const: true + tool_calls: + type: array + description: > + An array of tool calls the run step was involved in. These can be + associated with one of three types of tools: `code_interpreter`, + `file_search`, or `function`. + items: + oneOf: + - $ref: "#/components/schemas/RunStepDetailsToolCallsCodeObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsFileSearchObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsFunctionObject" + required: + - type + - tool_calls + RunStepObject: + type: object + title: Run steps + description: | + Represents a step in execution of a run. + properties: + id: + description: The identifier of the run step, which can be referenced in API + endpoints. + type: string + object: + description: The object type, which is always `thread.run.step`. + type: string + enum: + - thread.run.step + x-stainless-const: true + created_at: + description: The Unix timestamp (in seconds) for when the run step was created. + type: integer + assistant_id: + description: The ID of the [assistant](/docs/api-reference/assistants) + associated with the run step. + type: string + thread_id: + description: The ID of the [thread](/docs/api-reference/threads) that was run. + type: string + run_id: + description: The ID of the [run](/docs/api-reference/runs) that this run step is + a part of. + type: string + type: + description: The type of run step, which can be either `message_creation` or + `tool_calls`. + type: string + enum: + - message_creation + - tool_calls + status: + description: The status of the run step, which can be either `in_progress`, + `cancelled`, `failed`, `completed`, or `expired`. + type: string + enum: + - in_progress + - cancelled + - failed + - completed + - expired + step_details: + type: object + description: The details of the run step. + oneOf: + - $ref: "#/components/schemas/RunStepDetailsMessageCreationObject" + - $ref: "#/components/schemas/RunStepDetailsToolCallsObject" + last_error: + type: object + description: The last error associated with this run step. Will be `null` if + there are no errors. + nullable: true + properties: + code: + type: string + description: One of `server_error` or `rate_limit_exceeded`. + enum: + - server_error + - rate_limit_exceeded + message: + type: string + description: A human-readable description of the error. + required: + - code + - message + expired_at: + description: The Unix timestamp (in seconds) for when the run step expired. A + step is considered expired if the parent run is expired. + type: integer + nullable: true + cancelled_at: + description: The Unix timestamp (in seconds) for when the run step was cancelled. + type: integer + nullable: true + failed_at: + description: The Unix timestamp (in seconds) for when the run step failed. + type: integer + nullable: true + completed_at: + description: The Unix timestamp (in seconds) for when the run step completed. + type: integer + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + usage: + $ref: "#/components/schemas/RunStepCompletionUsage" + required: + - id + - object + - created_at + - assistant_id + - thread_id + - run_id + - type + - status + - step_details + - last_error + - expired_at + - cancelled_at + - failed_at + - completed_at + - metadata + - usage + x-oaiMeta: + name: The run step object + beta: true + example: | + { + "id": "step_abc123", + "object": "thread.run.step", + "created_at": 1699063291, + "run_id": "run_abc123", + "assistant_id": "asst_abc123", + "thread_id": "thread_abc123", + "type": "message_creation", + "status": "completed", + "cancelled_at": null, + "completed_at": 1699063291, + "expired_at": null, + "failed_at": null, + "last_error": null, + "step_details": { + "type": "message_creation", + "message_creation": { + "message_id": "msg_abc123" + } + }, + "usage": { + "prompt_tokens": 123, + "completion_tokens": 456, + "total_tokens": 579 + } + } + RunStepStreamEvent: + oneOf: + - type: object + properties: + event: + type: string + enum: + - thread.run.step.created + x-stainless-const: true + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + is created. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.in_progress + x-stainless-const: true + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + moves to an `in_progress` state. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.delta + x-stainless-const: true + data: + $ref: "#/components/schemas/RunStepDeltaObject" + required: + - event + - data + description: Occurs when parts of a [run + step](/docs/api-reference/run-steps/step-object) are being streamed. + x-oaiMeta: + dataDescription: "`data` is a [run step + delta](/docs/api-reference/assistants-streaming/run-step-delta-ob\ + ject)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.completed + x-stainless-const: true + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + is completed. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.failed + x-stainless-const: true + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + fails. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.cancelled + x-stainless-const: true + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + is cancelled. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.step.expired + x-stainless-const: true + data: + $ref: "#/components/schemas/RunStepObject" + required: + - event + - data + description: Occurs when a [run step](/docs/api-reference/run-steps/step-object) + expires. + x-oaiMeta: + dataDescription: "`data` is a [run step](/docs/api-reference/run-steps/step-object)" + RunStreamEvent: + oneOf: + - type: object + properties: + event: + type: string + enum: + - thread.run.created + x-stainless-const: true + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a new [run](/docs/api-reference/runs/object) is created. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.queued + x-stainless-const: true + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to a + `queued` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.in_progress + x-stainless-const: true + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to an + `in_progress` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.requires_action + x-stainless-const: true + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to a + `requires_action` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.completed + x-stainless-const: true + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) is completed. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.incomplete + x-stainless-const: true + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) ends with + status `incomplete`. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.failed + x-stainless-const: true + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) fails. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.cancelling + x-stainless-const: true + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) moves to a + `cancelling` status. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.cancelled + x-stainless-const: true + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) is cancelled. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + - type: object + properties: + event: + type: string + enum: + - thread.run.expired + x-stainless-const: true + data: + $ref: "#/components/schemas/RunObject" + required: + - event + - data + description: Occurs when a [run](/docs/api-reference/runs/object) expires. + x-oaiMeta: + dataDescription: "`data` is a [run](/docs/api-reference/runs/object)" + RunToolCallObject: + type: object + description: Tool call objects + properties: + id: + type: string + description: The ID of the tool call. This ID must be referenced when you submit + the tool outputs in using the [Submit tool outputs to + run](/docs/api-reference/runs/submitToolOutputs) endpoint. + type: + type: string + description: The type of tool call the output is required for. For now, this is + always `function`. + enum: + - function + x-stainless-const: true + function: + type: object + description: The function definition. + properties: + name: + type: string + description: The name of the function. + arguments: + type: string + description: The arguments that the model expects you to pass to the function. + required: + - name + - arguments + required: + - id + - type + - function + Screenshot: + type: object + title: Screenshot + description: | + A screenshot action. + properties: + type: + type: string + enum: + - screenshot + default: screenshot + description: | + Specifies the event type. For a screenshot action, this property is + always set to `screenshot`. + x-stainless-const: true + required: + - type + Scroll: + type: object + title: Scroll + description: | + A scroll action. + properties: + type: + type: string + enum: + - scroll + default: scroll + description: | + Specifies the event type. For a scroll action, this property is + always set to `scroll`. + x-stainless-const: true + x: + type: integer + description: | + The x-coordinate where the scroll occurred. + y: + type: integer + description: | + The y-coordinate where the scroll occurred. + scroll_x: + type: integer + description: | + The horizontal scroll distance. + scroll_y: + type: integer + description: | + The vertical scroll distance. + required: + - type + - x + - y + - scroll_x + - scroll_y + ServiceTier: + type: string + description: > + Specifies the latency tier to use for processing the request. This + parameter is relevant for customers subscribed to the scale tier + service: + - If set to 'auto', and the Project is Scale tier enabled, the system + will utilize scale tier credits until they are exhausted. + - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarantee. + - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarantee. + - If set to 'flex', the request will be processed with the Flex Processing service tier. [Learn more](/docs/guides/flex-processing). + - When not set, the default behavior is 'auto'. + + When this parameter is set, the response body will include the `service_tier` utilized. + enum: + - auto + - default + - flex + - scale + nullable: true + default: auto + StaticChunkingStrategy: + type: object + additionalProperties: false + properties: + max_chunk_size_tokens: + type: integer + minimum: 100 + maximum: 4096 + description: The maximum number of tokens in each chunk. The default value is + `800`. The minimum value is `100` and the maximum value is `4096`. + chunk_overlap_tokens: + type: integer + description: > + The number of tokens that overlap between chunks. The default value + is `400`. + + + Note that the overlap must not exceed half of + `max_chunk_size_tokens`. + required: + - max_chunk_size_tokens + - chunk_overlap_tokens + StaticChunkingStrategyRequestParam: + type: object + title: Static Chunking Strategy + description: Customize your own chunking strategy by setting chunk size and + chunk overlap. + additionalProperties: false + properties: + type: + type: string + description: Always `static`. + enum: + - static + x-stainless-const: true + static: + $ref: "#/components/schemas/StaticChunkingStrategy" + required: + - type + - static + StaticChunkingStrategyResponseParam: + type: object + title: Static Chunking Strategy + additionalProperties: false + properties: + type: + type: string + description: Always `static`. + enum: + - static + x-stainless-const: true + static: + $ref: "#/components/schemas/StaticChunkingStrategy" + required: + - type + - static + StopConfiguration: + description: | + Not supported with latest reasoning models `o3` and `o4-mini`. + + Up to 4 sequences where the API will stop generating further tokens. The + returned text will not contain the stop sequence. + default: null + nullable: true + oneOf: + - type: string + default: <|endoftext|> + example: "\n" + nullable: true + - type: array + minItems: 1 + maxItems: 4 + items: + type: string + example: '["\n"]' + SubmitToolOutputsRunRequest: + type: object + additionalProperties: false + properties: + tool_outputs: + description: A list of tools for which the outputs are being submitted. + type: array + items: + type: object + properties: + tool_call_id: + type: string + description: The ID of the tool call in the `required_action` object within the + run object the output is being submitted for. + output: + type: string + description: The output of the tool call to be submitted to continue the run. + stream: + type: boolean + nullable: true + description: > + If `true`, returns a stream of events that happen during the Run as + server-sent events, terminating when the Run enters a terminal state + with a `data: [DONE]` message. + required: + - tool_outputs + TextResponseFormatConfiguration: + description: > + An object specifying the format that the model must output. + + + Configuring `{ "type": "json_schema" }` enables Structured Outputs, + + which ensures the model will match your supplied JSON schema. Learn more + in the + + [Structured Outputs guide](/docs/guides/structured-outputs). + + + The default format is `{ "type": "text" }` with no additional options. + + + **Not recommended for gpt-4o and newer models:** + + + Setting to `{ "type": "json_object" }` enables the older JSON mode, + which + + ensures the message the model generates is valid JSON. Using + `json_schema` + + is preferred for models that support it. + oneOf: + - $ref: "#/components/schemas/ResponseFormatText" + - $ref: "#/components/schemas/TextResponseFormatJsonSchema" + - $ref: "#/components/schemas/ResponseFormatJsonObject" + TextResponseFormatJsonSchema: + type: object + title: JSON schema + description: | + JSON Schema response format. Used to generate structured JSON responses. + Learn more about [Structured Outputs](/docs/guides/structured-outputs). + properties: + type: + type: string + description: The type of response format being defined. Always `json_schema`. + enum: + - json_schema + x-stainless-const: true + description: + type: string + description: > + A description of what the response format is for, used by the model + to + + determine how to respond in the format. + name: + type: string + description: | + The name of the response format. Must be a-z, A-Z, 0-9, or contain + underscores and dashes, with a maximum length of 64. + schema: + $ref: "#/components/schemas/ResponseFormatJsonSchemaSchema" + strict: + type: boolean + nullable: true + default: false + description: > + Whether to enable strict schema adherence when generating the + output. + + If set to true, the model will always follow the exact schema + defined + + in the `schema` field. Only a subset of JSON Schema is supported + when + + `strict` is `true`. To learn more, read the [Structured Outputs + + guide](/docs/guides/structured-outputs). + required: + - type + - schema + - name + ThreadObject: + type: object + title: Thread + description: Represents a thread that contains + [messages](/docs/api-reference/messages). + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `thread`. + type: string + enum: + - thread + x-stainless-const: true + created_at: + description: The Unix timestamp (in seconds) for when the thread was created. + type: integer + tool_resources: + type: object + description: > + A set of resources that are made available to the assistant's tools + in this thread. The resources are specific to the type of tool. For + example, the `code_interpreter` tool requires a list of file IDs, + while the `file_search` tool requires a list of vector store IDs. + properties: + code_interpreter: + type: object + properties: + file_ids: + type: array + description: > + A list of [file](/docs/api-reference/files) IDs made + available to the `code_interpreter` tool. There can be a + maximum of 20 files associated with the tool. + default: [] + maxItems: 20 + items: + type: string + file_search: + type: object + properties: + vector_store_ids: + type: array + description: > + The [vector store](/docs/api-reference/vector-stores/object) + attached to this thread. There can be a maximum of 1 vector + store attached to the thread. + maxItems: 1 + items: + type: string + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + required: + - id + - object + - created_at + - tool_resources + - metadata + x-oaiMeta: + name: The thread object + beta: true + example: | + { + "id": "thread_abc123", + "object": "thread", + "created_at": 1698107661, + "metadata": {} + } + ThreadStreamEvent: + oneOf: + - type: object + properties: + enabled: + type: boolean + description: Whether to enable input audio transcription. + event: + type: string + enum: + - thread.created + x-stainless-const: true + data: + $ref: "#/components/schemas/ThreadObject" + required: + - event + - data + description: Occurs when a new [thread](/docs/api-reference/threads/object) is + created. + x-oaiMeta: + dataDescription: "`data` is a [thread](/docs/api-reference/threads/object)" + ToggleCertificatesRequest: + type: object + properties: + certificate_ids: + type: array + items: + type: string + example: cert_abc + minItems: 1 + maxItems: 10 + required: + - certificate_ids + Tool: + description: | + A tool that can be used to generate a response. + discriminator: + propertyName: type + oneOf: + - $ref: "#/components/schemas/FunctionTool" + - $ref: "#/components/schemas/FileSearchTool" + - $ref: "#/components/schemas/WebSearchPreviewTool" + - $ref: "#/components/schemas/ComputerUsePreviewTool" + - $ref: "#/components/schemas/MCPTool" + - $ref: "#/components/schemas/CodeInterpreterTool" + - $ref: "#/components/schemas/ImageGenTool" + - $ref: "#/components/schemas/LocalShellTool" + ToolChoiceFunction: + type: object + title: Function tool + description: | + Use this option to force the model to call a specific function. + properties: + type: + type: string + enum: + - function + description: For function calling, the type is always `function`. + x-stainless-const: true + name: + type: string + description: The name of the function to call. + required: + - type + - name + ToolChoiceOptions: + type: string + title: Tool choice mode + description: > + Controls which (if any) tool is called by the model. + + + `none` means the model will not call any tool and instead generates a + message. + + + `auto` means the model can pick between generating a message or calling + one or + + more tools. + + + `required` means the model must call one or more tools. + enum: + - none + - auto + - required + ToolChoiceTypes: + type: object + title: Hosted tool + description: > + Indicates that the model should use a built-in tool to generate a + response. + + [Learn more about built-in tools](/docs/guides/tools). + properties: + type: + type: string + description: | + The type of hosted tool the model should to use. Learn more about + [built-in tools](/docs/guides/tools). + + Allowed values are: + - `file_search` + - `web_search_preview` + - `computer_use_preview` + - `code_interpreter` + - `mcp` + - `image_generation` + enum: + - file_search + - web_search_preview + - computer_use_preview + - web_search_preview_2025_03_11 + - image_generation + - code_interpreter + - mcp + required: + - type + TranscriptTextDeltaEvent: + type: object + description: Emitted when there is an additional text delta. This is also the + first event emitted when the transcription starts. Only emitted when you + [create a transcription](/docs/api-reference/audio/create-transcription) + with the `Stream` parameter set to `true`. + properties: + type: + type: string + description: | + The type of the event. Always `transcript.text.delta`. + enum: + - transcript.text.delta + x-stainless-const: true + delta: + type: string + description: | + The text delta that was additionally transcribed. + logprobs: + type: array + description: > + The log probabilities of the delta. Only included if you [create a + transcription](/docs/api-reference/audio/create-transcription) with + the `include[]` parameter set to `logprobs`. + items: + type: object + properties: + token: + type: string + description: | + The token that was used to generate the log probability. + logprob: + type: number + description: | + The log probability of the token. + bytes: + type: array + items: + type: integer + description: | + The bytes that were used to generate the log probability. + required: + - type + - delta + x-oaiMeta: + name: Stream Event (transcript.text.delta) + group: transcript + example: | + { + "type": "transcript.text.delta", + "delta": " wonderful" + } + TranscriptTextDoneEvent: + type: object + description: Emitted when the transcription is complete. Contains the complete + transcription text. Only emitted when you [create a + transcription](/docs/api-reference/audio/create-transcription) with the + `Stream` parameter set to `true`. + properties: + type: + type: string + description: | + The type of the event. Always `transcript.text.done`. + enum: + - transcript.text.done + x-stainless-const: true + text: + type: string + description: | + The text that was transcribed. + logprobs: + type: array + description: > + The log probabilities of the individual tokens in the transcription. + Only included if you [create a + transcription](/docs/api-reference/audio/create-transcription) with + the `include[]` parameter set to `logprobs`. + items: + type: object + properties: + token: + type: string + description: | + The token that was used to generate the log probability. + logprob: + type: number + description: | + The log probability of the token. + bytes: + type: array + items: + type: integer + description: | + The bytes that were used to generate the log probability. + required: + - type + - text + x-oaiMeta: + name: Stream Event (transcript.text.done) + group: transcript + example: > + { + "type": "transcript.text.done", + "text": "I see skies of blue and clouds of white, the bright blessed days, the dark sacred nights, and I think to myself, what a wonderful world." + } + TranscriptionChunkingStrategy: + type: object + description: >- + Controls how the audio is cut into chunks. When set to `"auto"`, the + + server first normalizes loudness and then uses voice activity detection + (VAD) to + + choose boundaries. `server_vad` object can be provided to tweak VAD + detection + + parameters manually. If unset, the audio is transcribed as a single + block. + oneOf: + - type: string + enum: + - auto + default: + - auto + description: > + Automatically set chunking parameters based on the audio. Must be + set to `"auto"`. + x-stainless-const: true + - $ref: "#/components/schemas/VadConfig" + TranscriptionInclude: + type: string + enum: + - logprobs + default: [] + TranscriptionSegment: + type: object + properties: + id: + type: integer + description: Unique identifier of the segment. + seek: + type: integer + description: Seek offset of the segment. + start: + type: number + format: float + description: Start time of the segment in seconds. + end: + type: number + format: float + description: End time of the segment in seconds. + text: + type: string + description: Text content of the segment. + tokens: + type: array + items: + type: integer + description: Array of token IDs for the text content. + temperature: + type: number + format: float + description: Temperature parameter used for generating the segment. + avg_logprob: + type: number + format: float + description: Average logprob of the segment. If the value is lower than -1, + consider the logprobs failed. + compression_ratio: + type: number + format: float + description: Compression ratio of the segment. If the value is greater than 2.4, + consider the compression failed. + no_speech_prob: + type: number + format: float + description: Probability of no speech in the segment. If the value is higher + than 1.0 and the `avg_logprob` is below -1, consider this segment + silent. + required: + - id + - seek + - start + - end + - text + - tokens + - temperature + - avg_logprob + - compression_ratio + - no_speech_prob + TranscriptionWord: + type: object + properties: + word: + type: string + description: The text content of the word. + start: + type: number + format: float + description: Start time of the word in seconds. + end: + type: number + format: float + description: End time of the word in seconds. + required: + - word + - start + - end + TruncationObject: + type: object + title: Thread Truncation Controls + description: Controls for how a thread will be truncated prior to the run. Use + this to control the intial context window of the run. + properties: + type: + type: string + description: The truncation strategy to use for the thread. The default is + `auto`. If set to `last_messages`, the thread will be truncated to + the n most recent messages in the thread. When set to `auto`, + messages in the middle of the thread will be dropped to fit the + context length of the model, `max_prompt_tokens`. + enum: + - auto + - last_messages + last_messages: + type: integer + description: The number of most recent messages from the thread when + constructing the context for the run. + minimum: 1 + nullable: true + required: + - type + Type: + type: object + title: Type + description: | + An action to type in text. + properties: + type: + type: string + enum: + - type + default: type + description: | + Specifies the event type. For a type action, this property is + always set to `type`. + x-stainless-const: true + text: + type: string + description: | + The text to type. + required: + - type + - text + UpdateVectorStoreFileAttributesRequest: + type: object + additionalProperties: false + properties: + attributes: + $ref: "#/components/schemas/VectorStoreFileAttributes" + required: + - attributes + x-oaiMeta: + name: Update vector store file attributes request + UpdateVectorStoreRequest: + type: object + additionalProperties: false + properties: + name: + description: The name of the vector store. + type: string + nullable: true + expires_after: + allOf: + - $ref: "#/components/schemas/VectorStoreExpirationAfter" + - nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + Upload: + type: object + title: Upload + description: | + The Upload object can accept byte chunks in the form of Parts. + properties: + id: + type: string + description: The Upload unique identifier, which can be referenced in API + endpoints. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the Upload was created. + filename: + type: string + description: The name of the file to be uploaded. + bytes: + type: integer + description: The intended number of bytes to be uploaded. + purpose: + type: string + description: The intended purpose of the file. [Please refer + here](/docs/api-reference/files/object#files/object-purpose) for + acceptable values. + status: + type: string + description: The status of the Upload. + enum: + - pending + - completed + - cancelled + - expired + expires_at: + type: integer + description: The Unix timestamp (in seconds) for when the Upload will expire. + object: + type: string + description: The object type, which is always "upload". + enum: + - upload + x-stainless-const: true + file: + allOf: + - $ref: "#/components/schemas/OpenAIFile" + - nullable: true + description: The ready File object after the Upload is completed. + required: + - bytes + - created_at + - expires_at + - filename + - id + - purpose + - status + x-oaiMeta: + name: The upload object + example: | + { + "id": "upload_abc123", + "object": "upload", + "bytes": 2147483648, + "created_at": 1719184911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + "status": "completed", + "expires_at": 1719127296, + "file": { + "id": "file-xyz321", + "object": "file", + "bytes": 2147483648, + "created_at": 1719186911, + "filename": "training_examples.jsonl", + "purpose": "fine-tune", + } + } + UploadCertificateRequest: + type: object + properties: + name: + type: string + description: An optional name for the certificate + content: + type: string + description: The certificate content in PEM format + required: + - content + UploadPart: + type: object + title: UploadPart + description: > + The upload Part represents a chunk of bytes we can add to an Upload + object. + properties: + id: + type: string + description: The upload Part unique identifier, which can be referenced in API + endpoints. + created_at: + type: integer + description: The Unix timestamp (in seconds) for when the Part was created. + upload_id: + type: string + description: The ID of the Upload object that this Part was added to. + object: + type: string + description: The object type, which is always `upload.part`. + enum: + - upload.part + x-stainless-const: true + required: + - created_at + - id + - object + - upload_id + x-oaiMeta: + name: The upload part object + example: | + { + "id": "part_def456", + "object": "upload.part", + "created_at": 1719186911, + "upload_id": "upload_abc123" + } + UsageAudioSpeechesResult: + type: object + description: The aggregated audio speeches usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.audio_speeches.result + x-stainless-const: true + characters: + type: integer + description: The number of characters processed. + num_model_requests: + type: integer + description: The count of requests made to the model. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + required: + - object + - characters + - num_model_requests + x-oaiMeta: + name: Audio speeches usage object + example: | + { + "object": "organization.usage.audio_speeches.result", + "characters": 45, + "num_model_requests": 1, + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "tts-1" + } + UsageAudioTranscriptionsResult: + type: object + description: The aggregated audio transcriptions usage details of the specific + time bucket. + properties: + object: + type: string + enum: + - organization.usage.audio_transcriptions.result + x-stainless-const: true + seconds: + type: integer + description: The number of seconds processed. + num_model_requests: + type: integer + description: The count of requests made to the model. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + required: + - object + - seconds + - num_model_requests + x-oaiMeta: + name: Audio transcriptions usage object + example: | + { + "object": "organization.usage.audio_transcriptions.result", + "seconds": 10, + "num_model_requests": 1, + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "tts-1" + } + UsageCodeInterpreterSessionsResult: + type: object + description: The aggregated code interpreter sessions usage details of the + specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.code_interpreter_sessions.result + x-stainless-const: true + num_sessions: + type: integer + description: The number of code interpreter sessions. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + required: + - object + - sessions + x-oaiMeta: + name: Code interpreter sessions usage object + example: | + { + "object": "organization.usage.code_interpreter_sessions.result", + "num_sessions": 1, + "project_id": "proj_abc" + } + UsageCompletionsResult: + type: object + description: The aggregated completions usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.completions.result + x-stainless-const: true + input_tokens: + type: integer + description: The aggregated number of text input tokens used, including cached + tokens. For customers subscribe to scale tier, this includes scale + tier tokens. + input_cached_tokens: + type: integer + description: The aggregated number of text input tokens that has been cached + from previous requests. For customers subscribe to scale tier, this + includes scale tier tokens. + output_tokens: + type: integer + description: The aggregated number of text output tokens used. For customers + subscribe to scale tier, this includes scale tier tokens. + input_audio_tokens: + type: integer + description: The aggregated number of audio input tokens used, including cached + tokens. + output_audio_tokens: + type: integer + description: The aggregated number of audio output tokens used. + num_model_requests: + type: integer + description: The count of requests made to the model. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + batch: + type: boolean + nullable: true + description: When `group_by=batch`, this field tells whether the grouped usage + result is batch or not. + required: + - object + - input_tokens + - output_tokens + - num_model_requests + x-oaiMeta: + name: Completions usage object + example: | + { + "object": "organization.usage.completions.result", + "input_tokens": 5000, + "output_tokens": 1000, + "input_cached_tokens": 4000, + "input_audio_tokens": 300, + "output_audio_tokens": 200, + "num_model_requests": 5, + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "gpt-4o-mini-2024-07-18", + "batch": false + } + UsageEmbeddingsResult: + type: object + description: The aggregated embeddings usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.embeddings.result + x-stainless-const: true + input_tokens: + type: integer + description: The aggregated number of input tokens used. + num_model_requests: + type: integer + description: The count of requests made to the model. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + required: + - object + - input_tokens + - num_model_requests + x-oaiMeta: + name: Embeddings usage object + example: | + { + "object": "organization.usage.embeddings.result", + "input_tokens": 20, + "num_model_requests": 2, + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "text-embedding-ada-002-v2" + } + UsageImagesResult: + type: object + description: The aggregated images usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.images.result + x-stainless-const: true + images: + type: integer + description: The number of images processed. + num_model_requests: + type: integer + description: The count of requests made to the model. + source: + type: string + nullable: true + description: When `group_by=source`, this field provides the source of the + grouped usage result, possible values are `image.generation`, + `image.edit`, `image.variation`. + size: + type: string + nullable: true + description: When `group_by=size`, this field provides the image size of the + grouped usage result. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + required: + - object + - images + - num_model_requests + x-oaiMeta: + name: Images usage object + example: | + { + "object": "organization.usage.images.result", + "images": 2, + "num_model_requests": 2, + "size": "1024x1024", + "source": "image.generation", + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "dall-e-3" + } + UsageModerationsResult: + type: object + description: The aggregated moderations usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.moderations.result + x-stainless-const: true + input_tokens: + type: integer + description: The aggregated number of input tokens used. + num_model_requests: + type: integer + description: The count of requests made to the model. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + user_id: + type: string + nullable: true + description: When `group_by=user_id`, this field provides the user ID of the + grouped usage result. + api_key_id: + type: string + nullable: true + description: When `group_by=api_key_id`, this field provides the API key ID of + the grouped usage result. + model: + type: string + nullable: true + description: When `group_by=model`, this field provides the model name of the + grouped usage result. + required: + - object + - input_tokens + - num_model_requests + x-oaiMeta: + name: Moderations usage object + example: | + { + "object": "organization.usage.moderations.result", + "input_tokens": 20, + "num_model_requests": 2, + "project_id": "proj_abc", + "user_id": "user-abc", + "api_key_id": "key_abc", + "model": "text-moderation" + } + UsageResponse: + type: object + properties: + object: + type: string + enum: + - page + x-stainless-const: true + data: + type: array + items: + $ref: "#/components/schemas/UsageTimeBucket" + has_more: + type: boolean + next_page: + type: string + required: + - object + - data + - has_more + - next_page + UsageTimeBucket: + type: object + properties: + object: + type: string + enum: + - bucket + x-stainless-const: true + start_time: + type: integer + end_time: + type: integer + result: + type: array + items: + oneOf: + - $ref: "#/components/schemas/UsageCompletionsResult" + - $ref: "#/components/schemas/UsageEmbeddingsResult" + - $ref: "#/components/schemas/UsageModerationsResult" + - $ref: "#/components/schemas/UsageImagesResult" + - $ref: "#/components/schemas/UsageAudioSpeechesResult" + - $ref: "#/components/schemas/UsageAudioTranscriptionsResult" + - $ref: "#/components/schemas/UsageVectorStoresResult" + - $ref: "#/components/schemas/UsageCodeInterpreterSessionsResult" + - $ref: "#/components/schemas/CostsResult" + required: + - object + - start_time + - end_time + - result + UsageVectorStoresResult: + type: object + description: The aggregated vector stores usage details of the specific time bucket. + properties: + object: + type: string + enum: + - organization.usage.vector_stores.result + x-stainless-const: true + usage_bytes: + type: integer + description: The vector stores usage in bytes. + project_id: + type: string + nullable: true + description: When `group_by=project_id`, this field provides the project ID of + the grouped usage result. + required: + - object + - usage_bytes + x-oaiMeta: + name: Vector stores usage object + example: | + { + "object": "organization.usage.vector_stores.result", + "usage_bytes": 1024, + "project_id": "proj_abc" + } + User: + type: object + description: Represents an individual `user` within an organization. + properties: + object: + type: string + enum: + - organization.user + description: The object type, which is always `organization.user` + x-stainless-const: true + id: + type: string + description: The identifier, which can be referenced in API endpoints + name: + type: string + description: The name of the user + email: + type: string + description: The email address of the user + role: + type: string + enum: + - owner + - reader + description: "`owner` or `reader`" + added_at: + type: integer + description: The Unix timestamp (in seconds) of when the user was added. + required: + - object + - id + - name + - email + - role + - added_at + x-oaiMeta: + name: The user object + example: | + { + "object": "organization.user", + "id": "user_abc", + "name": "First Last", + "email": "user@example.com", + "role": "owner", + "added_at": 1711471533 + } + UserDeleteResponse: + type: object + properties: + object: + type: string + enum: + - organization.user.deleted + x-stainless-const: true + id: + type: string + deleted: + type: boolean + required: + - object + - id + - deleted + UserListResponse: + type: object + properties: + object: + type: string + enum: + - list + x-stainless-const: true + data: + type: array + items: + $ref: "#/components/schemas/User" + first_id: + type: string + last_id: + type: string + has_more: + type: boolean + required: + - object + - data + - first_id + - last_id + - has_more + UserRoleUpdateRequest: + type: object + properties: + role: + type: string + enum: + - owner + - reader + description: "`owner` or `reader`" + required: + - role + VadConfig: + type: object + additionalProperties: false + required: + - type + properties: + type: + type: string + enum: + - server_vad + description: Must be set to `server_vad` to enable manual chunking using server + side VAD. + prefix_padding_ms: + type: integer + default: 300 + description: | + Amount of audio to include before the VAD detected speech (in + milliseconds). + silence_duration_ms: + type: integer + default: 200 + description: | + Duration of silence to detect speech stop (in milliseconds). + With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + threshold: + type: number + default: 0.5 + description: > + Sensitivity threshold (0.0 to 1.0) for voice activity detection. A + + higher threshold will require louder audio to activate the model, + and + + thus might perform better in noisy environments. + ValidateGraderRequest: + type: object + title: ValidateGraderRequest + properties: + grader: + type: object + description: The grader used for the fine-tuning job. + oneOf: + - $ref: "#/components/schemas/GraderStringCheck" + - $ref: "#/components/schemas/GraderTextSimilarity" + - $ref: "#/components/schemas/GraderPython" + - $ref: "#/components/schemas/GraderScoreModel" + - $ref: "#/components/schemas/GraderMulti" + required: + - grader + ValidateGraderResponse: + type: object + title: ValidateGraderResponse + properties: + grader: + type: object + description: The grader used for the fine-tuning job. + oneOf: + - $ref: "#/components/schemas/GraderStringCheck" + - $ref: "#/components/schemas/GraderTextSimilarity" + - $ref: "#/components/schemas/GraderPython" + - $ref: "#/components/schemas/GraderScoreModel" + - $ref: "#/components/schemas/GraderMulti" + VectorStoreExpirationAfter: + type: object + title: Vector store expiration policy + description: The expiration policy for a vector store. + properties: + anchor: + description: "Anchor timestamp after which the expiration policy applies. + Supported anchors: `last_active_at`." + type: string + enum: + - last_active_at + x-stainless-const: true + days: + description: The number of days after the anchor time that the vector store will + expire. + type: integer + minimum: 1 + maximum: 365 + required: + - anchor + - days + VectorStoreFileAttributes: + type: object + description: > + Set of 16 key-value pairs that can be attached to an object. This can + be + + useful for storing additional information about the object in a + structured + + format, and querying for objects via API or the dashboard. Keys are + strings + + with a maximum length of 64 characters. Values are strings with a + maximum + + length of 512 characters, booleans, or numbers. + maxProperties: 16 + propertyNames: + type: string + maxLength: 64 + additionalProperties: + oneOf: + - type: string + maxLength: 512 + - type: number + - type: boolean + x-oaiTypeLabel: map + nullable: true + VectorStoreFileBatchObject: + type: object + title: Vector store file batch + description: A batch of files attached to a vector store. + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `vector_store.file_batch`. + type: string + enum: + - vector_store.files_batch + x-stainless-const: true + created_at: + description: The Unix timestamp (in seconds) for when the vector store files + batch was created. + type: integer + vector_store_id: + description: The ID of the [vector + store](/docs/api-reference/vector-stores/object) that the + [File](/docs/api-reference/files) is attached to. + type: string + status: + description: The status of the vector store files batch, which can be either + `in_progress`, `completed`, `cancelled` or `failed`. + type: string + enum: + - in_progress + - completed + - cancelled + - failed + file_counts: + type: object + properties: + in_progress: + description: The number of files that are currently being processed. + type: integer + completed: + description: The number of files that have been processed. + type: integer + failed: + description: The number of files that have failed to process. + type: integer + cancelled: + description: The number of files that where cancelled. + type: integer + total: + description: The total number of files. + type: integer + required: + - in_progress + - completed + - cancelled + - failed + - total + required: + - id + - object + - created_at + - vector_store_id + - status + - file_counts + x-oaiMeta: + name: The vector store files batch object + beta: true + example: | + { + "id": "vsfb_123", + "object": "vector_store.files_batch", + "created_at": 1698107661, + "vector_store_id": "vs_abc123", + "status": "completed", + "file_counts": { + "in_progress": 0, + "completed": 100, + "failed": 0, + "cancelled": 0, + "total": 100 + } + } + VectorStoreFileContentResponse: + type: object + description: Represents the parsed content of a vector store file. + properties: + object: + type: string + enum: + - vector_store.file_content.page + description: The object type, which is always `vector_store.file_content.page` + x-stainless-const: true + data: + type: array + description: Parsed content of the file. + items: + type: object + properties: + type: + type: string + description: The content type (currently only `"text"`) + text: + type: string + description: The text content + has_more: + type: boolean + description: Indicates if there are more content pages to fetch. + next_page: + type: string + description: The token for the next page, if any. + nullable: true + required: + - object + - data + - has_more + - next_page + VectorStoreFileObject: + type: object + title: Vector store files + description: A list of files attached to a vector store. + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `vector_store.file`. + type: string + enum: + - vector_store.file + x-stainless-const: true + usage_bytes: + description: The total vector store usage in bytes. Note that this may be + different from the original file size. + type: integer + created_at: + description: The Unix timestamp (in seconds) for when the vector store file was + created. + type: integer + vector_store_id: + description: The ID of the [vector + store](/docs/api-reference/vector-stores/object) that the + [File](/docs/api-reference/files) is attached to. + type: string + status: + description: The status of the vector store file, which can be either + `in_progress`, `completed`, `cancelled`, or `failed`. The status + `completed` indicates that the vector store file is ready for use. + type: string + enum: + - in_progress + - completed + - cancelled + - failed + last_error: + type: object + description: The last error associated with this vector store file. Will be + `null` if there are no errors. + nullable: true + properties: + code: + type: string + description: One of `server_error` or `rate_limit_exceeded`. + enum: + - server_error + - unsupported_file + - invalid_file + message: + type: string + description: A human-readable description of the error. + required: + - code + - message + chunking_strategy: + type: object + description: The strategy used to chunk the file. + oneOf: + - $ref: "#/components/schemas/StaticChunkingStrategyResponseParam" + - $ref: "#/components/schemas/OtherChunkingStrategyResponseParam" + attributes: + $ref: "#/components/schemas/VectorStoreFileAttributes" + required: + - id + - object + - usage_bytes + - created_at + - vector_store_id + - status + - last_error + x-oaiMeta: + name: The vector store file object + beta: true + example: | + { + "id": "file-abc123", + "object": "vector_store.file", + "usage_bytes": 1234, + "created_at": 1698107661, + "vector_store_id": "vs_abc123", + "status": "completed", + "last_error": null, + "chunking_strategy": { + "type": "static", + "static": { + "max_chunk_size_tokens": 800, + "chunk_overlap_tokens": 400 + } + } + } + VectorStoreObject: + type: object + title: Vector store + description: A vector store is a collection of processed files can be used by + the `file_search` tool. + properties: + id: + description: The identifier, which can be referenced in API endpoints. + type: string + object: + description: The object type, which is always `vector_store`. + type: string + enum: + - vector_store + x-stainless-const: true + created_at: + description: The Unix timestamp (in seconds) for when the vector store was + created. + type: integer + name: + description: The name of the vector store. + type: string + usage_bytes: + description: The total number of bytes used by the files in the vector store. + type: integer + file_counts: + type: object + properties: + in_progress: + description: The number of files that are currently being processed. + type: integer + completed: + description: The number of files that have been successfully processed. + type: integer + failed: + description: The number of files that have failed to process. + type: integer + cancelled: + description: The number of files that were cancelled. + type: integer + total: + description: The total number of files. + type: integer + required: + - in_progress + - completed + - failed + - cancelled + - total + status: + description: The status of the vector store, which can be either `expired`, + `in_progress`, or `completed`. A status of `completed` indicates + that the vector store is ready for use. + type: string + enum: + - expired + - in_progress + - completed + expires_after: + $ref: "#/components/schemas/VectorStoreExpirationAfter" + expires_at: + description: The Unix timestamp (in seconds) for when the vector store will + expire. + type: integer + nullable: true + last_active_at: + description: The Unix timestamp (in seconds) for when the vector store was last + active. + type: integer + nullable: true + metadata: + $ref: "#/components/schemas/Metadata" + required: + - id + - object + - usage_bytes + - created_at + - status + - last_active_at + - name + - file_counts + - metadata + x-oaiMeta: + name: The vector store object + example: | + { + "id": "vs_123", + "object": "vector_store", + "created_at": 1698107661, + "usage_bytes": 123456, + "last_active_at": 1698107661, + "name": "my_vector_store", + "status": "completed", + "file_counts": { + "in_progress": 0, + "completed": 100, + "cancelled": 0, + "failed": 0, + "total": 100 + }, + "last_used_at": 1698107661 + } + VectorStoreSearchRequest: + type: object + additionalProperties: false + properties: + query: + description: A query string for a search + oneOf: + - type: string + - type: array + items: + type: string + description: A list of queries to search for. + minItems: 1 + rewrite_query: + description: Whether to rewrite the natural language query for vector search. + type: boolean + default: false + max_num_results: + description: The maximum number of results to return. This number should be + between 1 and 50 inclusive. + type: integer + default: 10 + minimum: 1 + maximum: 50 + filters: + description: A filter to apply based on file attributes. + oneOf: + - $ref: "#/components/schemas/ComparisonFilter" + - $ref: "#/components/schemas/CompoundFilter" + ranking_options: + description: Ranking options for search. + type: object + additionalProperties: false + properties: + ranker: + type: string + enum: + - auto + - default-2024-11-15 + default: auto + score_threshold: + type: number + minimum: 0 + maximum: 1 + default: 0 + required: + - query + x-oaiMeta: + name: Vector store search request + VectorStoreSearchResultContentObject: + type: object + additionalProperties: false + properties: + type: + description: The type of content. + type: string + enum: + - text + text: + description: The text content returned from search. + type: string + required: + - type + - text + x-oaiMeta: + name: Vector store search result content object + VectorStoreSearchResultItem: + type: object + additionalProperties: false + properties: + file_id: + type: string + description: The ID of the vector store file. + filename: + type: string + description: The name of the vector store file. + score: + type: number + description: The similarity score for the result. + minimum: 0 + maximum: 1 + attributes: + $ref: "#/components/schemas/VectorStoreFileAttributes" + content: + type: array + description: Content chunks from the file. + items: + $ref: "#/components/schemas/VectorStoreSearchResultContentObject" + required: + - file_id + - filename + - score + - attributes + - content + x-oaiMeta: + name: Vector store search result item + VectorStoreSearchResultsPage: + type: object + additionalProperties: false + properties: + object: + type: string + enum: + - vector_store.search_results.page + description: The object type, which is always `vector_store.search_results.page` + x-stainless-const: true + search_query: + type: array + items: + type: string + description: The query used for this search. + minItems: 1 + data: + type: array + description: The list of search result items. + items: + $ref: "#/components/schemas/VectorStoreSearchResultItem" + has_more: + type: boolean + description: Indicates if there are more results to fetch. + next_page: + type: string + description: The token for the next page, if any. + nullable: true + required: + - object + - search_query + - data + - has_more + - next_page + x-oaiMeta: + name: Vector store search results page + VoiceIdsShared: + example: ash + anyOf: + - type: string + - type: string + enum: + - alloy + - ash + - ballad + - coral + - echo + - fable + - onyx + - nova + - sage + - shimmer + - verse + Wait: + type: object + title: Wait + description: | + A wait action. + properties: + type: + type: string + enum: + - wait + default: wait + description: | + Specifies the event type. For a wait action, this property is + always set to `wait`. + x-stainless-const: true + required: + - type + WebSearchContextSize: + type: string + description: > + High level guidance for the amount of context window space to use for + the + + search. One of `low`, `medium`, or `high`. `medium` is the default. + enum: + - low + - medium + - high + default: medium + WebSearchLocation: + type: object + title: Web search location + description: Approximate location parameters for the search. + properties: + country: + type: string + description: > + The two-letter + + [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the + user, + + e.g. `US`. + region: + type: string + description: | + Free text input for the region of the user, e.g. `California`. + city: + type: string + description: | + Free text input for the city of the user, e.g. `San Francisco`. + timezone: + type: string + description: > + The [IANA + timezone](https://timeapi.io/documentation/iana-timezones) + + of the user, e.g. `America/Los_Angeles`. + WebSearchToolCall: + type: object + title: Web search tool call + description: | + The results of a web search tool call. See the + [web search guide](/docs/guides/tools-web-search) for more information. + properties: + id: + type: string + description: | + The unique ID of the web search tool call. + type: + type: string + enum: + - web_search_call + description: | + The type of the web search tool call. Always `web_search_call`. + x-stainless-const: true + status: + type: string + description: | + The status of the web search tool call. + enum: + - in_progress + - searching + - completed + - failed + required: + - id + - type + - status + InputTextContent: + properties: + type: + type: string + enum: + - input_text + description: The type of the input item. Always `input_text`. + default: input_text + x-stainless-const: true + text: + type: string + description: The text input to the model. + type: object + required: + - type + - text + title: Input text + description: A text input to the model. + InputImageContent: + properties: + type: + type: string + enum: + - input_image + description: The type of the input item. Always `input_image`. + default: input_image + x-stainless-const: true + image_url: + type: string + description: The URL of the image to be sent to the model. A fully qualified URL + or base64 encoded image in a data URL. + nullable: true + file_id: + type: string + description: The ID of the file to be sent to the model. + nullable: true + detail: + type: string + enum: + - low + - high + - auto + description: The detail level of the image to be sent to the model. One of + `high`, `low`, or `auto`. Defaults to `auto`. + type: object + required: + - type + - detail + title: Input image + description: An image input to the model. Learn about [image + inputs](/docs/guides/vision). + InputFileContent: + properties: + type: + type: string + enum: + - input_file + description: The type of the input item. Always `input_file`. + default: input_file + x-stainless-const: true + file_id: + type: string + description: The ID of the file to be sent to the model. + nullable: true + filename: + type: string + description: The name of the file to be sent to the model. + file_data: + type: string + description: | + The content of the file to be sent to the model. + type: object + required: &a1 + - type + title: Input file + description: A file input to the model. + FunctionTool: + properties: + type: + type: string + enum: + - function + description: The type of the function tool. Always `function`. + default: function + x-stainless-const: true + name: + type: string + description: The name of the function to call. + description: + type: string + description: A description of the function. Used by the model to determine + whether or not to call the function. + nullable: true + parameters: + additionalProperties: {} + type: object + description: A JSON schema object describing the parameters of the function. + nullable: true + strict: + type: boolean + description: Whether to enforce strict parameter validation. Default `true`. + nullable: true + type: object + required: + - type + - name + - strict + - parameters + title: Function + description: Defines a function in your own code the model can choose to call. + Learn more about [function + calling](https://platform.openai.com/docs/guides/function-calling). + RankingOptions: + properties: + ranker: + type: string + enum: + - auto + - default-2024-11-15 + description: The ranker to use for the file search. + score_threshold: + type: number + description: The score threshold for the file search, a number between 0 and 1. + Numbers closer to 1 will attempt to return only the most relevant + results, but may return fewer results. + type: object + required: [] + Filters: + anyOf: + - $ref: "#/components/schemas/ComparisonFilter" + - $ref: "#/components/schemas/CompoundFilter" + FileSearchTool: + properties: + type: + type: string + enum: + - file_search + description: The type of the file search tool. Always `file_search`. + default: file_search + x-stainless-const: true + vector_store_ids: + items: + type: string + type: array + description: The IDs of the vector stores to search. + max_num_results: + type: integer + description: The maximum number of results to return. This number should be + between 1 and 50 inclusive. + ranking_options: + $ref: "#/components/schemas/RankingOptions" + description: Ranking options for search. + filters: + $ref: "#/components/schemas/Filters" + description: A filter to apply. + nullable: true + type: object + required: + - type + - vector_store_ids + title: File search + description: A tool that searches for relevant content from uploaded files. + Learn more about the [file search + tool](https://platform.openai.com/docs/guides/tools-file-search). + ApproximateLocation: + properties: + type: + type: string + enum: + - approximate + description: The type of location approximation. Always `approximate`. + default: approximate + x-stainless-const: true + country: + type: string + description: The two-letter [ISO country + code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, e.g. + `US`. + nullable: true + region: + type: string + description: Free text input for the region of the user, e.g. `California`. + nullable: true + city: + type: string + description: Free text input for the city of the user, e.g. `San Francisco`. + nullable: true + timezone: + type: string + description: The [IANA + timezone](https://timeapi.io/documentation/iana-timezones) of the + user, e.g. `America/Los_Angeles`. + nullable: true + type: object + required: *a1 + WebSearchPreviewTool: + properties: + type: + type: string + enum: + - web_search_preview + - web_search_preview_2025_03_11 + description: The type of the web search tool. One of `web_search_preview` or + `web_search_preview_2025_03_11`. + default: web_search_preview + x-stainless-const: true + user_location: + $ref: "#/components/schemas/ApproximateLocation" + description: The user's location. + nullable: true + search_context_size: + type: string + enum: + - low + - medium + - high + description: High level guidance for the amount of context window space to use + for the search. One of `low`, `medium`, or `high`. `medium` is the + default. + type: object + required: *a1 + title: Web search preview + description: This tool searches the web for relevant results to use in a + response. Learn more about the [web search + tool](https://platform.openai.com/docs/guides/tools-web-search). + ComputerUsePreviewTool: + properties: + type: + type: string + enum: + - computer_use_preview + description: The type of the computer use tool. Always `computer_use_preview`. + default: computer_use_preview + x-stainless-const: true + environment: + type: string + enum: + - windows + - mac + - linux + - ubuntu + - browser + description: The type of computer environment to control. + display_width: + type: integer + description: The width of the computer display. + display_height: + type: integer + description: The height of the computer display. + type: object + required: + - type + - environment + - display_width + - display_height + title: Computer use preview + description: A tool that controls a virtual computer. Learn more about the + [computer + tool](https://platform.openai.com/docs/guides/tools-computer-use). + FileCitationBody: + properties: + type: + type: string + enum: + - file_citation + description: The type of the file citation. Always `file_citation`. + default: file_citation + x-stainless-const: true + file_id: + type: string + description: The ID of the file. + index: + type: integer + description: The index of the file in the list of files. + type: object + required: + - type + - file_id + - index + title: File citation + description: A citation to a file. + UrlCitationBody: + properties: + type: + type: string + enum: + - url_citation + description: The type of the URL citation. Always `url_citation`. + default: url_citation + x-stainless-const: true + url: + type: string + description: The URL of the web resource. + start_index: + type: integer + description: The index of the first character of the URL citation in the message. + end_index: + type: integer + description: The index of the last character of the URL citation in the message. + title: + type: string + description: The title of the web resource. + type: object + required: + - type + - url + - start_index + - end_index + - title + title: URL citation + description: A citation for a web resource used to generate a model response. + ContainerFileCitationBody: + properties: + type: + type: string + enum: + - container_file_citation + description: The type of the container file citation. Always + `container_file_citation`. + default: container_file_citation + x-stainless-const: true + container_id: + type: string + description: The ID of the container file. + file_id: + type: string + description: The ID of the file. + start_index: + type: integer + description: The index of the first character of the container file citation in + the message. + end_index: + type: integer + description: The index of the last character of the container file citation in + the message. + type: object + required: + - type + - container_id + - file_id + - start_index + - end_index + title: Container file citation + description: A citation for a container file used to generate a model response. + Annotation: + oneOf: + - $ref: "#/components/schemas/FileCitationBody" + - $ref: "#/components/schemas/UrlCitationBody" + - $ref: "#/components/schemas/ContainerFileCitationBody" + - $ref: "#/components/schemas/FilePath" + discriminator: + propertyName: type + TopLogProb: + properties: + token: + type: string + logprob: + type: number + bytes: + items: + type: integer + type: array + type: object + required: + - token + - logprob + - bytes + title: Top log probability + description: The top log probability of a token. + LogProb: + properties: + token: + type: string + logprob: + type: number + bytes: + items: + type: integer + type: array + top_logprobs: + items: + $ref: "#/components/schemas/TopLogProb" + type: array + type: object + required: + - token + - logprob + - bytes + - top_logprobs + title: Log probability + description: The log probability of a token. + OutputTextContent: + properties: + type: + type: string + enum: + - output_text + description: The type of the output text. Always `output_text`. + default: output_text + x-stainless-const: true + text: + type: string + description: The text output from the model. + annotations: + items: + $ref: "#/components/schemas/Annotation" + type: array + description: The annotations of the text output. + logprobs: + items: + $ref: "#/components/schemas/LogProb" + type: array + type: object + required: + - type + - text + - annotations + title: Output text + description: A text output from the model. + RefusalContent: + properties: + type: + type: string + enum: + - refusal + description: The type of the refusal. Always `refusal`. + default: refusal + x-stainless-const: true + refusal: + type: string + description: The refusal explanationfrom the model. + type: object + required: + - type + - refusal + title: Refusal + description: A refusal from the model. + ComputerCallSafetyCheckParam: + properties: + id: + type: string + description: The ID of the pending safety check. + code: + type: string + description: The type of the pending safety check. + nullable: true + message: + type: string + description: Details about the pending safety check. + nullable: true + type: object + required: + - id + description: A pending safety check for the computer call. + ComputerCallOutputItemParam: + properties: + id: + type: string + description: The ID of the computer tool call output. + nullable: true + call_id: + type: string + maxLength: 64 + minLength: 1 + description: The ID of the computer tool call that produced the output. + type: + type: string + enum: + - computer_call_output + description: The type of the computer tool call output. Always + `computer_call_output`. + default: computer_call_output + x-stainless-const: true + output: + $ref: "#/components/schemas/ComputerScreenshotImage" + acknowledged_safety_checks: + items: + $ref: "#/components/schemas/ComputerCallSafetyCheckParam" + type: array + description: The safety checks reported by the API that have been acknowledged + by the developer. + nullable: true + status: + type: string + enum: + - in_progress + - completed + - incomplete + description: The status of the message input. One of `in_progress`, `completed`, + or `incomplete`. Populated when input items are returned via API. + nullable: true + type: object + required: + - call_id + - type + - output + title: Computer tool call output + description: The output of a computer tool call. + FunctionCallOutputItemParam: + properties: + id: + type: string + description: The unique ID of the function tool call output. Populated when this + item is returned via API. + nullable: true + call_id: + type: string + maxLength: 64 + minLength: 1 + description: The unique ID of the function tool call generated by the model. + type: + type: string + enum: + - function_call_output + description: The type of the function tool call output. Always + `function_call_output`. + default: function_call_output + x-stainless-const: true + output: + type: string + maxLength: 10485760 + description: A JSON string of the output of the function tool call. + status: + type: string + enum: + - in_progress + - completed + - incomplete + description: The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + nullable: true + type: object + required: + - call_id + - type + - output + title: Function tool call output + description: The output of a function tool call. + ItemReferenceParam: + properties: + type: + type: string + enum: + - item_reference + description: The type of item to reference. Always `item_reference`. + default: item_reference + x-stainless-const: true + nullable: true + id: + type: string + description: The ID of the item to reference. + type: object + required: + - id + title: Item reference + description: An internal identifier for an item to reference. + securitySchemes: + ApiKeyAuth: + type: http + scheme: bearer +x-oaiMeta: + navigationGroups: + - id: responses + title: Responses + - id: chat + title: Chat Completions + - id: realtime + title: Realtime + beta: true + - id: endpoints + title: Platform APIs + - id: vector_stores + title: Vector stores + - id: containers + title: Containers + - id: assistants + title: Assistants + beta: true + - id: administration + title: Administration + - id: legacy + title: Legacy + groups: + - id: responses + title: Responses + description: > + OpenAI's most advanced interface for generating model responses. + Supports + + text and image inputs, and text outputs. Create stateful interactions + + with the model, using the output of previous responses as input. Extend + + the model's capabilities with built-in tools for file search, web + search, + + computer use, and more. Allow the model access to external systems and + data + + using function calling. + + + Related guides: + + - [Quickstart](/docs/quickstart?api-mode=responses) + + - [Text inputs and outputs](/docs/guides/text?api-mode=responses) + + - [Image inputs](/docs/guides/images?api-mode=responses) + + - [Structured + Outputs](/docs/guides/structured-outputs?api-mode=responses) + + - [Function calling](/docs/guides/function-calling?api-mode=responses) + + - [Conversation + state](/docs/guides/conversation-state?api-mode=responses) + + - [Extend the models with tools](/docs/guides/tools?api-mode=responses) + navigationGroup: responses + sections: + - type: endpoint + key: createResponse + path: create + - type: endpoint + key: getResponse + path: get + - type: endpoint + key: deleteResponse + path: delete + - type: endpoint + key: cancelResponse + path: cancel + - type: endpoint + key: listInputItems + path: input-items + - type: object + key: Response + path: object + - type: object + key: ResponseItemList + path: list + - id: responses-streaming + title: Streaming + description: > + When you [create a Response](/docs/api-reference/responses/create) with + + `stream` set to `true`, the server will emit server-sent events to the + + client as the Response is generated. This section contains the events + that + + are emitted by the server. + + + [Learn more about streaming + responses](/docs/guides/streaming-responses?api-mode=responses). + navigationGroup: responses + sections: + - type: object + key: ResponseCreatedEvent + path: + - type: object + key: ResponseInProgressEvent + path: + - type: object + key: ResponseCompletedEvent + path: + - type: object + key: ResponseFailedEvent + path: + - type: object + key: ResponseIncompleteEvent + path: + - type: object + key: ResponseOutputItemAddedEvent + path: + - type: object + key: ResponseOutputItemDoneEvent + path: + - type: object + key: ResponseContentPartAddedEvent + path: + - type: object + key: ResponseContentPartDoneEvent + path: + - type: object + key: ResponseTextDeltaEvent + path: + - type: object + key: ResponseTextDoneEvent + path: + - type: object + key: ResponseRefusalDeltaEvent + path: + - type: object + key: ResponseRefusalDoneEvent + path: + - type: object + key: ResponseFunctionCallArgumentsDeltaEvent + path: + - type: object + key: ResponseFunctionCallArgumentsDoneEvent + path: + - type: object + key: ResponseFileSearchCallInProgressEvent + path: + - type: object + key: ResponseFileSearchCallSearchingEvent + path: + - type: object + key: ResponseFileSearchCallCompletedEvent + path: + - type: object + key: ResponseWebSearchCallInProgressEvent + path: + - type: object + key: ResponseWebSearchCallSearchingEvent + path: + - type: object + key: ResponseWebSearchCallCompletedEvent + path: + - type: object + key: ResponseReasoningSummaryPartAddedEvent + path: + - type: object + key: ResponseReasoningSummaryPartDoneEvent + path: + - type: object + key: ResponseReasoningSummaryTextDeltaEvent + path: + - type: object + key: ResponseReasoningSummaryTextDoneEvent + path: + - type: object + key: ResponseImageGenCallCompletedEvent + path: + - type: object + key: ResponseImageGenCallGeneratingEvent + path: + - type: object + key: ResponseImageGenCallInProgressEvent + path: + - type: object + key: ResponseImageGenCallPartialImageEvent + path: + - type: object + key: ResponseMCPCallArgumentsDeltaEvent + path: + - type: object + key: ResponseMCPCallArgumentsDoneEvent + path: + - type: object + key: ResponseMCPCallCompletedEvent + path: + - type: object + key: ResponseMCPCallFailedEvent + path: + - type: object + key: ResponseMCPCallInProgressEvent + path: + - type: object + key: ResponseMCPListToolsCompletedEvent + path: + - type: object + key: ResponseMCPListToolsFailedEvent + path: + - type: object + key: ResponseMCPListToolsInProgressEvent + path: + - type: object + key: ResponseOutputTextAnnotationAddedEvent + path: + - type: object + key: ResponseQueuedEvent + path: + - type: object + key: ResponseReasoningDeltaEvent + path: + - type: object + key: ResponseReasoningDoneEvent + path: + - type: object + key: ResponseReasoningSummaryDeltaEvent + path: + - type: object + key: ResponseReasoningSummaryDoneEvent + path: + - type: object + key: ResponseErrorEvent + path: + - id: chat + title: Chat Completions + description: | + The Chat Completions API endpoint will generate a model response from a + list of messages comprising a conversation. + + Related guides: + - [Quickstart](/docs/quickstart?api-mode=chat) + - [Text inputs and outputs](/docs/guides/text?api-mode=chat) + - [Image inputs](/docs/guides/images?api-mode=chat) + - [Audio inputs and outputs](/docs/guides/audio?api-mode=chat) + - [Structured Outputs](/docs/guides/structured-outputs?api-mode=chat) + - [Function calling](/docs/guides/function-calling?api-mode=chat) + - [Conversation state](/docs/guides/conversation-state?api-mode=chat) + + **Starting a new project?** We recommend trying [Responses](/docs/api-reference/responses) + to take advantage of the latest OpenAI platform features. Compare + [Chat Completions with Responses](/docs/guides/responses-vs-chat-completions?api-mode=responses). + navigationGroup: chat + sections: + - type: endpoint + key: createChatCompletion + path: create + - type: endpoint + key: getChatCompletion + path: get + - type: endpoint + key: getChatCompletionMessages + path: getMessages + - type: endpoint + key: listChatCompletions + path: list + - type: endpoint + key: updateChatCompletion + path: update + - type: endpoint + key: deleteChatCompletion + path: delete + - type: object + key: CreateChatCompletionResponse + path: object + - type: object + key: ChatCompletionList + path: list-object + - type: object + key: ChatCompletionMessageList + path: message-list + - id: chat-streaming + title: Streaming + description: | + Stream Chat Completions in real time. Receive chunks of completions + returned from the model using server-sent events. + [Learn more](/docs/guides/streaming-responses?api-mode=chat). + navigationGroup: chat + sections: + - type: object + key: CreateChatCompletionStreamResponse + path: streaming + - id: realtime + title: Realtime + beta: true + description: | + Communicate with a GPT-4o class model in real time using WebRTC or + WebSockets. Supports text and audio inputs and ouputs, along with audio + transcriptions. + [Learn more about the Realtime API](/docs/guides/realtime). + navigationGroup: realtime + - id: realtime-sessions + title: Session tokens + description: > + REST API endpoint to generate ephemeral session tokens for use in + client-side + + applications. + navigationGroup: realtime + sections: + - type: endpoint + key: create-realtime-session + path: create + - type: endpoint + key: create-realtime-transcription-session + path: create-transcription + - type: object + key: RealtimeSessionCreateResponse + path: session_object + - type: object + key: RealtimeTranscriptionSessionCreateResponse + path: transcription_session_object + - id: realtime-client-events + title: Client events + description: > + These are events that the OpenAI Realtime WebSocket server will accept + from the client. + navigationGroup: realtime + sections: + - type: object + key: RealtimeClientEventSessionUpdate + path: + - type: object + key: RealtimeClientEventInputAudioBufferAppend + path: + - type: object + key: RealtimeClientEventInputAudioBufferCommit + path: + - type: object + key: RealtimeClientEventInputAudioBufferClear + path: + - type: object + key: RealtimeClientEventConversationItemCreate + path: + - type: object + key: RealtimeClientEventConversationItemRetrieve + path: + - type: object + key: RealtimeClientEventConversationItemTruncate + path: + - type: object + key: RealtimeClientEventConversationItemDelete + path: + - type: object + key: RealtimeClientEventResponseCreate + path: + - type: object + key: RealtimeClientEventResponseCancel + path: + - type: object + key: RealtimeClientEventTranscriptionSessionUpdate + path: + - type: object + key: RealtimeClientEventOutputAudioBufferClear + path: + - id: realtime-server-events + title: Server events + description: > + These are events emitted from the OpenAI Realtime WebSocket server to + the client. + navigationGroup: realtime + sections: + - type: object + key: RealtimeServerEventError + path: + - type: object + key: RealtimeServerEventSessionCreated + path: + - type: object + key: RealtimeServerEventSessionUpdated + path: + - type: object + key: RealtimeServerEventConversationCreated + path: + - type: object + key: RealtimeServerEventConversationItemCreated + path: + - type: object + key: RealtimeServerEventConversationItemRetrieved + path: + - type: object + key: RealtimeServerEventConversationItemInputAudioTranscriptionCompleted + path: + - type: object + key: RealtimeServerEventConversationItemInputAudioTranscriptionDelta + path: + - type: object + key: RealtimeServerEventConversationItemInputAudioTranscriptionFailed + path: + - type: object + key: RealtimeServerEventConversationItemTruncated + path: + - type: object + key: RealtimeServerEventConversationItemDeleted + path: + - type: object + key: RealtimeServerEventInputAudioBufferCommitted + path: + - type: object + key: RealtimeServerEventInputAudioBufferCleared + path: + - type: object + key: RealtimeServerEventInputAudioBufferSpeechStarted + path: + - type: object + key: RealtimeServerEventInputAudioBufferSpeechStopped + path: + - type: object + key: RealtimeServerEventResponseCreated + path: + - type: object + key: RealtimeServerEventResponseDone + path: + - type: object + key: RealtimeServerEventResponseOutputItemAdded + path: + - type: object + key: RealtimeServerEventResponseOutputItemDone + path: + - type: object + key: RealtimeServerEventResponseContentPartAdded + path: + - type: object + key: RealtimeServerEventResponseContentPartDone + path: + - type: object + key: RealtimeServerEventResponseTextDelta + path: + - type: object + key: RealtimeServerEventResponseTextDone + path: + - type: object + key: RealtimeServerEventResponseAudioTranscriptDelta + path: + - type: object + key: RealtimeServerEventResponseAudioTranscriptDone + path: + - type: object + key: RealtimeServerEventResponseAudioDelta + path: + - type: object + key: RealtimeServerEventResponseAudioDone + path: + - type: object + key: RealtimeServerEventResponseFunctionCallArgumentsDelta + path: + - type: object + key: RealtimeServerEventResponseFunctionCallArgumentsDone + path: + - type: object + key: RealtimeServerEventTranscriptionSessionUpdated + path: + - type: object + key: RealtimeServerEventRateLimitsUpdated + path: + - type: object + key: RealtimeServerEventOutputAudioBufferStarted + path: + - type: object + key: RealtimeServerEventOutputAudioBufferStopped + path: + - type: object + key: RealtimeServerEventOutputAudioBufferCleared + path: + - id: audio + title: Audio + description: | + Learn how to turn audio into text or text into audio. + + Related guide: [Speech to text](/docs/guides/speech-to-text) + navigationGroup: endpoints + sections: + - type: endpoint + key: createSpeech + path: createSpeech + - type: endpoint + key: createTranscription + path: createTranscription + - type: endpoint + key: createTranslation + path: createTranslation + - type: object + key: CreateTranscriptionResponseJson + path: json-object + - type: object + key: CreateTranscriptionResponseVerboseJson + path: verbose-json-object + - type: object + key: TranscriptTextDeltaEvent + path: transcript-text-delta-event + - type: object + key: TranscriptTextDoneEvent + path: transcript-text-done-event + - id: images + title: Images + description: > + Given a prompt and/or an input image, the model will generate a new + image. + + Related guide: [Image generation](/docs/guides/images) + navigationGroup: endpoints + sections: + - type: endpoint + key: createImage + path: create + - type: endpoint + key: createImageEdit + path: createEdit + - type: endpoint + key: createImageVariation + path: createVariation + - type: object + key: ImagesResponse + path: object + - id: embeddings + title: Embeddings + description: > + Get a vector representation of a given input that can be easily consumed + by machine learning models and algorithms. + + Related guide: [Embeddings](/docs/guides/embeddings) + navigationGroup: endpoints + sections: + - type: endpoint + key: createEmbedding + path: create + - type: object + key: Embedding + path: object + - id: evals + title: Evals + description: | + Create, manage, and run evals in the OpenAI platform. + Related guide: [Evals](/docs/guides/evals) + navigationGroup: endpoints + sections: + - type: endpoint + key: createEval + path: create + - type: endpoint + key: getEval + path: get + - type: endpoint + key: updateEval + path: update + - type: endpoint + key: deleteEval + path: delete + - type: endpoint + key: listEvals + path: list + - type: endpoint + key: getEvalRuns + path: getRuns + - type: endpoint + key: getEvalRun + path: getRun + - type: endpoint + key: createEvalRun + path: createRun + - type: endpoint + key: cancelEvalRun + path: cancelRun + - type: endpoint + key: deleteEvalRun + path: deleteRun + - type: endpoint + key: getEvalRunOutputItem + path: getRunOutputItem + - type: endpoint + key: getEvalRunOutputItems + path: getRunOutputItems + - type: object + key: Eval + path: object + - type: object + key: EvalRun + path: run-object + - type: object + key: EvalRunOutputItem + path: run-output-item-object + - id: fine-tuning + title: Fine-tuning + description: > + Manage fine-tuning jobs to tailor a model to your specific training + data. + + Related guide: [Fine-tune models](/docs/guides/fine-tuning) + navigationGroup: endpoints + sections: + - type: endpoint + key: createFineTuningJob + path: create + - type: endpoint + key: listPaginatedFineTuningJobs + path: list + - type: endpoint + key: listFineTuningEvents + path: list-events + - type: endpoint + key: listFineTuningJobCheckpoints + path: list-checkpoints + - type: endpoint + key: listFineTuningCheckpointPermissions + path: list-permissions + - type: endpoint + key: createFineTuningCheckpointPermission + path: create-permission + - type: endpoint + key: deleteFineTuningCheckpointPermission + path: delete-permission + - type: endpoint + key: retrieveFineTuningJob + path: retrieve + - type: endpoint + key: cancelFineTuningJob + path: cancel + - type: endpoint + key: resumeFineTuningJob + path: resume + - type: endpoint + key: pauseFineTuningJob + path: pause + - type: object + key: FineTuneChatRequestInput + path: chat-input + - type: object + key: FineTunePreferenceRequestInput + path: preference-input + - type: object + key: FineTuneReinforcementRequestInput + path: reinforcement-input + - type: object + key: FineTuningJob + path: object + - type: object + key: FineTuningJobEvent + path: event-object + - type: object + key: FineTuningJobCheckpoint + path: checkpoint-object + - type: object + key: FineTuningCheckpointPermission + path: permission-object + - id: graders + title: Graders + description: | + Manage and run graders in the OpenAI platform. + Related guide: [Graders](/docs/guides/graders) + navigationGroup: endpoints + sections: + - type: object + key: GraderStringCheck + path: string-check + - type: object + key: GraderTextSimilarity + path: text-similarity + - type: object + key: GraderScoreModel + path: score-model + - type: object + key: GraderLabelModel + path: label-model + - type: object + key: GraderPython + path: python + - type: object + key: GraderMulti + path: multi + - type: endpoint + key: runGrader + path: run + - type: endpoint + key: validateGrader + path: validate + beta: true + - id: batch + title: Batch + description: > + Create large batches of API requests for asynchronous processing. The + Batch API returns completions within 24 hours for a 50% discount. + + Related guide: [Batch](/docs/guides/batch) + navigationGroup: endpoints + sections: + - type: endpoint + key: createBatch + path: create + - type: endpoint + key: retrieveBatch + path: retrieve + - type: endpoint + key: cancelBatch + path: cancel + - type: endpoint + key: listBatches + path: list + - type: object + key: Batch + path: object + - type: object + key: BatchRequestInput + path: request-input + - type: object + key: BatchRequestOutput + path: request-output + - id: files + title: Files + description: > + Files are used to upload documents that can be used with features like + [Assistants](/docs/api-reference/assistants), + [Fine-tuning](/docs/api-reference/fine-tuning), and [Batch + API](/docs/guides/batch). + navigationGroup: endpoints + sections: + - type: endpoint + key: createFile + path: create + - type: endpoint + key: listFiles + path: list + - type: endpoint + key: retrieveFile + path: retrieve + - type: endpoint + key: deleteFile + path: delete + - type: endpoint + key: downloadFile + path: retrieve-contents + - type: object + key: OpenAIFile + path: object + - id: uploads + title: Uploads + description: | + Allows you to upload large files in multiple parts. + navigationGroup: endpoints + sections: + - type: endpoint + key: createUpload + path: create + - type: endpoint + key: addUploadPart + path: add-part + - type: endpoint + key: completeUpload + path: complete + - type: endpoint + key: cancelUpload + path: cancel + - type: object + key: Upload + path: object + - type: object + key: UploadPart + path: part-object + - id: models + title: Models + description: > + List and describe the various models available in the API. You can refer + to the [Models](/docs/models) documentation to understand what models + are available and the differences between them. + navigationGroup: endpoints + sections: + - type: endpoint + key: listModels + path: list + - type: endpoint + key: retrieveModel + path: retrieve + - type: endpoint + key: deleteModel + path: delete + - type: object + key: Model + path: object + - id: moderations + title: Moderations + description: > + Given text and/or image inputs, classifies if those inputs are + potentially harmful across several categories. + + Related guide: [Moderations](/docs/guides/moderation) + navigationGroup: endpoints + sections: + - type: endpoint + key: createModeration + path: create + - type: object + key: CreateModerationResponse + path: object + - id: vector-stores + title: Vector stores + description: > + Vector stores power semantic search for the Retrieval API and the + `file_search` tool in the Responses and Assistants APIs. + + + Related guide: [File Search](/docs/assistants/tools/file-search) + navigationGroup: vector_stores + sections: + - type: endpoint + key: createVectorStore + path: create + - type: endpoint + key: listVectorStores + path: list + - type: endpoint + key: getVectorStore + path: retrieve + - type: endpoint + key: modifyVectorStore + path: modify + - type: endpoint + key: deleteVectorStore + path: delete + - type: endpoint + key: searchVectorStore + path: search + - type: object + key: VectorStoreObject + path: object + - id: vector-stores-files + title: Vector store files + description: | + Vector store files represent files inside a vector store. + + Related guide: [File Search](/docs/assistants/tools/file-search) + navigationGroup: vector_stores + sections: + - type: endpoint + key: createVectorStoreFile + path: createFile + - type: endpoint + key: listVectorStoreFiles + path: listFiles + - type: endpoint + key: getVectorStoreFile + path: getFile + - type: endpoint + key: retrieveVectorStoreFileContent + path: getContent + - type: endpoint + key: updateVectorStoreFileAttributes + path: updateAttributes + - type: endpoint + key: deleteVectorStoreFile + path: deleteFile + - type: object + key: VectorStoreFileObject + path: file-object + - id: vector-stores-file-batches + title: Vector store file batches + description: > + Vector store file batches represent operations to add multiple files to + a vector store. + + Related guide: [File Search](/docs/assistants/tools/file-search) + navigationGroup: vector_stores + sections: + - type: endpoint + key: createVectorStoreFileBatch + path: createBatch + - type: endpoint + key: getVectorStoreFileBatch + path: getBatch + - type: endpoint + key: cancelVectorStoreFileBatch + path: cancelBatch + - type: endpoint + key: listFilesInVectorStoreBatch + path: listBatchFiles + - type: object + key: VectorStoreFileBatchObject + path: batch-object + - id: containers + title: Containers + description: | + Create and manage containers for use with the Code Interpreter tool. + navigationGroup: containers + sections: + - type: endpoint + key: CreateContainer + path: createContainers + - type: endpoint + key: ListContainers + path: listContainers + - type: endpoint + key: RetrieveContainer + path: retrieveContainer + - type: endpoint + key: DeleteContainer + path: deleteContainer + - type: object + key: ContainerResource + path: object + - id: container-files + title: Container Files + description: > + Create and manage container files for use with the Code Interpreter tool. + navigationGroup: containers + sections: + - type: endpoint + key: CreateContainerFile + path: createContainerFile + - type: endpoint + key: ListContainerFiles + path: listContainerFiles + - type: endpoint + key: RetrieveContainerFile + path: retrieveContainerFile + - type: endpoint + key: RetrieveContainerFileContent + path: retrieveContainerFileContent + - type: endpoint + key: DeleteContainerFile + path: deleteContainerFile + - type: object + key: ContainerFileResource + path: object + - id: assistants + title: Assistants + beta: true + description: | + Build assistants that can call models and use tools to perform tasks. + + [Get started with the Assistants API](/docs/assistants) + navigationGroup: assistants + sections: + - type: endpoint + key: createAssistant + path: createAssistant + - type: endpoint + key: listAssistants + path: listAssistants + - type: endpoint + key: getAssistant + path: getAssistant + - type: endpoint + key: modifyAssistant + path: modifyAssistant + - type: endpoint + key: deleteAssistant + path: deleteAssistant + - type: object + key: AssistantObject + path: object + - id: threads + title: Threads + beta: true + description: | + Create threads that assistants can interact with. + + Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants + sections: + - type: endpoint + key: createThread + path: createThread + - type: endpoint + key: getThread + path: getThread + - type: endpoint + key: modifyThread + path: modifyThread + - type: endpoint + key: deleteThread + path: deleteThread + - type: object + key: ThreadObject + path: object + - id: messages + title: Messages + beta: true + description: | + Create messages within threads + + Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants + sections: + - type: endpoint + key: createMessage + path: createMessage + - type: endpoint + key: listMessages + path: listMessages + - type: endpoint + key: getMessage + path: getMessage + - type: endpoint + key: modifyMessage + path: modifyMessage + - type: endpoint + key: deleteMessage + path: deleteMessage + - type: object + key: MessageObject + path: object + - id: runs + title: Runs + beta: true + description: | + Represents an execution run on a thread. + + Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants + sections: + - type: endpoint + key: createRun + path: createRun + - type: endpoint + key: createThreadAndRun + path: createThreadAndRun + - type: endpoint + key: listRuns + path: listRuns + - type: endpoint + key: getRun + path: getRun + - type: endpoint + key: modifyRun + path: modifyRun + - type: endpoint + key: submitToolOuputsToRun + path: submitToolOutputs + - type: endpoint + key: cancelRun + path: cancelRun + - type: object + key: RunObject + path: object + - id: run-steps + title: Run steps + beta: true + description: | + Represents the steps (model and tool calls) taken during the run. + + Related guide: [Assistants](/docs/assistants/overview) + navigationGroup: assistants + sections: + - type: endpoint + key: listRunSteps + path: listRunSteps + - type: endpoint + key: getRunStep + path: getRunStep + - type: object + key: RunStepObject + path: step-object + - id: assistants-streaming + title: Streaming + beta: true + description: | + Stream the result of executing a Run or resuming a Run after submitting tool outputs. + You can stream events from the [Create Thread and Run](/docs/api-reference/runs/createThreadAndRun), + [Create Run](/docs/api-reference/runs/createRun), and [Submit Tool Outputs](/docs/api-reference/runs/submitToolOutputs) + endpoints by passing `"stream": true`. The response will be a [Server-Sent events](https://html.spec.whatwg.org/multipage/server-sent-events.html#server-sent-events) stream. + Our Node and Python SDKs provide helpful utilities to make streaming easy. Reference the + [Assistants API quickstart](/docs/assistants/overview) to learn more. + navigationGroup: assistants + sections: + - type: object + key: MessageDeltaObject + path: message-delta-object + - type: object + key: RunStepDeltaObject + path: run-step-delta-object + - type: object + key: AssistantStreamEvent + path: events + - id: administration + title: Administration + description: | + Programmatically manage your organization. + The Audit Logs endpoint provides a log of all actions taken in the organization for security and monitoring purposes. + To access these endpoints please generate an Admin API Key through the [API Platform Organization overview](/organization/admin-keys). Admin API keys cannot be used for non-administration endpoints. + For best practices on setting up your organization, please refer to this [guide](/docs/guides/production-best-practices#setting-up-your-organization) + navigationGroup: administration + - id: admin-api-keys + title: Admin API Keys + description: | + Admin API keys enable Organization Owners to programmatically manage various aspects of their organization, including users, projects, and API keys. These keys provide administrative capabilities, such as creating, updating, and deleting users; managing projects; and overseeing API key lifecycles. + + Key Features of Admin API Keys: + + - User Management: Invite new users, update roles, and remove users from the organization. + + - Project Management: Create, update, archive projects, and manage user assignments within projects. + + - API Key Oversight: List, retrieve, and delete API keys associated with projects. + + Only Organization Owners have the authority to create and utilize Admin API keys. To manage these keys, Organization Owners can navigate to the Admin Keys section of their API Platform dashboard. + + For direct access to the Admin Keys management page, Organization Owners can use the following link: + + [https://platform.openai.com/settings/organization/admin-keys](https://platform.openai.com/settings/organization/admin-keys) + + It's crucial to handle Admin API keys with care due to their elevated permissions. Adhering to best practices, such as regular key rotation and assigning appropriate permissions, enhances security and ensures proper governance within the organization. + navigationGroup: administration + sections: + - type: endpoint + key: admin-api-keys-list + path: list + - type: endpoint + key: admin-api-keys-create + path: create + - type: endpoint + key: admin-api-keys-get + path: listget + - type: endpoint + key: admin-api-keys-delete + path: delete + - type: object + key: AdminApiKey + path: object + - id: invite + title: Invites + description: Invite and manage invitations for an organization. + navigationGroup: administration + sections: + - type: endpoint + key: list-invites + path: list + - type: endpoint + key: inviteUser + path: create + - type: endpoint + key: retrieve-invite + path: retrieve + - type: endpoint + key: delete-invite + path: delete + - type: object + key: Invite + path: object + - id: users + title: Users + description: | + Manage users and their role in an organization. + navigationGroup: administration + sections: + - type: endpoint + key: list-users + path: list + - type: endpoint + key: modify-user + path: modify + - type: endpoint + key: retrieve-user + path: retrieve + - type: endpoint + key: delete-user + path: delete + - type: object + key: User + path: object + - id: projects + title: Projects + description: > + Manage the projects within an orgnanization includes creation, updating, + and archiving or projects. + + The Default project cannot be archived. + navigationGroup: administration + sections: + - type: endpoint + key: list-projects + path: list + - type: endpoint + key: create-project + path: create + - type: endpoint + key: retrieve-project + path: retrieve + - type: endpoint + key: modify-project + path: modify + - type: endpoint + key: archive-project + path: archive + - type: object + key: Project + path: object + - id: project-users + title: Project users + description: > + Manage users within a project, including adding, updating roles, and + removing users. + navigationGroup: administration + sections: + - type: endpoint + key: list-project-users + path: list + - type: endpoint + key: create-project-user + path: creeate + - type: endpoint + key: retrieve-project-user + path: retrieve + - type: endpoint + key: modify-project-user + path: modify + - type: endpoint + key: delete-project-user + path: delete + - type: object + key: ProjectUser + path: object + - id: project-service-accounts + title: Project service accounts + description: > + Manage service accounts within a project. A service account is a bot + user that is not associated with a user. + + If a user leaves an organization, their keys and membership in projects + will no longer work. Service accounts + + do not have this limitation. However, service accounts can also be + deleted from a project. + navigationGroup: administration + sections: + - type: endpoint + key: list-project-service-accounts + path: list + - type: endpoint + key: create-project-service-account + path: create + - type: endpoint + key: retrieve-project-service-account + path: retrieve + - type: endpoint + key: delete-project-service-account + path: delete + - type: object + key: ProjectServiceAccount + path: object + - id: project-api-keys + title: Project API keys + description: > + Manage API keys for a given project. Supports listing and deleting keys + for users. + + This API does not allow issuing keys for users, as users need to + authorize themselves to generate keys. + navigationGroup: administration + sections: + - type: endpoint + key: list-project-api-keys + path: list + - type: endpoint + key: retrieve-project-api-key + path: retrieve + - type: endpoint + key: delete-project-api-key + path: delete + - type: object + key: ProjectApiKey + path: object + - id: project-rate-limits + title: Project rate limits + description: > + Manage rate limits per model for projects. Rate limits may be configured + to be equal to or lower than the organization's rate limits. + navigationGroup: administration + sections: + - type: endpoint + key: list-project-rate-limits + path: list + - type: endpoint + key: update-project-rate-limits + path: update + - type: object + key: ProjectRateLimit + path: object + - id: audit-logs + title: Audit logs + description: > + Logs of user actions and configuration changes within this organization. + + To log events, an Organization Owner must activate logging in the [Data + Controls Settings](/settings/organization/data-controls/data-retention). + + Once activated, for security reasons, logging cannot be deactivated. + navigationGroup: administration + sections: + - type: endpoint + key: list-audit-logs + path: list + - type: object + key: AuditLog + path: object + - id: usage + title: Usage + description: > + The **Usage API** provides detailed insights into your activity across + the OpenAI API. It also includes a separate [Costs + endpoint](/docs/api-reference/usage/costs), which offers visibility into + your spend, breaking down consumption by invoice line items and project + IDs. + + + While the Usage API delivers granular usage data, it may not always + reconcile perfectly with the Costs due to minor differences in how usage + and spend are recorded. For financial purposes, we recommend using the + [Costs endpoint](/docs/api-reference/usage/costs) or the [Costs + tab](/settings/organization/usage) in the Usage Dashboard, which will + reconcile back to your billing invoice. + navigationGroup: administration + sections: + - type: endpoint + key: usage-completions + path: completions + - type: object + key: UsageCompletionsResult + path: completions_object + - type: endpoint + key: usage-embeddings + path: embeddings + - type: object + key: UsageEmbeddingsResult + path: embeddings_object + - type: endpoint + key: usage-moderations + path: moderations + - type: object + key: UsageModerationsResult + path: moderations_object + - type: endpoint + key: usage-images + path: images + - type: object + key: UsageImagesResult + path: images_object + - type: endpoint + key: usage-audio-speeches + path: audio_speeches + - type: object + key: UsageAudioSpeechesResult + path: audio_speeches_object + - type: endpoint + key: usage-audio-transcriptions + path: audio_transcriptions + - type: object + key: UsageAudioTranscriptionsResult + path: audio_transcriptions_object + - type: endpoint + key: usage-vector-stores + path: vector_stores + - type: object + key: UsageVectorStoresResult + path: vector_stores_object + - type: endpoint + key: usage-code-interpreter-sessions + path: code_interpreter_sessions + - type: object + key: UsageCodeInterpreterSessionsResult + path: code_interpreter_sessions_object + - type: endpoint + key: usage-costs + path: costs + - type: object + key: CostsResult + path: costs_object + - id: certificates + beta: true + title: Certificates + description: | + Manage Mutual TLS certificates across your organization and projects. + + [Learn more about Mutual TLS.](https://help.openai.com/en/articles/10876024-openai-mutual-tls-beta-program) + navigationGroup: administration + sections: + - type: endpoint + key: uploadCertificate + path: uploadCertificate + - type: endpoint + key: getCertificate + path: getCertificate + - type: endpoint + key: modifyCertificate + path: modifyCertificate + - type: endpoint + key: deleteCertificate + path: deleteCertificate + - type: endpoint + key: listOrganizationCertificates + path: listOrganizationCertificates + - type: endpoint + key: listProjectCertificates + path: listProjectCertificates + - type: endpoint + key: activateOrganizationCertificates + path: activateOrganizationCertificates + - type: endpoint + key: deactivateOrganizationCertificates + path: deactivateOrganizationCertificates + - type: endpoint + key: activateProjectCertificates + path: activateProjectCertificates + - type: endpoint + key: deactivateProjectCertificates + path: deactivateProjectCertificates + - type: object + key: Certificate + path: object + - id: completions + title: Completions + legacy: true + navigationGroup: legacy + description: > + Given a prompt, the model will return one or more predicted completions + along with the probabilities of alternative tokens at each position. + Most developer should use our [Chat Completions + API](/docs/guides/text-generation#text-generation-models) to leverage + our best and newest models. + sections: + - type: endpoint + key: createCompletion + path: create + - type: object + key: CreateCompletionResponse + path: object diff --git a/specification/base/typespec/administration/custom.tsp b/specification/base/typespec/administration/custom.tsp new file mode 100644 index 000000000..1589d157f --- /dev/null +++ b/specification/base/typespec/administration/custom.tsp @@ -0,0 +1,3 @@ +import "@typespec/http"; + +namespace OpenAI; diff --git a/specification/base/typespec/administration/main.tsp b/specification/base/typespec/administration/main.tsp new file mode 100644 index 000000000..5ad1d3a2b --- /dev/null +++ b/specification/base/typespec/administration/main.tsp @@ -0,0 +1 @@ +import "./models.tsp"; diff --git a/specification/base/typespec/administration/models.tsp b/specification/base/typespec/administration/models.tsp new file mode 100644 index 000000000..6fecfe846 --- /dev/null +++ b/specification/base/typespec/administration/models.tsp @@ -0,0 +1,1411 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from AuditLog.certificates_activated.certificates +alias AuditLogCertificatesActivatedCertificate = { + /** The certificate ID. */ + id?: string; + + /** The name of the certificate. */ + name?: string; +}; + +// Tool generated type. Extracts from AuditLog.certificates_deactivated.certificates +alias AuditLogCertificatesDeactivatedCertificate = { + /** The certificate ID. */ + id?: string; + + /** The name of the certificate. */ + name?: string; +}; + +// Tool generated type. Extracts from Invite.projects +alias InviteProject = { + /** Project's public ID */ + id?: string; + + /** Project membership role */ + role?: "member" | "owner"; +}; + +// Tool generated type. Extracts from InviteRequest.projects +alias InviteRequestProject = { + /** Project's public ID */ + id: string; + + /** Project membership role */ + role: "member" | "owner"; +}; + +/** Represents an individual Admin API key in an org. */ +model AdminApiKey { + @doc(""" + The object type, which is always `organization.admin_api_key` + """) + object: string; + + /** The identifier, which can be referenced in API endpoints */ + id: string; + + /** The name of the API key */ + name: string; + + /** The redacted value of the API key */ + redacted_value: string; + + /** The value of the API key. Only shown on create. */ + value?: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the API key was created */ + @encode("unixTimestamp", int64) + created_at: utcDateTime; + + /** The Unix timestamp (in seconds) of when the API key was last used */ + last_used_at: int64 | null; + + owner: { + @doc(""" + Always `user` + """) + type?: string; + + /** The object type, which is always organization.user */ + object?: string; + + /** The identifier, which can be referenced in API endpoints */ + id?: string; + + /** The name of the user */ + name?: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the user was created */ + @encode("unixTimestamp", int64) + created_at?: utcDateTime; + + @doc(""" + Always `owner` + """) + role?: string; + }; +} + +model ApiKeyList { + object?: string; + data?: AdminApiKey[]; + has_more?: boolean; + first_id?: string; + last_id?: string; +} + +/** The service account that performed the audit logged action. */ +model AuditLogActorServiceAccount { + /** The service account id. */ + id?: string; +} + +/** The user who performed the audit logged action. */ +model AuditLogActorUser { + /** The user id. */ + id?: string; + + /** The user email. */ + email?: string; +} + +/** The API Key used to perform the audit logged action. */ +model AuditLogActorApiKey { + /** The tracking id of the API key. */ + id?: string; + + @doc(""" + The type of API key. Can be either `user` or `service_account`. + """) + type?: "user" | "service_account"; + + user?: AuditLogActorUser; + service_account?: AuditLogActorServiceAccount; +} + +/** The session in which the audit logged action was performed. */ +model AuditLogActorSession { + user?: AuditLogActorUser; + + /** The IP address from which the action was performed. */ + ip_address?: string; +} + +/** The actor who performed the audit logged action. */ +model AuditLogActor { + @doc(""" + The type of actor. Is either `session` or `api_key`. + """) + type?: "session" | "api_key"; + + session?: AuditLogActorSession; + api_key?: AuditLogActorApiKey; +} + +/** The event type. */ +union AuditLogEventType { + "api_key.created", + "api_key.updated", + "api_key.deleted", + "checkpoint_permission.created", + "checkpoint_permission.deleted", + "invite.sent", + "invite.accepted", + "invite.deleted", + "login.succeeded", + "login.failed", + "logout.succeeded", + "logout.failed", + "organization.updated", + "project.created", + "project.updated", + "project.archived", + "service_account.created", + "service_account.updated", + "service_account.deleted", + "rate_limit.updated", + "rate_limit.deleted", + "user.added", + "user.updated", + "user.deleted", +} + +/** A log of a user action or configuration change within this organization. */ +model AuditLog { + /** The ID of this log. */ + id: string; + + type: AuditLogEventType; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of the event. */ + @encode("unixTimestamp", int32) + effective_at: utcDateTime; + + /** The project that the action was scoped to. Absent for actions not scoped to projects. */ + project?: { + /** The project ID. */ + id?: string; + + /** The project title. */ + name?: string; + }; + + actor: AuditLogActor; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "api_key.created") + api_key_created?: { + /** The tracking ID of the API key. */ + id?: string; + + /** The payload used to create the API key. */ + data?: { + @doc(""" + A list of scopes allowed for the API key, e.g. `["api.model.request"]` + """) + scopes?: string[]; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "api_key.updated") + api_key_updated?: { + /** The tracking ID of the API key. */ + id?: string; + + /** The payload used to update the API key. */ + changes_requested?: { + @doc(""" + A list of scopes allowed for the API key, e.g. `["api.model.request"]` + """) + scopes?: string[]; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "api_key.deleted") + api_key_deleted?: { + /** The tracking ID of the API key. */ + id?: string; + }; + + /** The project and fine-tuned model checkpoint that the checkpoint permission was created for. */ + @encodedName("application/json", "checkpoint_permission.created") + checkpoint_permission_created?: { + /** The ID of the checkpoint permission. */ + id?: string; + + /** The payload used to create the checkpoint permission. */ + data?: { + /** The ID of the project that the checkpoint permission was created for. */ + project_id?: string; + + /** The ID of the fine-tuned model checkpoint. */ + fine_tuned_model_checkpoint?: string; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "checkpoint_permission.deleted") + checkpoint_permission_deleted?: { + /** The ID of the checkpoint permission. */ + id?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "invite.sent") + invite_sent?: { + /** The ID of the invite. */ + id?: string; + + /** The payload used to create the invite. */ + data?: { + /** The email invited to the organization. */ + email?: string; + + @doc(""" + The role the email was invited to be. Is either `owner` or `member`. + """) + role?: string; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "invite.accepted") + invite_accepted?: { + /** The ID of the invite. */ + id?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "invite.deleted") + invite_deleted?: { + /** The ID of the invite. */ + id?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "login.failed") + login_failed?: { + /** The error code of the failure. */ + error_code?: string; + + /** The error message of the failure. */ + error_message?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "logout.failed") + logout_failed?: { + /** The error code of the failure. */ + error_code?: string; + + /** The error message of the failure. */ + error_message?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "organization.updated") + organization_updated?: { + /** The organization ID. */ + id?: string; + + /** The payload used to update the organization settings. */ + changes_requested?: { + /** The organization title. */ + title?: string; + + /** The organization description. */ + description?: string; + + /** The organization name. */ + name?: string; + + @doc(""" + Visibility of the threads page which shows messages created with the Assistants API and Playground. One of `ANY_ROLE`, `OWNERS`, or `NONE`. + """) + threads_ui_visibility?: string; + + @doc(""" + Visibility of the usage dashboard which shows activity and costs for your organization. One of `ANY_ROLE` or `OWNERS`. + """) + usage_dashboard_visibility?: string; + + @doc(""" + How your organization logs data from supported API calls. One of `disabled`, `enabled_per_call`, `enabled_for_all_projects`, or `enabled_for_selected_projects` + """) + api_call_logging?: string; + + @doc(""" + The list of project ids if api_call_logging is set to `enabled_for_selected_projects` + """) + api_call_logging_project_ids?: string; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "project.created") + project_created?: { + /** The project ID. */ + id?: string; + + /** The payload used to create the project. */ + data?: { + /** The project name. */ + name?: string; + + /** The title of the project as seen on the dashboard. */ + title?: string; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "project.updated") + project_updated?: { + /** The project ID. */ + id?: string; + + /** The payload used to update the project. */ + changes_requested?: { + /** The title of the project as seen on the dashboard. */ + title?: string; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "project.archived") + project_archived?: { + /** The project ID. */ + id?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "rate_limit.updated") + rate_limit_updated?: { + /** The rate limit ID */ + id?: string; + + /** The payload used to update the rate limits. */ + changes_requested?: { + /** The maximum requests per minute. */ + max_requests_per_1_minute?: int32; + + /** The maximum tokens per minute. */ + max_tokens_per_1_minute?: int32; + + /** The maximum images per minute. Only relevant for certain models. */ + max_images_per_1_minute?: int32; + + /** The maximum audio megabytes per minute. Only relevant for certain models. */ + max_audio_megabytes_per_1_minute?: int32; + + /** The maximum requests per day. Only relevant for certain models. */ + max_requests_per_1_day?: int32; + + /** The maximum batch input tokens per day. Only relevant for certain models. */ + batch_1_day_max_input_tokens?: int32; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "rate_limit.deleted") + rate_limit_deleted?: { + /** The rate limit ID */ + id?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "service_account.created") + service_account_created?: { + /** The service account ID. */ + id?: string; + + /** The payload used to create the service account. */ + data?: { + @doc(""" + The role of the service account. Is either `owner` or `member`. + """) + role?: string; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "service_account.updated") + service_account_updated?: { + /** The service account ID. */ + id?: string; + + /** The payload used to updated the service account. */ + changes_requested?: { + @doc(""" + The role of the service account. Is either `owner` or `member`. + """) + role?: string; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "service_account.deleted") + service_account_deleted?: { + /** The service account ID. */ + id?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "user.added") + user_added?: { + /** The user ID. */ + id?: string; + + /** The payload used to add the user to the project. */ + data?: { + @doc(""" + The role of the user. Is either `owner` or `member`. + """) + role?: string; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "user.updated") + user_updated?: { + /** The project ID. */ + id?: string; + + /** The payload used to update the user. */ + changes_requested?: { + @doc(""" + The role of the user. Is either `owner` or `member`. + """) + role?: string; + }; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "user.deleted") + user_deleted?: { + /** The user ID. */ + id?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "certificate.created") + certificate_created?: { + /** The certificate ID. */ + id?: string; + + /** The name of the certificate. */ + name?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "certificate.updated") + certificate_updated?: { + /** The certificate ID. */ + id?: string; + + /** The name of the certificate. */ + name?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "certificate.deleted") + certificate_deleted?: { + /** The certificate ID. */ + id?: string; + + /** The name of the certificate. */ + name?: string; + + /** The certificate content in PEM format. */ + certificate?: string; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "certificates.activated") + certificates_activated?: { + certificates?: AuditLogCertificatesActivatedCertificate[]; + }; + + @doc(""" + The details for events with this `type`. + """) + @encodedName("application/json", "certificates.deactivated") + certificates_deactivated?: { + certificates?: AuditLogCertificatesDeactivatedCertificate[]; + }; +} + +model ListAuditLogsResponse { + object: "list"; + data: AuditLog[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +@doc(""" + Represents an individual `invite` to the organization. + """) +model Invite { + @doc(""" + The object type, which is always `organization.invite` + """) + object: "organization.invite"; + + /** The identifier, which can be referenced in API endpoints */ + id: string; + + /** The email address of the individual to whom the invite was sent */ + email: string; + + @doc(""" + `owner` or `reader` + """) + role: "owner" | "reader"; + + @doc(""" + `accepted`,`expired`, or `pending` + """) + status: "accepted" | "expired" | "pending"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the invite was sent. */ + @encode("unixTimestamp", int32) + invited_at: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the invite expires. */ + @encode("unixTimestamp", int32) + expires_at: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the invite was accepted. */ + @encode("unixTimestamp", int32) + accepted_at?: utcDateTime; + + /** The projects that were granted membership upon acceptance of the invite. */ + projects?: InviteProject[]; +} + +model InviteListResponse { + @doc(""" + The object type, which is always `list` + """) + object: "list"; + + data: Invite[]; + + @doc(""" + The first `invite_id` in the retrieved `list` + """) + first_id?: string; + + @doc(""" + The last `invite_id` in the retrieved `list` + """) + last_id?: string; + + @doc(""" + The `has_more` property is used for pagination to indicate there are additional results. + """) + has_more?: boolean; +} + +model InviteRequest { + /** Send an email to this address */ + email: string; + + @doc(""" + `owner` or `reader` + """) + role: "reader" | "owner"; + + /** An array of projects to which membership is granted at the same time the org invite is accepted. If omitted, the user will be invited to the default project for compatibility with legacy behavior. */ + projects?: InviteRequestProject[]; +} + +model InviteDeleteResponse { + @doc(""" + The object type, which is always `organization.invite.deleted` + """) + object: "organization.invite.deleted"; + + id: string; + deleted: boolean; +} + +@doc(""" + Represents an individual `user` within an organization. + """) +model User { + @doc(""" + The object type, which is always `organization.user` + """) + object: "organization.user"; + + /** The identifier, which can be referenced in API endpoints */ + id: string; + + /** The name of the user */ + name: string; + + /** The email address of the user */ + email: string; + + @doc(""" + `owner` or `reader` + """) + role: "owner" | "reader"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the user was added. */ + @encode("unixTimestamp", int32) + added_at: utcDateTime; +} + +model UserListResponse { + object: "list"; + data: User[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model UserRoleUpdateRequest { + @doc(""" + `owner` or `reader` + """) + role: "owner" | "reader"; +} + +model UserDeleteResponse { + object: "organization.user.deleted"; + id: string; + deleted: boolean; +} + +/** Represents an individual project. */ +model Project { + /** The identifier, which can be referenced in API endpoints */ + id: string; + + @doc(""" + The object type, which is always `organization.project` + """) + object: "organization.project"; + + /** The name of the project. This appears in reporting. */ + name: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the project was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + @doc(""" + The Unix timestamp (in seconds) of when the project was archived or `null`. + """) + @encode("unixTimestamp", int32) + archived_at?: utcDateTime | null; + + @doc(""" + `active` or `archived` + """) + status: "active" | "archived"; +} + +model ProjectListResponse { + object: "list"; + data: Project[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model ProjectCreateRequest { + /** The friendly name of the project, this name appears in reports. */ + name: string; +} + +model ProjectUpdateRequest { + /** The updated name of the project, this name appears in reports. */ + name: string; +} + +/** Represents an individual user in a project. */ +model ProjectUser { + @doc(""" + The object type, which is always `organization.project.user` + """) + object: "organization.project.user"; + + /** The identifier, which can be referenced in API endpoints */ + id: string; + + /** The name of the user */ + name: string; + + /** The email address of the user */ + email: string; + + @doc(""" + `owner` or `member` + """) + role: "owner" | "member"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the project was added. */ + @encode("unixTimestamp", int32) + added_at: utcDateTime; +} + +model ProjectUserListResponse { + object: string; + data: ProjectUser[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model ProjectUserCreateRequest { + /** The ID of the user. */ + user_id: string; + + @doc(""" + `owner` or `member` + """) + role: "owner" | "member"; +} + +model ProjectUserUpdateRequest { + @doc(""" + `owner` or `member` + """) + role: "owner" | "member"; +} + +model ProjectUserDeleteResponse { + object: "organization.project.user.deleted"; + id: string; + deleted: boolean; +} + +/** Represents an individual service account in a project. */ +model ProjectServiceAccount { + @doc(""" + The object type, which is always `organization.project.service_account` + """) + object: "organization.project.service_account"; + + /** The identifier, which can be referenced in API endpoints */ + id: string; + + /** The name of the service account */ + name: string; + + @doc(""" + `owner` or `member` + """) + role: "owner" | "member"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the service account was created */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; +} + +model ProjectServiceAccountListResponse { + object: "list"; + data: ProjectServiceAccount[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model ProjectServiceAccountCreateRequest { + /** The name of the service account being created. */ + name: string; +} + +model ProjectServiceAccountCreateResponse { + object: "organization.project.service_account"; + id: string; + name: string; + + @doc(""" + Service accounts can only have one role of type `member` + """) + role: "member"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + api_key: ProjectServiceAccountApiKey; +} + +model ProjectServiceAccountApiKey { + @doc(""" + The object type, which is always `organization.project.service_account.api_key` + """) + object: "organization.project.service_account.api_key"; + + value: string; + name: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + id: string; +} + +model ProjectServiceAccountDeleteResponse { + object: "organization.project.service_account.deleted"; + id: string; + deleted: boolean; +} + +/** Represents an individual API key in a project. */ +model ProjectApiKey { + @doc(""" + The object type, which is always `organization.project.api_key` + """) + object: "organization.project.api_key"; + + /** The redacted value of the API key */ + redacted_value: string; + + /** The name of the API key */ + name: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the API key was created */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the API key was last used. */ + @encode("unixTimestamp", int32) + last_used_at: utcDateTime; + + /** The identifier, which can be referenced in API endpoints */ + id: string; + + owner: { + @doc(""" + `user` or `service_account` + """) + type?: "user" | "service_account"; + + user?: ProjectUser; + service_account?: ProjectServiceAccount; + }; +} + +model ProjectApiKeyListResponse { + object: "list"; + data: ProjectApiKey[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model ProjectApiKeyDeleteResponse { + object: "organization.project.api_key.deleted"; + id: string; + deleted: boolean; +} + +/** The aggregated costs details of the specific time bucket. */ +model CostsResult { + object: "organization.costs.result"; + + /** The monetary value in its associated currency. */ + amount?: { + /** The numeric value of the cost. */ + value?: float32; + + /** Lowercase ISO-4217 currency e.g. "usd" */ + currency?: string; + }; + + @doc(""" + When `group_by=line_item`, this field provides the line item of the grouped costs result. + """) + line_item?: string | null; + + @doc(""" + When `group_by=project_id`, this field provides the project ID of the grouped costs result. + """) + project_id?: string | null; +} + +/** Represents a project rate limit config. */ +model ProjectRateLimit { + @doc(""" + The object type, which is always `project.rate_limit` + """) + object: "project.rate_limit"; + + /** The identifier, which can be referenced in API endpoints. */ + id: string; + + /** The model this rate limit applies to. */ + `model`: string; + + /** The maximum requests per minute. */ + max_requests_per_1_minute: int32; + + /** The maximum tokens per minute. */ + max_tokens_per_1_minute: int32; + + /** The maximum images per minute. Only present for relevant models. */ + max_images_per_1_minute?: int32; + + /** The maximum audio megabytes per minute. Only present for relevant models. */ + max_audio_megabytes_per_1_minute?: int32; + + /** The maximum requests per day. Only present for relevant models. */ + max_requests_per_1_day?: int32; + + /** The maximum batch input tokens per day. Only present for relevant models. */ + batch_1_day_max_input_tokens?: int32; +} + +model ProjectRateLimitListResponse { + object: "list"; + data: ProjectRateLimit[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model ProjectRateLimitUpdateRequest { + /** The maximum requests per minute. */ + max_requests_per_1_minute?: int32; + + /** The maximum tokens per minute. */ + max_tokens_per_1_minute?: int32; + + /** The maximum images per minute. Only relevant for certain models. */ + max_images_per_1_minute?: int32; + + /** The maximum audio megabytes per minute. Only relevant for certain models. */ + max_audio_megabytes_per_1_minute?: int32; + + /** The maximum requests per day. Only relevant for certain models. */ + max_requests_per_1_day?: int32; + + /** The maximum batch input tokens per day. Only relevant for certain models. */ + batch_1_day_max_input_tokens?: int32; +} + +/** The aggregated audio speeches usage details of the specific time bucket. */ +model UsageAudioSpeechesResult { + object: "organization.usage.audio_speeches.result"; + + /** The number of characters processed. */ + characters: int32; + + /** The count of requests made to the model. */ + num_model_requests: int32; + + @doc(""" + When `group_by=project_id`, this field provides the project ID of the grouped usage result. + """) + project_id?: string | null; + + @doc(""" + When `group_by=user_id`, this field provides the user ID of the grouped usage result. + """) + user_id?: string | null; + + @doc(""" + When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result. + """) + api_key_id?: string | null; + + @doc(""" + When `group_by=model`, this field provides the model name of the grouped usage result. + """) + `model`?: string | null; +} + +/** The aggregated audio transcriptions usage details of the specific time bucket. */ +model UsageAudioTranscriptionsResult { + object: "organization.usage.audio_transcriptions.result"; + + /** The number of seconds processed. */ + seconds: int32; + + /** The count of requests made to the model. */ + num_model_requests: int32; + + @doc(""" + When `group_by=project_id`, this field provides the project ID of the grouped usage result. + """) + project_id?: string | null; + + @doc(""" + When `group_by=user_id`, this field provides the user ID of the grouped usage result. + """) + user_id?: string | null; + + @doc(""" + When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result. + """) + api_key_id?: string | null; + + @doc(""" + When `group_by=model`, this field provides the model name of the grouped usage result. + """) + `model`?: string | null; +} + +/** The aggregated code interpreter sessions usage details of the specific time bucket. */ +model UsageCodeInterpreterSessionsResult { + object: "organization.usage.code_interpreter_sessions.result"; + + /** The number of code interpreter sessions. */ + num_sessions?: int32; + + @doc(""" + When `group_by=project_id`, this field provides the project ID of the grouped usage result. + """) + project_id?: string | null; +} + +/** The aggregated completions usage details of the specific time bucket. */ +model UsageCompletionsResult { + object: "organization.usage.completions.result"; + + /** The aggregated number of text input tokens used, including cached tokens. For customers subscribe to scale tier, this includes scale tier tokens. */ + input_tokens: int32; + + /** The aggregated number of text input tokens that has been cached from previous requests. For customers subscribe to scale tier, this includes scale tier tokens. */ + input_cached_tokens?: int32; + + /** The aggregated number of text output tokens used. For customers subscribe to scale tier, this includes scale tier tokens. */ + output_tokens: int32; + + /** The aggregated number of audio input tokens used, including cached tokens. */ + input_audio_tokens?: int32; + + /** The aggregated number of audio output tokens used. */ + output_audio_tokens?: int32; + + /** The count of requests made to the model. */ + num_model_requests: int32; + + @doc(""" + When `group_by=project_id`, this field provides the project ID of the grouped usage result. + """) + project_id?: string | null; + + @doc(""" + When `group_by=user_id`, this field provides the user ID of the grouped usage result. + """) + user_id?: string | null; + + @doc(""" + When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result. + """) + api_key_id?: string | null; + + @doc(""" + When `group_by=model`, this field provides the model name of the grouped usage result. + """) + `model`?: string | null; + + @doc(""" + When `group_by=batch`, this field tells whether the grouped usage result is batch or not. + """) + batch?: boolean | null; +} + +/** The aggregated embeddings usage details of the specific time bucket. */ +model UsageEmbeddingsResult { + object: "organization.usage.embeddings.result"; + + /** The aggregated number of input tokens used. */ + input_tokens: int32; + + /** The count of requests made to the model. */ + num_model_requests: int32; + + @doc(""" + When `group_by=project_id`, this field provides the project ID of the grouped usage result. + """) + project_id?: string | null; + + @doc(""" + When `group_by=user_id`, this field provides the user ID of the grouped usage result. + """) + user_id?: string | null; + + @doc(""" + When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result. + """) + api_key_id?: string | null; + + @doc(""" + When `group_by=model`, this field provides the model name of the grouped usage result. + """) + `model`?: string | null; +} + +/** The aggregated images usage details of the specific time bucket. */ +model UsageImagesResult { + object: "organization.usage.images.result"; + + /** The number of images processed. */ + images: int32; + + /** The count of requests made to the model. */ + num_model_requests: int32; + + @doc(""" + When `group_by=source`, this field provides the source of the grouped usage result, possible values are `image.generation`, `image.edit`, `image.variation`. + """) + source?: string | null; + + @doc(""" + When `group_by=size`, this field provides the image size of the grouped usage result. + """) + size?: string | null; + + @doc(""" + When `group_by=project_id`, this field provides the project ID of the grouped usage result. + """) + project_id?: string | null; + + @doc(""" + When `group_by=user_id`, this field provides the user ID of the grouped usage result. + """) + user_id?: string | null; + + @doc(""" + When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result. + """) + api_key_id?: string | null; + + @doc(""" + When `group_by=model`, this field provides the model name of the grouped usage result. + """) + `model`?: string | null; +} + +/** The aggregated moderations usage details of the specific time bucket. */ +model UsageModerationsResult { + object: "organization.usage.moderations.result"; + + /** The aggregated number of input tokens used. */ + input_tokens: int32; + + /** The count of requests made to the model. */ + num_model_requests: int32; + + @doc(""" + When `group_by=project_id`, this field provides the project ID of the grouped usage result. + """) + project_id?: string | null; + + @doc(""" + When `group_by=user_id`, this field provides the user ID of the grouped usage result. + """) + user_id?: string | null; + + @doc(""" + When `group_by=api_key_id`, this field provides the API key ID of the grouped usage result. + """) + api_key_id?: string | null; + + @doc(""" + When `group_by=model`, this field provides the model name of the grouped usage result. + """) + `model`?: string | null; +} + +model UsageResponse { + object: "page"; + data: UsageTimeBucket[]; + has_more: boolean; + next_page: string; +} + +model UsageTimeBucket { + object: "bucket"; + start_time: int32; + end_time: int32; + result: ( + | UsageCompletionsResult + | UsageEmbeddingsResult + | UsageModerationsResult + | UsageImagesResult + | UsageAudioSpeechesResult + | UsageAudioTranscriptionsResult + | UsageVectorStoresResult + | UsageCodeInterpreterSessionsResult + | CostsResult)[]; +} + +/** The aggregated vector stores usage details of the specific time bucket. */ +model UsageVectorStoresResult { + object: "organization.usage.vector_stores.result"; + + /** The vector stores usage in bytes. */ + usage_bytes: int32; + + @doc(""" + When `group_by=project_id`, this field provides the project ID of the grouped usage result. + """) + project_id?: string | null; +} + +@doc(""" + Represents an individual `certificate` uploaded to the organization. + """) +model Certificate { + @doc(""" + The object type. + + - If creating, updating, or getting a specific certificate, the object type is `certificate`. + - If listing, activating, or deactivating certificates for the organization, the object type is `organization.certificate`. + - If listing, activating, or deactivating certificates for a project, the object type is `organization.project.certificate`. + """) + object: "certificate" | "organization.certificate" | "organization.project.certificate"; + + /** The identifier, which can be referenced in API endpoints */ + id: string; + + /** The name of the certificate. */ + name: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the certificate was uploaded. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + certificate_details: { + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the certificate becomes valid. */ + @encode("unixTimestamp", int32) + valid_at?: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the certificate expires. */ + @encode("unixTimestamp", int32) + expires_at?: utcDateTime; + + /** The content of the certificate in PEM format. */ + content?: string; + }; + + /** Whether the certificate is currently active at the specified scope. Not returned when getting details for a specific certificate. */ + active?: boolean; +} + +model DeleteCertificateResponse { + @doc(""" + The object type, must be `certificate.deleted`. + """) + object: "certificate.deleted"; + + /** The ID of the certificate that was deleted. */ + id: string; +} + +model ListCertificatesResponse { + data: Certificate[]; + first_id?: string; + last_id?: string; + has_more: boolean; + object: "list"; +} + +model ModifyCertificateRequest { + /** The updated name for the certificate */ + name: string; +} + +model ToggleCertificatesRequest { + @minItems(1) + @maxItems(10) + certificate_ids: string[]; +} + +model UploadCertificateRequest { + /** An optional name for the certificate */ + name?: string; + + /** The certificate content in PEM format */ + content: string; +} diff --git a/specification/base/typespec/assistants/custom.tsp b/specification/base/typespec/assistants/custom.tsp new file mode 100644 index 000000000..004dbcf6a --- /dev/null +++ b/specification/base/typespec/assistants/custom.tsp @@ -0,0 +1,65 @@ +import "@azure-tools/typespec-client-generator-core"; +import "@typespec/http"; +import "../common/models.tsp"; +import "../vector-stores/models.tsp"; + +using Azure.ClientGenerator.Core; +using TypeSpec.OpenAPI; +using TypeSpec.Http; + +namespace OpenAI; + +// This customization allows us to concretely specify that the file_search object must provide +// either ID references --or-- in-line creation helpers, but not both. + +model ToolResourcesFileSearch { + ...ToolResourcesFileSearchIdsOnly; + ...ToolResourcesFileSearchVectorStoreCreationHelpers; +} + +model ToolResourcesFileSearchIdsOnly { + /** + * The [vector store](/docs/api-reference/vector-stores/object) attached to this assistant. + * There can be a maximum of 1 vector store attached to the assistant. + */ + @maxItems(1) + vector_store_ids?: string[]; +} + +model ToolResourcesFileSearchVectorStoreCreationHelpers { + /** + * A helper to create a [vector store](/docs/api-reference/vector-stores/object) with + * file_ids and attach it to this assistant. There can be a maximum of 1 vector store + * attached to the assistant. + */ + @maxItems(1) + vector_stores?: ToolResourcesFileSearchVectorStoreCreationHelper[]; +} + +alias ToolResourcesFileSearchVectorStoreCreationHelper = { + /** + * A list of [file](/docs/api-reference/files) IDs to add to the vector store. There can be + * a maximum of 10000 files in a vector store. + */ + @maxItems(10000) + file_ids?: string[]; + + @doc(""" + The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. Only applicable if `file_ids` is non-empty. + """) + @extension("x-oaiExpandable", true) + chunking_strategy?: ChunkingStrategyRequestParam; + + ...MetadataPropertyForRequest; +}; + +union AssistantToolDefinitionType { + code_interpreter: "code_interpreter", + file_search: "file_search", + function: "function", +} + +@discriminator("type") +model AssistantToolDefinition { + type: AssistantToolDefinitionType; +} diff --git a/specification/base/typespec/assistants/main.tsp b/specification/base/typespec/assistants/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/assistants/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/assistants/models.tsp b/specification/base/typespec/assistants/models.tsp new file mode 100644 index 000000000..2bfe7a928 --- /dev/null +++ b/specification/base/typespec/assistants/models.tsp @@ -0,0 +1,376 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../common"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@doc(""" + Specifies the format that the model must output. Compatible with [GPT-4o](/docs/models#gpt-4o), [GPT-4 Turbo](/docs/models#gpt-4-turbo-and-gpt-4), and all GPT-3.5 Turbo models since `gpt-3.5-turbo-1106`. + + Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](/docs/guides/structured-outputs). + + Setting to `{ "type": "json_object" }` enables JSON mode, which ensures the message the model generates is valid JSON. + + **Important:** when using JSON mode, you **must** also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length. + """) +union AssistantsApiResponseFormatOption { + "auto", + ResponseFormatText, + ResponseFormatJsonObject, + ResponseFormatJsonSchema, +} + +model CreateAssistantRequest { + /** ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them. */ + @extension("x-oaiTypeLabel", "string") + `model`: AssistantSupportedModels; + + /** The name of the assistant. The maximum length is 256 characters. */ + @maxLength(256) + name?: string | null; + + /** The description of the assistant. The maximum length is 512 characters. */ + @maxLength(512) + description?: string | null; + + /** The system instructions that the assistant uses. The maximum length is 256,000 characters. */ + @maxLength(256000) + instructions?: string | null; + + reasoning_effort?: ReasoningEffort | null = "medium"; + + // Tool customization: use common model base for tool definitions + @doc(""" + A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`. + """) + @maxItems(128) + tools?: AssistantToolDefinition[] = #[]; + + @doc(""" + A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + """) + tool_resources?: { + code_interpreter?: { + @doc(""" + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + """) + @maxItems(20) + file_ids?: string[] = #[]; + }; + + // Tool customization: use custom type for sophisticated union + file_search?: ToolResourcesFileSearch; + } | null; + + ...MetadataPropertyForRequest; + + /** What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. */ + @minValue(0) + @maxValue(2) + temperature?: float32 | null = 1; + + /** + * An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + * + * We generally recommend altering this or temperature but not both. + */ + @minValue(0) + @maxValue(1) + top_p?: float32 | null = 1; + + response_format?: AssistantsApiResponseFormatOption | null; +} + +model ModifyAssistantRequest { + /** ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them. */ + `model`?: AssistantSupportedModels; + + reasoning_effort?: ReasoningEffort | null = "medium"; + + /** The name of the assistant. The maximum length is 256 characters. */ + @maxLength(256) + name?: string | null; + + /** The description of the assistant. The maximum length is 512 characters. */ + @maxLength(512) + description?: string | null; + + /** The system instructions that the assistant uses. The maximum length is 256,000 characters. */ + @maxLength(256000) + instructions?: string | null; + + // Tool customization: use common model base for tool definitions + @doc(""" + A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`. + """) + @maxItems(128) + tools?: AssistantToolDefinition[] = #[]; + + @doc(""" + A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + """) + tool_resources?: { + code_interpreter?: { + @doc(""" + Overrides the list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + """) + @maxItems(20) + file_ids?: string[] = #[]; + }; + + // Tool customization: use custom type for sophisticated union + file_search?: ToolResourcesFileSearchIdsOnly; + } | null; + + ...MetadataPropertyForRequest; + + /** What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. */ + @minValue(0) + @maxValue(2) + temperature?: float32 | null = 1; + + /** + * An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + * + * We generally recommend altering this or temperature but not both. + */ + @minValue(0) + @maxValue(1) + top_p?: float32 | null = 1; + + response_format?: AssistantsApiResponseFormatOption | null; +} + +model ListAssistantsResponse { + // Tool customization: add a clear enum enforcement of constrained 'object' label + object: "list"; + + data: AssistantObject[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model DeleteAssistantResponse { + id: string; + deleted: boolean; + object: "assistant.deleted"; +} + +// Tool customization (apply_discriminator): apply a common model base for tool definitions +model AssistantToolsCode extends AssistantToolDefinition { + @doc(""" + The type of tool being defined: `code_interpreter` + """) + type: AssistantToolDefinitionType.code_interpreter; +} + +// Tool customization (apply_discriminator): apply a common model base for tool definitions +model AssistantToolsFileSearch extends AssistantToolDefinition { + @doc(""" + The type of tool being defined: `file_search` + """) + type: AssistantToolDefinitionType.file_search; + + /** Overrides for the file search tool. */ + file_search?: { + @doc(""" + The maximum number of results the file search tool should output. The default is 20 for `gpt-4*` models and 5 for `gpt-3.5-turbo`. This number should be between 1 and 50 inclusive. + + Note that the file search tool may output fewer than `max_num_results` results. See the [file search tool documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) for more information. + """) + @minValue(1) + @maxValue(50) + max_num_results?: int32; + + ranking_options?: FileSearchRankingOptions; + }; +} + +@doc(""" + The ranking options for the file search. If not specified, the file search tool will use the `auto` ranker and a score_threshold of 0. + + See the [file search tool documentation](/docs/assistants/tools/file-search#customizing-file-search-settings) for more information. + """) +model FileSearchRankingOptions { + ranker?: FileSearchRanker; + + /** The score threshold for the file search. All values must be a floating point number between 0 and 1. */ + @minValue(0) + @maxValue(1) + score_threshold: float32; +} + +model AssistantToolsFileSearchTypeOnly { + @doc(""" + The type of tool being defined: `file_search` + """) + type: "file_search"; +} + +// Tool customization (apply_discriminator): apply a common model base for tool definitions +model AssistantToolsFunction extends AssistantToolDefinition { + @doc(""" + The type of tool being defined: `function` + """) + type: AssistantToolDefinitionType.function; + + function: FunctionObject; +} + +@doc(""" + Represents an `assistant` that can call the model and use tools. + """) +model AssistantObject { + /** The identifier, which can be referenced in API endpoints. */ + id: string; + + @doc(""" + The object type, which is always `assistant`. + """) + object: "assistant"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the assistant was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The name of the assistant. The maximum length is 256 characters. */ + @maxLength(256) + name: string | null; + + /** The description of the assistant. The maximum length is 512 characters. */ + @maxLength(512) + description: string | null; + + /** ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them. */ + `model`: string; + + /** The system instructions that the assistant uses. The maximum length is 256,000 characters. */ + @maxLength(256000) + instructions: string | null; + + // Tool customization: use common model base for tool definitions + @doc(""" + A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types `code_interpreter`, `file_search`, or `function`. + """) + @maxItems(128) + tools: AssistantToolDefinition[] = #[]; + + @doc(""" + A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + """) + tool_resources?: { + code_interpreter?: { + @doc(""" + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter`` tool. There can be a maximum of 20 files associated with the tool. + """) + @maxItems(20) + file_ids?: string[] = #[]; + }; + + // Tool customization: use custom type for sophisticated union + file_search?: ToolResourcesFileSearchIdsOnly; + } | null; + + ...MetadataPropertyForResponse; + + /** What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. */ + @minValue(0) + @maxValue(2) + temperature?: float32 | null = 1; + + /** + * An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + * + * We generally recommend altering this or temperature but not both. + */ + @minValue(0) + @maxValue(1) + top_p?: float32 | null = 1; + + response_format?: AssistantsApiResponseFormatOption | null; +} + +/** Controls for how a thread will be truncated prior to the run. Use this to control the intial context window of the run. */ +model TruncationObject { + @doc(""" + The truncation strategy to use for the thread. The default is `auto`. If set to `last_messages`, the thread will be truncated to the n most recent messages in the thread. When set to `auto`, messages in the middle of the thread will be dropped to fit the context length of the model, `max_prompt_tokens`. + """) + type: "auto" | "last_messages"; + + /** The number of most recent messages from the thread when constructing the context for the run. */ + @minValue(1) + last_messages?: int32 | null; +} + +@doc(""" + Controls which (if any) tool is called by the model. + `none` means the model will not call any tools and instead generates a message. + `auto` is the default value and means the model can pick between generating a message or calling one or more tools. + `required` means the model must call one or more tools before responding to the user. + Specifying a particular tool like `{"type": "file_search"}` or `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. + """) +union AssistantsApiToolChoiceOption { + "none" | "auto" | "required", + AssistantsNamedToolChoice, +} + +/** Specifies a tool the model should use. Use to force the model to call a specific tool. */ +model AssistantsNamedToolChoice { + @doc(""" + The type of the tool. If type is `function`, the function name must be set + """) + type: "function" | "code_interpreter" | "file_search"; + + function?: { + /** The name of the function to call. */ + name: string; + }; +} + +union AssistantSupportedModels { + "gpt-4.1", + "gpt-4.1-mini", + "gpt-4.1-nano", + "gpt-4.1-2025-04-14", + "gpt-4.1-mini-2025-04-14", + "gpt-4.1-nano-2025-04-14", + "o3-mini", + "o3-mini-2025-01-31", + "o1", + "o1-2024-12-17", + "gpt-4o", + "gpt-4o-2024-11-20", + "gpt-4o-2024-08-06", + "gpt-4o-2024-05-13", + "gpt-4o-mini", + "gpt-4o-mini-2024-07-18", + "gpt-4.5-preview", + "gpt-4.5-preview-2025-02-27", + "gpt-4-turbo", + "gpt-4-turbo-2024-04-09", + "gpt-4-0125-preview", + "gpt-4-turbo-preview", + "gpt-4-1106-preview", + "gpt-4-vision-preview", + "gpt-4", + "gpt-4-0314", + "gpt-4-0613", + "gpt-4-32k", + "gpt-4-32k-0314", + "gpt-4-32k-0613", + "gpt-3.5-turbo", + "gpt-3.5-turbo-16k", + "gpt-3.5-turbo-0613", + "gpt-3.5-turbo-1106", + "gpt-3.5-turbo-0125", + "gpt-3.5-turbo-16k-0613", +} diff --git a/specification/base/typespec/assistants/operations.tsp b/specification/base/typespec/assistants/operations.tsp new file mode 100644 index 000000000..d42b8dbaa --- /dev/null +++ b/specification/base/typespec/assistants/operations.tsp @@ -0,0 +1,70 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("assistants") +@tag("Assistants") +interface Assistants { + @get + @operationId("listAssistants") + @summary("Returns a list of assistants.") + listAssistants( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + ...CommonPageQueryParameters, + ): ListAssistantsResponse | ErrorResponse; + + @post + @operationId("createAssistant") + @summary("Create an assistant with a model and instructions.") + createAssistant( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + @body requestBody: CreateAssistantRequest, + ): AssistantObject | ErrorResponse; + + @route("{assistant_id}") + @get + @operationId("getAssistant") + @summary("Retrieves an assistant.") + getAssistant( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the assistant to retrieve. */ + @path assistant_id: string, + ): AssistantObject | ErrorResponse; + + @route("{assistant_id}") + @post + @operationId("modifyAssistant") + @summary("Modifies an assistant.") + modifyAssistant( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the assistant to modify. */ + @path assistant_id: string, + + @body requestBody: ModifyAssistantRequest, + ): AssistantObject | ErrorResponse; + + @route("{assistant_id}") + @delete + @operationId("deleteAssistant") + @summary("Delete an assistant.") + deleteAssistant( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the assistant to delete. */ + @path assistant_id: string, + ): DeleteAssistantResponse | ErrorResponse; +} diff --git a/specification/base/typespec/audio/custom.tsp b/specification/base/typespec/audio/custom.tsp new file mode 100644 index 000000000..7f80f52d0 --- /dev/null +++ b/specification/base/typespec/audio/custom.tsp @@ -0,0 +1,17 @@ +import "./models.tsp"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union TranscriptionAudioResponseFormat { + AudioResponseFormat, +} + +union TranslationAudioResponseFormat { + AudioResponseFormat, +} + +@minValue(0) +@maxValue(1) +scalar ZeroOrOneFloat extends float32; diff --git a/specification/base/typespec/audio/main.tsp b/specification/base/typespec/audio/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/audio/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/audio/models.tsp b/specification/base/typespec/audio/models.tsp new file mode 100644 index 000000000..e7178f038 --- /dev/null +++ b/specification/base/typespec/audio/models.tsp @@ -0,0 +1,396 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../common"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from CreateTranscriptionResponseJson.logprobs +alias CreateTranscriptionResponseJsonLogprob = { + /** The token in the transcription. */ + token?: string; + + /** The log probability of the token. */ + logprob?: float32; + + /** The bytes of the token. */ + bytes?: float32[]; +}; + +// Tool generated type. Extracts from TranscriptTextDeltaEvent.logprobs +alias TranscriptTextDeltaEventLogprob = { + /** The token that was used to generate the log probability. */ + token?: string; + + /** The log probability of the token. */ + logprob?: float32; + + /** The bytes that were used to generate the log probability. */ + bytes?: int32[]; +}; + +// Tool generated type. Extracts from TranscriptTextDoneEvent.logprobs +alias TranscriptTextDoneEventLogprob = { + /** The token that was used to generate the log probability. */ + token?: string; + + /** The log probability of the token. */ + logprob?: float32; + + /** The bytes that were used to generate the log probability. */ + bytes?: int32[]; +}; + +@doc(""" + The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`. For `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`, the only supported format is `json`. + """) +union AudioResponseFormat { + "json", + "text", + "srt", + "verbose_json", + "vtt", +} + +model CreateSpeechRequest { + @doc(""" + One of the available [TTS models](/docs/models#tts): `tts-1`, `tts-1-hd` or `gpt-4o-mini-tts`. + """) + @extension("x-oaiTypeLabel", "string") + `model`: string | "tts-1" | "tts-1-hd" | "gpt-4o-mini-tts"; + + /** The text to generate audio for. The maximum length is 4096 characters. */ + @maxLength(4096) + input: string; + + @doc(""" + Control the voice of your generated audio with additional instructions. Does not work with `tts-1` or `tts-1-hd`. + """) + @maxLength(4096) + instructions?: string; + + @doc(""" + The voice to use when generating the audio. Supported voices are `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, and `verse`. Previews of the voices are available in the [Text to speech guide](/docs/guides/text-to-speech#voice-options). + """) + voice: VoiceIdsShared; + + @doc(""" + The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`. + """) + response_format?: "mp3" | "opus" | "aac" | "flac" | "wav" | "pcm" = "mp3"; + + @doc(""" + The speed of the generated audio. Select a value from `0.25` to `4.0`. `1.0` is the default. Does not work with `gpt-4o-mini-tts`. + """) + @minValue(0.25) + @maxValue(4) + speed?: float32 = 1; +} + +model CreateTranscriptionRequest { + // Tool customization: Apply HttpPart for property in multipart request model + /** The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. */ + @extension("x-oaiTypeLabel", "file") + file: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + ID of the model to use. The options are `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `whisper-1` (which is powered by our open source Whisper V2 model). + """) + @extension("x-oaiTypeLabel", "string") + `model`: HttpPart< + | string + | "whisper-1" + | "gpt-4o-transcribe" + | "gpt-4o-mini-transcribe">; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format will improve accuracy and latency. + """) + language?: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + /** An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text#prompting) should match the audio language. */ + prompt?: HttpPart; + + // Tool customization: Use scenario-specific composed union and apply HttpPart for property in multipart request model + response_format?: HttpPart; + + // Tool customization: Use scenario-specific composed union and apply HttpPart for property in multipart request model + /** The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. */ + temperature?: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + Additional information to include in the transcription response. + `logprobs` will return the log probabilities of the tokens in the + response to understand the model's confidence in the transcription. + `logprobs` only works with response_format set to `json` and only with + the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`. + """) + `include[]`?: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency. + """) + `timestamp_granularities[]`?: HttpPart<("word" | "segment")[]>; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + If set to true, the model response data will be streamed to the client + as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). + See the [Streaming section of the Speech-to-Text guide](/docs/guides/speech-to-text?lang=curl#streaming-transcriptions) + for more information. + + Note: Streaming is not supported for the `whisper-1` model and will be ignored. + """) + stream?: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + Controls how the audio is cut into chunks. When set to `"auto"`, the server first normalizes loudness and then uses voice activity detection (VAD) to choose boundaries. `server_vad` object can be provided to tweak VAD detection parameters manually. If unset, the audio is transcribed as a single block. + """) + @extension("x-oaiTypeLabel", "string") + chunking_strategy?: HttpPart; +} + +model CreateTranslationRequest { + // Tool customization: Apply HttpPart for property in multipart request model + /** The audio file object (not file name) translate, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm. */ + @extension("x-oaiTypeLabel", "file") + file: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + ID of the model to use. Only `whisper-1` (which is powered by our open source Whisper V2 model) is currently available. + """) + @extension("x-oaiTypeLabel", "string") + `model`: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + /** An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text#prompting) should be in English. */ + prompt?: HttpPart; + + // Tool customization: Use scenario-specific composed union and apply HttpPart for property in multipart request model + @doc(""" + The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`. + """) + response_format?: HttpPart; + + // Tool customization: Use scenario-specific composed union and apply HttpPart for property in multipart request model + /** The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit. */ + temperature?: HttpPart; +} + +/** Represents a transcription response returned by model, based on the provided input. */ +model CreateTranscriptionResponseJson { + /** The transcribed text. */ + text: string; + + @doc(""" + The log probabilities of the tokens in the transcription. Only returned with the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe` if `logprobs` is added to the `include` array. + """) + logprobs?: CreateTranscriptionResponseJsonLogprob[]; +} + +// Tool customization: Add a missing 'task' field, present on the wire but not in the spec +/** Represents a verbose json transcription response returned by model, based on the provided input. */ +model CreateTranscriptionResponseVerboseJson { + /** The task label. */ + task: "transcribe"; + + /** The language of the input audio. */ + language: string; + + // Tool customization: improve representation of float duration + /** The duration of the input audio. */ + @encode("seconds", float32) + duration: duration; + + /** The transcribed text. */ + text: string; + + /** Extracted words and their corresponding timestamps. */ + words?: TranscriptionWord[]; + + /** Segments of the transcribed text and their corresponding details. */ + segments?: TranscriptionSegment[]; +} + +model CreateTranslationResponseJson { + text: string; +} + +// Tool customization: Add a missing 'task' field, present on the wire but not in the spec +model CreateTranslationResponseVerboseJson { + /** The task label. */ + task: "translate"; + + @doc(""" + The language of the output translation (always `english`). + """) + language: string; + + // Tool customization: improve representation of float duration + /** The duration of the input audio. */ + @encode("seconds", float32) + duration: duration; + + /** The translated text. */ + text: string; + + /** Segments of the translated text and their corresponding details. */ + segments?: TranscriptionSegment[]; +} + +// Tool customization: Establish discriminated type hierarchy for transcription stream events +union CreateTranscriptionResponseStreamEventType { + string, + transcript_text_delta: "transcript.text.delta", + transcript_text_done: "transcript.text.done", +} +@discriminator("type") +model CreateTranscriptionResponseStreamEvent { + type: CreateTranscriptionResponseStreamEventType; +} + +model TranscriptionSegment { + /** Unique identifier of the segment. */ + id: int32; + + /** Seek offset of the segment. */ + seek: int32; + + // Tool customization: numeric timespans are encoded durations + /** Start time of the segment in seconds. */ + @encode("seconds", float32) + start: duration; + + // Tool customization: numeric timespans are encoded durations + /** End time of the segment in seconds. */ + @encode("seconds", float32) + end: duration; + + /** Text content of the segment. */ + text: string; + + /** Array of token IDs for the text content. */ + tokens: int32[]; + + /** Temperature parameter used for generating the segment. */ + temperature: float32; + + /** Average logprob of the segment. If the value is lower than -1, consider the logprobs failed. */ + avg_logprob: float32; + + /** Compression ratio of the segment. If the value is greater than 2.4, consider the compression failed. */ + compression_ratio: float32; + + @doc(""" + Probability of no speech in the segment. If the value is higher than 1.0 and the `avg_logprob` is below -1, consider this segment silent. + """) + no_speech_prob: float32; +} + +model TranscriptionWord { + /** The text content of the word. */ + word: string; + + // Tool customization: numeric timespans are encoded durations + /** Start time of the word in seconds. */ + @encode("seconds", float32) + start: duration; + + // Tool customization: numeric timespans are encoded durations + /** End time of the word in seconds. */ + @encode("seconds", float32) + end: duration; +} + +// Tool customization (apply_discriminator): Apply discriminated type base for transcription stream events +@doc(""" + Emitted when there is an additional text delta. This is also the first event emitted when the transcription starts. Only emitted when you [create a transcription](/docs/api-reference/audio/create-transcription) with the `Stream` parameter set to `true`. + """) +model TranscriptTextDeltaEvent extends CreateTranscriptionResponseStreamEvent { + @doc(""" + The type of the event. Always `transcript.text.delta`. + """) + type: CreateTranscriptionResponseStreamEventType.transcript_text_delta; + + /** The text delta that was additionally transcribed. */ + delta: string; + + @doc(""" + The log probabilities of the delta. Only included if you [create a transcription](/docs/api-reference/audio/create-transcription) with the `include[]` parameter set to `logprobs`. + """) + logprobs?: TranscriptTextDeltaEventLogprob[]; +} + +// Tool customization (apply_discriminator): Apply discriminated type base for transcription stream events +@doc(""" + Emitted when the transcription is complete. Contains the complete transcription text. Only emitted when you [create a transcription](/docs/api-reference/audio/create-transcription) with the `Stream` parameter set to `true`. + """) +model TranscriptTextDoneEvent extends CreateTranscriptionResponseStreamEvent { + @doc(""" + The type of the event. Always `transcript.text.done`. + """) + type: CreateTranscriptionResponseStreamEventType.transcript_text_done; + + /** The text that was transcribed. */ + text: string; + + @doc(""" + The log probabilities of the individual tokens in the transcription. Only included if you [create a transcription](/docs/api-reference/audio/create-transcription) with the `include[]` parameter set to `logprobs`. + """) + logprobs?: TranscriptTextDoneEventLogprob[]; +} + +union TranscriptionInclude { + "logprobs", +} + +@doc(""" + Controls how the audio is cut into chunks. When set to `"auto"`, the + server first normalizes loudness and then uses voice activity detection (VAD) to + choose boundaries. `server_vad` object can be provided to tweak VAD detection + parameters manually. If unset, the audio is transcribed as a single block. + """) +union TranscriptionChunkingStrategy { + "auto", + VadConfig, +} + +model VadConfig { + @doc(""" + Must be set to `server_vad` to enable manual chunking using server side VAD. + """) + type: "server_vad"; + + /** + * Amount of audio to include before the VAD detected speech (in + * milliseconds). + */ + prefix_padding_ms?: int32 = 300; + + /** + * Duration of silence to detect speech stop (in milliseconds). + * With shorter values the model will respond more quickly, + * but may jump in on short pauses from the user. + */ + silence_duration_ms?: int32 = 200; + + /** + * Sensitivity threshold (0.0 to 1.0) for voice activity detection. A + * higher threshold will require louder audio to activate the model, and + * thus might perform better in noisy environments. + */ + threshold?: float32 = 0.5; +} diff --git a/specification/base/typespec/audio/operations.tsp b/specification/base/typespec/audio/operations.tsp new file mode 100644 index 000000000..deba33022 --- /dev/null +++ b/specification/base/typespec/audio/operations.tsp @@ -0,0 +1,70 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/audio") +interface Audio { + @route("speech") + @post + @operationId("createSpeech") + @tag("Audio") + @summary("Generates audio from the input text.") + createSpeech( + @header accept: "application/octet-stream", + @body requestBody: CreateSpeechRequest, + ): { + /** chunked */ + @header("Transfer-Encoding") transferEncoding?: string; + + @header contentType: "application/octet-stream"; + @body responseBody: bytes; + }; + + @route("transcriptions") + @post + @operationId("createTranscription") + @tag("Audio") + @summary("Transcribes audio into the input language.") + createTranscription( + ...AcceptJsonOrEventStreamHeader, + @header contentType: "multipart/form-data", + @multipartBody requestBody: CreateTranscriptionRequest, + ): + | CreateTranscriptionResponseVerboseJson + | CreateTranscriptionResponseJson + | SseResponseOf + | { + // TODO: This response is not defined in the OpenAPI spec. + @header contentType: "text/plain"; + + @body responseBody: string; + } + | ErrorResponse; + + @route("translations") + @post + @operationId("createTranslation") + @tag("Audio") + @summary("Translates audio into English..") + createTranslation( + @header accept: "application/json", + @header contentType: "multipart/form-data", + @multipartBody requestBody: CreateTranslationRequest, + ): + | CreateTranslationResponseVerboseJson + | CreateTranslationResponseJson + | { + // TODO: This response is not defined in the OpenAPI spec. + @header contentType: "text/plain"; + + @body responseBody: string; + } + | ErrorResponse; +} diff --git a/specification/base/typespec/batch/main.tsp b/specification/base/typespec/batch/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/batch/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/batch/models.tsp b/specification/base/typespec/batch/models.tsp new file mode 100644 index 000000000..6baca754d --- /dev/null +++ b/specification/base/typespec/batch/models.tsp @@ -0,0 +1,184 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../common"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from Batch.errors.data +alias BatchErrorsData = { + /** An error code identifying the error type. */ + code?: string; + + /** A human-readable message providing more details about the error. */ + message?: string; + + /** The name of the parameter that caused the error, if applicable. */ + param?: string | null; + + /** The line number of the input file where the error occurred, if applicable. */ + line?: int32 | null; +}; + +model Batch { + id: string; + + @doc(""" + The object type, which is always `batch`. + """) + object: "batch"; + + /** The OpenAI API endpoint used by the batch. */ + endpoint: string; + + errors?: { + // Tool customization: add a clear enum enforcement of constrained 'object' label + @doc(""" + The object type, which is always `list`. + """) + object?: "list"; + + data?: BatchErrorsData[]; + }; + + /** The ID of the input file for the batch. */ + input_file_id: string; + + /** The time frame within which the batch should be processed. */ + completion_window: string; + + /** The current status of the batch. */ + status: + | "validating" + | "failed" + | "in_progress" + | "finalizing" + | "completed" + | "expired" + | "cancelling" + | "cancelled"; + + /** The ID of the file containing the outputs of successfully executed requests. */ + output_file_id?: string; + + /** The ID of the file containing the outputs of requests with errors. */ + error_file_id?: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the batch was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the batch started processing. */ + @encode("unixTimestamp", int32) + in_progress_at?: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the batch will expire. */ + @encode("unixTimestamp", int32) + expires_at?: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the batch started finalizing. */ + @encode("unixTimestamp", int32) + finalizing_at?: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the batch was completed. */ + @encode("unixTimestamp", int32) + completed_at?: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the batch failed. */ + @encode("unixTimestamp", int32) + failed_at?: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the batch expired. */ + @encode("unixTimestamp", int32) + expired_at?: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the batch started cancelling. */ + @encode("unixTimestamp", int32) + cancelling_at?: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the batch was cancelled. */ + @encode("unixTimestamp", int32) + cancelled_at?: utcDateTime; + + /** The request counts for different statuses within the batch. */ + request_counts?: { + /** Total number of requests in the batch. */ + total: int32; + + /** Number of requests that have been completed successfully. */ + completed: int32; + + /** Number of requests that have failed. */ + failed: int32; + }; + + ...MetadataPropertyForResponse; +} + +/** The per-line object of the batch input file */ +model BatchRequestInput { + /** A developer-provided per-request id that will be used to match outputs to inputs. Must be unique for each request in a batch. */ + custom_id?: string; + + @doc(""" + The HTTP method to be used for the request. Currently only `POST` is supported. + """) + method?: "POST"; + + // Tool customization: url uses the url type + @doc(""" + The OpenAI API relative URL to be used for the request. Currently `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported. + """) + url?: url; +} + +/** The per-line object of the batch output and error files */ +model BatchRequestOutput { + id?: string; + + /** A developer-provided per-request id that will be used to match outputs to inputs. */ + custom_id?: string; + + response?: { + /** The HTTP status code of the response */ + status_code?: int32; + + /** An unique identifier for the OpenAI API request. Please include this request ID when contacting support. */ + request_id?: string; + + /** The JSON body of the response */ + @extension("x-oaiTypeLabel", "map") + body?: Record; + } | null; + + /** For requests that failed with a non-HTTP error, this will contain more information on the cause of the failure. */ + error?: { + /** A machine-readable error code. */ + code?: string; + + /** A human-readable error message. */ + message?: string; + } | null; +} + +model ListBatchesResponse { + data: Batch[]; + first_id?: string; + last_id?: string; + has_more: boolean; + object: "list"; +} diff --git a/specification/base/typespec/batch/operations.tsp b/specification/base/typespec/batch/operations.tsp new file mode 100644 index 000000000..dfc7508da --- /dev/null +++ b/specification/base/typespec/batch/operations.tsp @@ -0,0 +1,90 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/batches") +interface Batches { + @post + @operationId("createBatch") + @tag("Batch") + @summary("Creates and executes a batch from an uploaded file of requests") + createBatch( + @header accept: "application/json", + + /** + * The ID of an uploaded file that contains requests for the new batch. + * + * See [upload file](/docs/api-reference/files/create) for how to upload a file. + * + * Your input file must be formatted as a [JSONL file](/docs/api-reference/batch/requestInput), + * and must be uploaded with the purpose `batch`. + */ + input_file_id: string, + + /** + * The endpoint to be used for all requests in the batch. Currently `/v1/chat/completions` and + * `/v1/embeddings` are supported. + */ + endpoint: "/v1/chat/completions" | "/v1/embeddings", + + /** + * The time frame within which the batch should be processed. Currently only `24h` is supported. + */ + completion_window: "24h", + + /** Optional custom metadata for the batch. */ + ...MetadataPropertyForRequest, + ): Batch | ErrorResponse; + + @get + @operationId("listBatches") + @tag("Batch") + @summary("List your organization's batches.") + listBatches( + @header accept: "application/json", + + /** + * A cursor for use in pagination. `after` is an object ID that defines your place in the list. + * For instance, if you make a list request and receive 100 objects, ending with obj_foo, your + * subsequent call can include after=obj_foo in order to fetch the next page of the list. + */ + @query after?: string, + + /** + * A limit on the number of objects to be returned. Limit can range between 1 and 100, and the + * default is 20. + */ + @query limit?: int32 = 20, + ): ListBatchesResponse | ErrorResponse; + + @route("{batch_id}") + @get + @operationId("retrieveBatch") + @tag("Batch") + @summary("Retrieves a batch.") + retrieveBatch( + @header accept: "application/json", + + /** The ID of the batch to retrieve. */ + @path batch_id: string, + ): Batch | ErrorResponse; + + @route("{batch_id}/cancel") + @post + @operationId("cancelBatch") + @tag("Batch") + @summary("Cancels an in-progress batch.") + cancelBatch( + @header accept: "application/json", + + /** The ID of the batch to cancel. */ + @path batch_id: string, + ): Batch | ErrorResponse; +} diff --git a/specification/base/typespec/chat/custom.tsp b/specification/base/typespec/chat/custom.tsp new file mode 100644 index 000000000..befdcfeae --- /dev/null +++ b/specification/base/typespec/chat/custom.tsp @@ -0,0 +1,54 @@ +import "../common"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union ChatOutputPredictionType { + string, + static_content: "content", +} + +/** + * Base representation of predicted output from a model. + */ +@discriminator("type") +model ChatOutputPrediction { + type: ChatOutputPredictionType; +} + +model ChatCompletionFunctionChoice {} + +model ChatCompletionToolChoice {} + +union ChatCompletionRequestMessageContentPartType { + text: "text", + file: "file", + input_audio: "input_audio", + image_url: "image_url", + refusal: "refusal", +} + +@discriminator("type") +model ChatCompletionRequestMessageContentPart { + type: ChatCompletionRequestMessageContentPartType; +} + +model ChatCompletionMessageAudioChunk { + id?: string; + transcript?: string; + + @encode("base64") + data?: bytes; + + @encode("unixTimestamp", int32) + expires_at?: utcDateTime; +} + +enum ChatToolKind { + function, +} + +enum ChatToolCallKind { + function, +} diff --git a/specification/base/typespec/chat/main.tsp b/specification/base/typespec/chat/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/chat/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/chat/models.tsp b/specification/base/typespec/chat/models.tsp new file mode 100644 index 000000000..7eb299190 --- /dev/null +++ b/specification/base/typespec/chat/models.tsp @@ -0,0 +1,982 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../common"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from CreateChatCompletionResponse.choices +alias CreateChatCompletionResponseChoice = { + @doc(""" + The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, + `length` if the maximum number of tokens specified in the request was reached, + `content_filter` if content was omitted due to a flag from our content filters, + `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. + """) + finish_reason: + | "stop" + | "length" + | "tool_calls" + | "content_filter" + | "function_call"; + + /** The index of the choice in the list of choices. */ + index: int32; + + message: ChatCompletionResponseMessage; + + /** Log probability information for the choice. */ + logprobs: { + // Tool customization: Apply read-only visibility via annotation + /** A list of message content tokens with log probability information. */ + @visibility(Lifecycle.Read) + content: ChatCompletionTokenLogprob[] | null; + + // Tool customization: Apply read-only visibility via annotation + /** A list of message refusal tokens with log probability information. */ + @visibility(Lifecycle.Read) + refusal: ChatCompletionTokenLogprob[] | null; + } | null; +}; + +// Tool generated type. Extracts from ChatCompletionResponseMessage.annotations +alias ChatCompletionResponseMessageAnnotation = { + @doc(""" + The type of the URL citation. Always `url_citation`. + """) + type: "url_citation"; + + /** A URL citation when using web search. */ + url_citation: { + /** The index of the last character of the URL citation in the message. */ + end_index: int32; + + /** The index of the first character of the URL citation in the message. */ + start_index: int32; + + // Tool customization: url uses the url type + /** The URL of the web resource. */ + url: url; + + /** The title of the web resource. */ + title: string; + }; +}; + +// Tool generated type. Extracts from ChatCompletionTokenLogprob.top_logprobs +alias ChatCompletionTokenLogprobTopLogprob = { + /** The token. */ + token: string; + + @doc(""" + The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. + """) + logprob: float32; + + @doc(""" + A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. + """) + bytes: int32[] | null; +}; + +// Tool generated type. Extracts from CreateChatCompletionStreamResponse.choices +alias CreateChatCompletionStreamResponseChoice = { + delta: ChatCompletionStreamResponseDelta; + + /** Log probability information for the choice. */ + logprobs?: { + // Tool customization: Apply read-only visibility via annotation + /** A list of message content tokens with log probability information. */ + @visibility(Lifecycle.Read) + content: ChatCompletionTokenLogprob[] | null; + + // Tool customization: Apply read-only visibility via annotation + /** A list of message refusal tokens with log probability information. */ + @visibility(Lifecycle.Read) + refusal: ChatCompletionTokenLogprob[] | null; + } | null; + + @doc(""" + The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, + `length` if the maximum number of tokens specified in the request was reached, + `content_filter` if content was omitted due to a flag from our content filters, + `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. + """) + finish_reason: + | "stop" + | "length" + | "tool_calls" + | "content_filter" + | "function_call" + | null; + + /** The index of the choice in the list of choices. */ + index: int32; +}; + +// Tool generated type. Extracts from ChatCompletionMessageList.data +alias ChatCompletionMessageListData = { + ...ChatCompletionResponseMessage; + + /** The identifier of the chat message. */ + id: string; +}; + +model CreateChatCompletionRequest { + ...ModelResponsePropertiesForRequest; + + /** + * A list of messages comprising the conversation so far. Depending on the + * [model](/docs/models) you use, different message types (modalities) are + * supported, like [text](/docs/guides/text-generation), + * [images](/docs/guides/vision), and [audio](/docs/guides/audio). + */ + @minItems(1) + messages: ChatCompletionRequestMessage[]; + + @doc(""" + Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI + offers a wide range of models with different capabilities, performance + characteristics, and price points. Refer to the [model guide](/docs/models) + to browse and compare available models. + """) + `model`: ModelIdsShared; + + modalities?: ResponseModalities | null; + reasoning_effort?: ReasoningEffort | null = "medium"; + + /** An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). */ + max_completion_tokens?: int32 | null; + + /** + * Number between -2.0 and 2.0. Positive values penalize new tokens based on + * their existing frequency in the text so far, decreasing the model's + * likelihood to repeat the same line verbatim. + */ + @minValue(-2) + @maxValue(2) + frequency_penalty?: float32 | null = 0; + + /** + * Number between -2.0 and 2.0. Positive values penalize new tokens based on + * whether they appear in the text so far, increasing the model's likelihood + * to talk about new topics. + */ + @minValue(-2) + @maxValue(2) + presence_penalty?: float32 | null = 0; + + /** + * This tool searches the web for relevant results to use in a response. + * Learn more about the [web search tool](/docs/guides/tools-web-search?api-mode=chat). + */ + web_search_options?: { + /** Approximate location parameters for the search. */ + user_location?: { + @doc(""" + The type of location approximation. Always `approximate`. + """) + type: "approximate"; + + approximate: WebSearchLocation; + } | null; + + search_context_size?: WebSearchContextSize = "medium"; + }; + + @doc(""" + An integer between 0 and 20 specifying the number of most likely tokens to + return at each token position, each with an associated log probability. + `logprobs` must be set to `true` if this parameter is used. + """) + @minValue(0) + @maxValue(20) + top_logprobs?: int32 | null; + + // Tool customization: apply a named union type + @doc(""" + An object specifying the format that the model must output. + + Setting to `{ "type": "json_schema", "json_schema": {...} }` enables + Structured Outputs which ensures the model will match your supplied JSON + schema. Learn more in the [Structured Outputs + guide](/docs/guides/structured-outputs). + + Setting to `{ "type": "json_object" }` enables the older JSON mode, which + ensures the message the model generates is valid JSON. Using `json_schema` + is preferred for models that support it. + """) + response_format?: ResponseFormat; + + @doc(""" + Parameters for audio output. Required when audio output is requested with + `modalities: ["audio"]`. [Learn more](/docs/guides/audio). + """) + audio?: { + @doc(""" + The voice the model uses to respond. Supported voices are + `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `nova`, `onyx`, `sage`, and `shimmer`. + """) + voice: VoiceIdsShared; + + @doc(""" + Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`, + `opus`, or `pcm16`. + """) + format: "wav" | "aac" | "mp3" | "flac" | "opus" | "pcm16"; + } | null; + + /** + * Whether or not to store the output of this chat completion request for + * use in our [model distillation](/docs/guides/distillation) or + * [evals](/docs/guides/evals) products. + */ + store?: boolean | null = false; + + /** + * If set to true, the model response data will be streamed to the client + * as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). + * See the [Streaming section below](/docs/api-reference/chat/streaming) + * for more information, along with the [streaming responses](/docs/guides/streaming-responses) + * guide for more information on how to handle the streaming events. + */ + stream?: boolean | null = false; + + stop?: StopConfiguration | null = null; + + /** + * Modify the likelihood of specified tokens appearing in the completion. + * + * Accepts a JSON object that maps tokens (specified by their token ID in the + * tokenizer) to an associated bias value from -100 to 100. Mathematically, + * the bias is added to the logits generated by the model prior to sampling. + * The exact effect will vary per model, but values between -1 and 1 should + * decrease or increase likelihood of selection; values like -100 or 100 + * should result in a ban or exclusive selection of the relevant token. + */ + @extension("x-oaiTypeLabel", "map") + logit_bias?: Record | null = null; + + @doc(""" + Whether to return log probabilities of the output tokens or not. If true, + returns the log probabilities of each output token returned in the + `content` of `message`. + """) + logprobs?: boolean | null = false; + + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @doc(""" + The maximum number of [tokens](/tokenizer) that can be generated in the + chat completion. This value can be used to control + [costs](https://openai.com/api/pricing/) for text generated via API. + + This value is now deprecated in favor of `max_completion_tokens`, and is + not compatible with [o-series models](/docs/guides/reasoning). + """) + max_tokens?: int32 | null; + + @doc(""" + How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. + """) + @minValue(1) + @maxValue(128) + n?: int32 | null = 1; + + // Tool customization: Apply an implied base discriminated type to 'prediction' + /** + * Configuration for a [Predicted Output](/docs/guides/predicted-outputs), + * which can greatly improve response times when large parts of the model + * response are known ahead of time. This is most common when you are + * regenerating a file with only minor changes to most of the content. + */ + prediction?: ChatOutputPrediction | null; + + @doc(""" + This feature is in Beta. + If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. + Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. + """) + @minValue(-9223372036854776000) + @maxValue(9223372036854776000) + seed?: int64 | null; + + stream_options?: ChatCompletionStreamOptions | null = null; + + /** A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. */ + tools?: ChatCompletionTool[]; + + tool_choice?: ChatCompletionToolChoiceOption; + parallel_tool_calls?: ParallelToolCalls = true; + + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @doc(""" + Deprecated in favor of `tool_choice`. + + Controls which (if any) function is called by the model. + + `none` means the model will not call a function and instead generates a + message. + + `auto` means the model can pick between generating a message or calling a + function. + + Specifying a particular function via `{"name": "my_function"}` forces the + model to call that function. + + `none` is the default when no functions are present. `auto` is the default + if functions are present. + """) + function_call?: "none" | "auto" | ChatCompletionFunctionCallOption; + + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @doc(""" + Deprecated in favor of `tools`. + + A list of functions the model may generate JSON inputs for. + """) + @minItems(1) + @maxItems(128) + functions?: ChatCompletionFunctions[]; +} + +/** Represents a chat completion response returned by model, based on the provided input. */ +model CreateChatCompletionResponse { + /** A unique identifier for the chat completion. */ + id: string; + + @doc(""" + A list of chat completion choices. Can be more than one if `n` is greater than 1. + """) + choices: CreateChatCompletionResponseChoice[]; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the chat completion was created. */ + @encode("unixTimestamp", int32) + created: utcDateTime; + + /** The model used for the chat completion. */ + `model`: string; + + service_tier?: ServiceTier | null = "auto"; + + @doc(""" + This fingerprint represents the backend configuration that the model runs with. + + Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. + """) + system_fingerprint?: string; + + @doc(""" + The object type, which is always `chat.completion`. + """) + object: "chat.completion"; + + usage?: CompletionUsage; +} + +model ChatCompletionTool { + // Tool customization: Use enum instead of string constants to maintain backwards compatibility + @doc(""" + The type of the tool. Currently, only `function` is supported. + """) + type: ChatToolKind.function; + + function: FunctionObject; +} + +/** Specifies a tool the model should use. Use to force the model to call a specific function. */ +model ChatCompletionNamedToolChoice { + @doc(""" + The type of the tool. Currently, only `function` is supported. + """) + type: "function"; + + function: { + /** The name of the function to call. */ + name: string; + }; +} + +@doc(""" + Controls which (if any) tool is called by the model. + `none` means the model will not call any tool and instead generates a message. + `auto` means the model can pick between generating a message or calling one or more tools. + `required` means the model must call one or more tools. + Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. + + `none` is the default when no tools are present. `auto` is the default if tools are present. + """) +union ChatCompletionToolChoiceOption { + "none" | "auto" | "required", + ChatCompletionNamedToolChoice, +} + +// Tool customization (apply_discriminator): apply custom, discriminated type base +/** Learn about [text inputs](/docs/guides/text-generation). */ +model ChatCompletionRequestMessageContentPartText + extends ChatCompletionRequestMessageContentPart { + /** The type of the content part. */ + type: ChatCompletionRequestMessageContentPartType.text; + + /** The text content. */ + text: string; +} + +// Tool customization (apply_discriminator): apply custom, discriminated type base +/** Learn about [image inputs](/docs/guides/vision). */ +model ChatCompletionRequestMessageContentPartImage + extends ChatCompletionRequestMessageContentPart { + /** The type of the content part. */ + type: ChatCompletionRequestMessageContentPartType.image_url; + + image_url: { + // Tool customization: url uses the url type + /** Either a URL of the image or the base64 encoded image data. */ + url: url; + + /** Specifies the detail level of the image. Learn more in the [Vision guide](/docs/guides/vision#low-or-high-fidelity-image-understanding). */ + detail?: "auto" | "low" | "high" = "auto"; + }; +} + +// Tool customization (apply_discriminator): apply custom, discriminated type base +model ChatCompletionRequestMessageContentPartRefusal + extends ChatCompletionRequestMessageContentPart { + /** The type of the content part. */ + type: ChatCompletionRequestMessageContentPartType.refusal; + + /** The refusal message generated by the model. */ + refusal: string; +} + +// Tool customization (apply_discriminator): apply custom, discriminated type base +/** Learn about [file inputs](/docs/guides/text) for text generation. */ +model ChatCompletionRequestMessageContentPartFile + extends ChatCompletionRequestMessageContentPart { + @doc(""" + The type of the content part. Always `file`. + """) + type: ChatCompletionRequestMessageContentPartType.file; + + file: { + /** + * The name of the file, used when passing the file to the model as a + * string. + */ + filename?: string; + + /** + * The base64 encoded file data, used when passing the file to the model + * as a string. + */ + file_data?: string; + + /** The ID of an uploaded file to use as input. */ + file_id?: string; + }; +} + +model ChatCompletionMessageToolCall { + /** The ID of the tool call. */ + id: string; + + // Tool customization: Use enum instead of string constants to maintain backwards compatibility + @doc(""" + The type of the tool. Currently, only `function` is supported. + """) + type: ChatToolCallKind.function; + + /** The function that the model called. */ + function: { + /** The name of the function to call. */ + name: string; + + /** The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. */ + arguments: string; + }; +} + +// Tool customization: convert to discriminated type +@discriminator("role") +model ChatCompletionRequestMessage { + /** The role of the author of this message. */ + role: ChatCompletionRole; + + /** The content of the message. Valid content part types vary per message role. */ + content?: string | ChatCompletionRequestMessageContentPart[] | null; +} + +// Tool customization (apply_discriminator): apply custom, discriminated type base +/** Learn about [audio inputs](/docs/guides/audio). */ +model ChatCompletionRequestMessageContentPartAudio + extends ChatCompletionRequestMessageContentPart { + @doc(""" + The type of the content part. Always `input_audio`. + """) + type: ChatCompletionRequestMessageContentPartType.input_audio; + + input_audio: { + // Tool customization: use encoded type for audio data + /** Base64 encoded audio data. */ + @encode("base64") + data: bytes; + + /** The format of the encoded audio data. Currently supports "wav" and "mp3". */ + format: "wav" | "mp3"; + }; +} + +union ChatCompletionRequestSystemMessageContentPart { + ChatCompletionRequestMessageContentPartText, +} + +union ChatCompletionRequestUserMessageContentPart { + ChatCompletionRequestMessageContentPartText, + ChatCompletionRequestMessageContentPartImage, + ChatCompletionRequestMessageContentPartAudio, + ChatCompletionRequestMessageContentPartFile, +} + +union ChatCompletionRequestAssistantMessageContentPart { + ChatCompletionRequestMessageContentPartText, + ChatCompletionRequestMessageContentPartRefusal, +} + +union ChatCompletionRequestToolMessageContentPart { + ChatCompletionRequestMessageContentPartText, +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + Developer-provided instructions that the model should follow, regardless of + messages sent by the user. With o1 models and newer, use `developer` messages + for this purpose instead. + """) +model ChatCompletionRequestSystemMessage extends ChatCompletionRequestMessage { + /** The contents of the system message. */ + content: string | ChatCompletionRequestSystemMessageContentPart[]; + + @doc(""" + The role of the messages author, in this case `system`. + """) + role: ChatCompletionRole.system; + + /** An optional name for the participant. Provides the model information to differentiate between participants of the same role. */ + name?: string; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + Developer-provided instructions that the model should follow, regardless of + messages sent by the user. With o1 models and newer, `developer` messages + replace the previous `system` messages. + """) +model ChatCompletionRequestDeveloperMessage + extends ChatCompletionRequestMessage { + /** The contents of the developer message. */ + content: string | ChatCompletionRequestMessageContentPartText[]; + + @doc(""" + The role of the messages author, in this case `developer`. + """) + role: ChatCompletionRole.developer; + + /** An optional name for the participant. Provides the model information to differentiate between participants of the same role. */ + name?: string; +} + +// Tool customization (apply_discriminator): apply discriminated type base +/** + * Messages sent by an end user, containing prompts or additional context + * information. + */ +model ChatCompletionRequestUserMessage extends ChatCompletionRequestMessage { + /** The contents of the user message. */ + content: string | ChatCompletionRequestUserMessageContentPart[]; + + @doc(""" + The role of the messages author, in this case `user`. + """) + role: ChatCompletionRole.user; + + /** An optional name for the participant. Provides the model information to differentiate between participants of the same role. */ + name?: string; +} + +// Tool customization (apply_discriminator): apply discriminated type base +/** Messages sent by the model in response to user messages. */ +model ChatCompletionRequestAssistantMessage + extends ChatCompletionRequestMessage { + @doc(""" + The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. + """) + content?: string | ChatCompletionRequestAssistantMessageContentPart[] | null; + + /** The refusal message by the assistant. */ + refusal?: string | null; + + @doc(""" + The role of the messages author, in this case `assistant`. + """) + role: ChatCompletionRole.assistant; + + /** An optional name for the participant. Provides the model information to differentiate between participants of the same role. */ + name?: string; + + /** + * Data about a previous audio response from the model. + * [Learn more](/docs/guides/audio). + */ + audio?: { + /** Unique identifier for a previous audio response from the model. */ + id: string; + } | null; + + tool_calls?: ChatCompletionMessageToolCalls; + + // Tool customization: preserve earlier, more intuitive field order + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @doc(""" + Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. + """) + function_call?: { + name: string; + arguments: string; + } | null; +} + +// Tool customization (apply_discriminator): apply discriminated type base +model ChatCompletionRequestToolMessage extends ChatCompletionRequestMessage { + @doc(""" + The role of the messages author, in this case `tool`. + """) + role: ChatCompletionRole.tool; + + /** The contents of the tool message. */ + content: string | ChatCompletionRequestToolMessageContentPart[]; + + /** Tool call that this message is responding to. */ + tool_call_id: string; +} + +// Tool customization (apply_discriminator): apply discriminated type base +#suppress "deprecated" "Warning unnecessary for spec description of deprecation" +#deprecated "This field is marked as deprecated." +model ChatCompletionRequestFunctionMessage + extends ChatCompletionRequestMessage { + @doc(""" + The role of the messages author, in this case `function`. + """) + role: ChatCompletionRole.function; + + /** The contents of the function message. */ + content: string | null; + + /** The name of the function to call. */ + name: string; +} + +/** The tool calls generated by the model, such as function calls. */ +model ChatCompletionMessageToolCalls is ChatCompletionMessageToolCall[]; + +@doc(""" + Output types that you would like the model to generate for this request. + Most models are capable of generating text, which is the default: + + `["text"]` + + The `gpt-4o-audio-preview` model can also be used to [generate audio](/docs/guides/audio). To + request that this model generate both text and audio responses, you can + use: + + `["text", "audio"]` + """) +model ChatCompletionModalities is ("text" | "audio")[]; + +// Tool customization: convert to enum +/** The role of the author of a message */ +enum ChatCompletionRole { + system, + developer, + user, + assistant, + tool, + function, +} + +/** A chat completion message generated by the model. */ +model ChatCompletionResponseMessage { + /** The contents of the message. */ + content: string | null; + + /** The refusal message generated by the model. */ + refusal: string | null; + + tool_calls?: ChatCompletionMessageToolCalls; + + /** + * Annotations for the message, when applicable, as when using the + * [web search tool](/docs/guides/tools-web-search?api-mode=chat). + */ + annotations?: ChatCompletionResponseMessageAnnotation[]; + + // Tool customization: use discriminated type base for role + /** The role of the author of this message. */ + role: ChatCompletionRole.assistant; + + // Tool customization: preserve earlier, more intuitive field order + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @doc(""" + Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. + """) + function_call?: { + name: string; + arguments: string; + }; + + /** + * If the audio output modality is requested, this object contains data + * about the audio response from the model. [Learn more](/docs/guides/audio). + */ + audio?: { + /** Unique identifier for this audio response. */ + id: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** + * The Unix timestamp (in seconds) for when this audio response will + * no longer be accessible on the server for use in multi-turn + * conversations. + */ + @encode("unixTimestamp", int32) + expires_at: utcDateTime; + + // Tool customization: use encoded type for audio data + /** + * Base64 encoded audio bytes generated by the model, in the format + * specified in the request. + */ + @encode("base64") + data: bytes; + + /** Transcript of the audio generated by the model. */ + transcript: string; + } | null; +} + +model ChatCompletionTokenLogprob { + /** The token. */ + token: string; + + @doc(""" + The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. + """) + logprob: float32; + + @doc(""" + A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. + """) + bytes: int32[] | null; + + @doc(""" + List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested `top_logprobs` returned. + """) + top_logprobs: ChatCompletionTokenLogprobTopLogprob[]; +} + +@doc(""" + Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. + """) +model ChatCompletionFunctionCallOption { + /** The name of the function to call. */ + name: string; +} + +#suppress "deprecated" "Warning unnecessary for spec description of deprecation" +#deprecated "This field is marked as deprecated." +model ChatCompletionFunctions { + /** A description of what the function does, used by the model to choose when and how to call the function. */ + description?: string; + + /** The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. */ + name: string; + + ...FunctionParametersCommon; +} + +// Tool customization: Add a missing "audio" to the chat streaming delta definition +/** A chat completion delta generated by streamed model responses. */ +model ChatCompletionStreamResponseDelta { + /** Response audio associated with the streaming chat delta payload. */ + audio?: ChatCompletionMessageAudioChunk; + + /** The contents of the chunk message. */ + content?: string | null; + + // Tool customization: preserve earlier, more intuitive field order + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @doc(""" + Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. + """) + function_call?: { + name?: string; + arguments?: string; + }; + + tool_calls?: ChatCompletionMessageToolCallChunk[]; + + // Tool customization: use discriminated type base for role + /** The role of the author of this message. */ + role?: ChatCompletionRole; + + /** The refusal message generated by the model. */ + refusal?: string | null; +} + +model ChatCompletionMessageToolCallChunk { + index: int32; + + /** The ID of the tool call. */ + id?: string; + + @doc(""" + The type of the tool. Currently, only `function` is supported. + """) + type?: "function"; + + function?: { + /** The name of the function to call. */ + name?: string; + + /** The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. */ + arguments?: string; + }; +} + +/** + * Represents a streamed chunk of a chat completion response returned + * by the model, based on the provided input. + * [Learn more](/docs/guides/streaming-responses). + */ +model CreateChatCompletionStreamResponse { + /** A unique identifier for the chat completion. Each chunk has the same ID. */ + id: string; + + @doc(""" + A list of chat completion choices. Can contain more than one elements if `n` is greater than 1. Can also be empty for the + last chunk if you set `stream_options: {"include_usage": true}`. + """) + choices: CreateChatCompletionStreamResponseChoice[]; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. */ + @encode("unixTimestamp", int32) + created: utcDateTime; + + /** The model to generate the completion. */ + `model`: string; + + service_tier?: ServiceTier | null = "auto"; + + @doc(""" + This fingerprint represents the backend configuration that the model runs with. + Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. + """) + system_fingerprint?: string; + + @doc(""" + The object type, which is always `chat.completion.chunk`. + """) + object: "chat.completion.chunk"; + + @doc(""" + An optional field that will only be present when you set + `stream_options: {"include_usage": true}` in your request. When present, it + contains a null value **except for the last chunk** which contains the + token usage statistics for the entire request. + + **NOTE:** If the stream is interrupted or cancelled, you may not + receive the final usage chunk which contains the total token usage for + the request. + """) + usage?: CompletionUsage | null; +} + +// Tool customization (apply_discriminator): Apply an implied base discriminated type to 'prediction' +/** + * Static predicted output content, such as the content of a text file that is + * being regenerated. + */ +model ChatOutputPredictionContent extends ChatOutputPrediction { + @doc(""" + The type of the predicted content you want to provide. This type is + currently always `content`. + """) + type: ChatOutputPredictionType.static_content; + + /** + * The content that should be matched when generating a model response. + * If generated tokens would match this content, the entire model response + * can be returned much more quickly. + */ + content: string | ChatCompletionRequestMessageContentPartText[]; +} + +model ChatCompletionDeleted { + /** The type of object being deleted. */ + object: "chat.completion.deleted"; + + /** The ID of the chat completion that was deleted. */ + id: string; + + /** Whether the chat completion was deleted. */ + deleted: boolean; +} + +/** An object representing a list of Chat Completions. */ +model ChatCompletionList { + /** The type of this object. It is always set to "list". */ + object: "list" = "list"; + + /** An array of chat completion objects. */ + @pageItems data: CreateChatCompletionResponse[]; + + /** The identifier of the first chat completion in the data array. */ + first_id: string; + + /** The identifier of the last chat completion in the data array. */ + @continuationToken last_id: string; + + /** Indicates whether there are more Chat Completions available. */ + has_more: boolean; +} + +/** An object representing a list of chat completion messages. */ +model ChatCompletionMessageList { + /** The type of this object. It is always set to "list". */ + object: "list" = "list"; + + /** An array of chat completion message objects. */ + @pageItems data: ChatCompletionMessageListData[]; + + /** The identifier of the first chat message in the data array. */ + first_id: string; + + /** The identifier of the last chat message in the data array. */ + @continuationToken last_id: string; + + /** Indicates whether there are more chat messages available. */ + has_more: boolean; +} diff --git a/specification/base/typespec/chat/operations.tsp b/specification/base/typespec/chat/operations.tsp new file mode 100644 index 000000000..d565152fc --- /dev/null +++ b/specification/base/typespec/chat/operations.tsp @@ -0,0 +1,90 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("chat/completions") +@tag("Chat") +interface Chat { + @get + @operationId("listChatCompletions") + @summary("Returns a list of chat completions.") + @list + listChatCompletions( + ...PageAfterQueryParameter, + ...PageLimitQueryParameter, + ...PageOrderQueryParameter, + @query metadata?: Record, + @query `model`?: string, + ): ChatCompletionList | ErrorResponse; + + @post + @operationId("createChatCompletion") + @summary("Creates a model response for the given chat conversation.") + createChatCompletion( + @header accept: "application/json", + @body requestBody: CreateChatCompletionRequest, + ): CreateChatCompletionResponse | SseResponseOf | ErrorResponse; + + @get + @route("{completion_id}") + @operationId("getChatCompletion") + @summary(""" + Get a stored chat completion. Only Chat Completions that have been created with the `store` parameter set to `true` will be returned. + """) + getChatCompletion( + /** The ID of the stored chat completion to retrieve. */ + @path completion_id: string, + ): CreateChatCompletionResponse | ErrorResponse; + + @post + @route("{completion_id}") + @operationId("updateChatCompletion") + @summary(""" + Modify a stored chat completion. Only Chat Completions that have been created with the `store` parameter set to `true` can be modified. Currently, the only supported modification is to update the `metadata` field.") + """) + updateChatCompletion( + /** The ID of the stored chat completion to update. */ + @path completion_id: string, + + /** + * Set of 16 key-value pairs that can be attached to an object. This can be + * useful for storing additional information about the object in a structured + * format, and querying for objects via API or the dashboard. + * + * Keys are strings with a maximum length of 64 characters. Values are strings + * with a maximum length of 512 characters. + */ + @extension("x-oaiTypeLabel", "map") + metadata: Record; + ): CreateChatCompletionResponse | ErrorResponse; + + @delete + @route("{completion_id}") + @operationId("deleteChatCompletion") + @summary("Delete a stored chat completion. Only Chat Completions that have been created with the `store` parameter set to `true` can be deleted.") + deleteChatCompletion( + /** The ID of the stored chat completion to delete. */ + @path completion_id: string, + ): ChatCompletionDeleted | ErrorResponse; + + @get + @route("{completion_id}/messages") + @operationId("getChatCompletionMessages") + @summary("Get the messages of a stored chat completion. Only Chat Completions that have been created with the `store` parameter set to `true` will be returned.") + @list + getChatCompletionMessages( + /** The ID of the stored chat completion to retrieve messages for. */ + @path completion_id: string, + + ...PageAfterQueryParameter, + ...PageLimitQueryParameter, + ...PageOrderQueryParameter, + ): ChatCompletionMessageList | ErrorResponse; +} diff --git a/specification/base/typespec/common/custom.tsp b/specification/base/typespec/common/custom.tsp new file mode 100644 index 000000000..4af4b46bb --- /dev/null +++ b/specification/base/typespec/common/custom.tsp @@ -0,0 +1,75 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@discriminator("type") +model ResponseFormat { + type: "text" | "json_object" | "json_schema"; +} + +alias AcceptJsonHeader = { + @header accept: "application/json"; +}; + +alias AcceptJsonOrEventStreamHeader = { + @header accept: "application/json" | "text/event-stream"; +}; + +alias AssistantsBetaHeader = { + @header("OpenAI-Beta") openAIBeta: "assistants=v2"; +}; + +alias PageLimitQueryParameter = { + /** + * A limit on the number of objects to be returned. Limit can range between 1 and 100, and the + * default is 20. + */ + @query limit?: int32 = 20; +}; + +alias PageOrderQueryParameter = { + /** + * Sort order by the `created_at` timestamp of the objects. `asc` for ascending order and`desc` + * for descending order. + */ + @query order?: PageOrderOptions; +}; + +enum PageOrderOptions { + asc, + desc, +} + +alias PageAfterQueryParameter = { + /** + * A cursor for use in pagination. `after` is an object ID that defines your place in the list. + * For instance, if you make a list request and receive 100 objects, ending with obj_foo, your + * subsequent call can include after=obj_foo in order to fetch the next page of the list. + */ + @query @continuationToken after?: string; +}; + +alias PageBeforeQueryParameter = { + /** + * A cursor for use in pagination. `before` is an object ID that defines your place in the list. + * For instance, if you make a list request and receive 100 objects, ending with obj_foo, your + * subsequent call can include before=obj_foo in order to fetch the previous page of the list. + */ + @query before?: string; +}; + +alias CommonPageQueryParameters = { + ...PageLimitQueryParameter; + ...PageOrderQueryParameter; + ...PageAfterQueryParameter; + ...PageBeforeQueryParameter; +}; + +alias SseResponseOf = { + @header("Content-Type") contentType: "text/event-stream"; + @body responseBody: T; +}; diff --git a/specification/base/typespec/common/main.tsp b/specification/base/typespec/common/main.tsp new file mode 100644 index 000000000..223114fb0 --- /dev/null +++ b/specification/base/typespec/common/main.tsp @@ -0,0 +1,2 @@ +import "./custom.tsp"; +import "./models.tsp"; diff --git a/specification/base/typespec/common/models.tsp b/specification/base/typespec/common/models.tsp new file mode 100644 index 000000000..b67a2ce5e --- /dev/null +++ b/specification/base/typespec/common/models.tsp @@ -0,0 +1,469 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +model Error { + code: string | null; + message: string; + param: string | null; + type: string; +} + +// Tool customization: apply error decorator +@error +model ErrorResponse { + error: Error; +} + +// Tool customization: Wrap for reuse +@doc(""" + The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. + + Omitting `parameters` defines a function with an empty parameter list. + """) +model FunctionParametersCommon { + /** + * The parameters the functions accepts, described as a JSON Schema object. See the [guide](/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. + * + * Omitting `parameters` defines a function with an empty parameter list. + */ + parameters?: unknown; +} + +model FunctionObject { + /** A description of what the function does, used by the model to choose when and how to call the function. */ + description?: string; + + /** The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. */ + name: string; + + ...FunctionParametersCommon; + + @doc(""" + Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the `parameters` field. Only a subset of JSON Schema is supported when `strict` is `true`. Learn more about Structured Outputs in the [function calling guide](docs/guides/function-calling). + """) + strict?: boolean | null = false; +} + +// Tool customization: Wrap for reuse +/** + * Set of 16 key-value pairs that can be attached to an object. This can be + * useful for storing additional information about the object in a structured + * format, and querying for objects via API or the dashboard. + * + * Keys are strings with a maximum length of 64 characters. Values are strings + * with a maximum length of 512 characters. + */ +model MetadataPropertyForRequest { + /** + * Set of 16 key-value pairs that can be attached to an object. This can be + * useful for storing additional information about the object in a structured + * format, and querying for objects via API or the dashboard. + * + * Keys are strings with a maximum length of 64 characters. Values are strings + * with a maximum length of 512 characters. + */ + @extension("x-oaiTypeLabel", "map") + metadata?: Record; +} +model MetadataPropertyForResponse { + /** + * Set of 16 key-value pairs that can be attached to an object. This can be + * useful for storing additional information about the object in a structured + * format, and querying for objects via API or the dashboard. + * + * Keys are strings with a maximum length of 64 characters. Values are strings + * with a maximum length of 512 characters. + */ + @extension("x-oaiTypeLabel", "map") + metadata: Record | null; +} + +// Tool customization (apply_discriminator): establish a common, discriminated union +/** Default response format. Used to generate text responses. */ +model ResponseFormatText extends ResponseFormat { + @doc(""" + The type of response format being defined. Always `text`. + """) + type: "text"; +} + +// Tool customization (apply_discriminator): establish a common, discriminated union +@doc(""" + JSON object response format. An older method of generating JSON responses. + Using `json_schema` is recommended for models that support it. Note that the + model will not generate JSON without a system or user message instructing it + to do so. + """) +model ResponseFormatJsonObject extends ResponseFormat { + @doc(""" + The type of response format being defined. Always `json_object`. + """) + type: "json_object"; +} + +/** + * The schema for the response format, described as a JSON Schema object. + * Learn how to build JSON schemas [here](https://json-schema.org/). + */ +model ResponseFormatJsonSchemaSchema is Record; + +// Tool customization (apply_discriminator): establish a common, discriminated union +/** + * JSON Schema response format. Used to generate structured JSON responses. + * Learn more about [Structured Outputs](/docs/guides/structured-outputs). + */ +model ResponseFormatJsonSchema extends ResponseFormat { + @doc(""" + The type of response format being defined. Always `json_schema`. + """) + type: "json_schema"; + + /** Structured Outputs configuration options, including a JSON Schema. */ + json_schema: { + /** + * A description of what the response format is for, used by the model to + * determine how to respond in the format. + */ + description?: string; + + /** + * The name of the response format. Must be a-z, A-Z, 0-9, or contain + * underscores and dashes, with a maximum length of 64. + */ + name: string; + + schema?: ResponseFormatJsonSchemaSchema; + + @doc(""" + Whether to enable strict schema adherence when generating the output. + If set to true, the model will always follow the exact schema defined + in the `schema` field. Only a subset of JSON Schema is supported when + `strict` is `true`. To learn more, read the [Structured Outputs + guide](/docs/guides/structured-outputs). + """) + strict?: boolean | null = false; + }; +} + +/** Whether to enable [parallel function calling](/docs/guides/function-calling#configuring-parallel-function-calling) during tool use. */ +scalar ParallelToolCalls extends boolean; + +/** Usage statistics for the completion request. */ +model CompletionUsage { + /** Number of tokens in the generated completion. */ + completion_tokens: int32 = 0; + + /** Number of tokens in the prompt. */ + prompt_tokens: int32 = 0; + + /** Total number of tokens used in the request (prompt + completion). */ + total_tokens: int32 = 0; + + /** Breakdown of tokens used in a completion. */ + completion_tokens_details?: { + /** + * When using Predicted Outputs, the number of tokens in the + * prediction that appeared in the completion. + */ + accepted_prediction_tokens?: int32 = 0; + + /** Audio input tokens generated by the model. */ + audio_tokens?: int32 = 0; + + /** Tokens generated by the model for reasoning. */ + reasoning_tokens?: int32 = 0; + + /** + * When using Predicted Outputs, the number of tokens in the + * prediction that did not appear in the completion. However, like + * reasoning tokens, these tokens are still counted in the total + * completion tokens for purposes of billing, output, and context window + * limits. + */ + rejected_prediction_tokens?: int32 = 0; + }; + + /** Breakdown of tokens used in the prompt. */ + prompt_tokens_details?: { + /** Audio input tokens present in the prompt. */ + audio_tokens?: int32 = 0; + + /** Cached tokens present in the prompt. */ + cached_tokens?: int32 = 0; + }; +} + +@doc(""" + Options for streaming response. Only set this when you set `stream: true`. + """) +model ChatCompletionStreamOptions { + @doc(""" + If set, an additional chunk will be streamed before the `data: [DONE]` + message. The `usage` field on this chunk shows the token usage statistics + for the entire request, and the `choices` field will always be an empty + array. + + All other chunks will also include a `usage` field, but with a null + value. **NOTE:** If the stream is interrupted, you may not receive the + final usage chunk which contains the total token usage for the request. + """) + include_usage?: boolean; +} + +@doc(""" + **o-series models only** + + Constrains effort on reasoning for + [reasoning models](https://platform.openai.com/docs/guides/reasoning). + Currently supported values are `low`, `medium`, and `high`. Reducing + reasoning effort can result in faster responses and fewer tokens used + on reasoning in a response. + """) +union ReasoningEffort { + "low", + "medium", + "high", +} + +// Tool customization: Stub for separated type +alias CreateModelResponseProperties = ModelResponsePropertiesForRequest; + +// Tool customization: Replace imprecise common spread source with split request/response models honoring optionality and nullability +model ModelResponsePropertiesForRequest { + ...MetadataPropertyForRequest; + + @doc(""" + What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. + We generally recommend altering this or `top_p` but not both. + """) + @minValue(0) + @maxValue(2) + temperature?: float32 | null = 1; + + @doc(""" + An alternative to sampling with temperature, called nucleus sampling, + where the model considers the results of the tokens with top_p probability + mass. So 0.1 means only the tokens comprising the top 10% probability mass + are considered. + + We generally recommend altering this or `temperature` but not both. + """) + @minValue(0) + @maxValue(1) + top_p?: float32 | null = 1; + + /** A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids). */ + user?: string; + + service_tier?: ServiceTier; +} +model ModelResponsePropertiesForResponse { + ...MetadataPropertyForResponse; + + @doc(""" + What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. + We generally recommend altering this or `top_p` but not both. + """) + @minValue(0) + @maxValue(2) + temperature: float32 | null; + + @doc(""" + An alternative to sampling with temperature, called nucleus sampling, + where the model considers the results of the tokens with top_p probability + mass. So 0.1 means only the tokens comprising the top 10% probability mass + are considered. + + We generally recommend altering this or `temperature` but not both. + """) + @minValue(0) + @maxValue(1) + top_p: float32 | null; + + /** A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids). */ + user: string | null; + + service_tier?: ServiceTier; +} + +@doc(""" + Output types that you would like the model to generate. + Most models are capable of generating text, which is the default: + + `["text"]` + + The `gpt-4o-audio-preview` model can also be used to + [generate audio](/docs/guides/audio). To request that this model generate + both text and audio responses, you can use: + + `["text", "audio"]` + """) +model ResponseModalities is ("text" | "audio")[]; + +@doc(""" + Not supported with latest reasoning models `o3` and `o4-mini`. + + Up to 4 sequences where the API will stop generating further tokens. The + returned text will not contain the stop sequence. + """) +union StopConfiguration { + string, + string[], +} + +@doc(""" + High level guidance for the amount of context window space to use for the + search. One of `low`, `medium`, or `high`. `medium` is the default. + """) +union WebSearchContextSize { + "low", + "medium", + "high", +} + +/** Approximate location parameters for the search. */ +model WebSearchLocation { + @doc(""" + The two-letter + [ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user, + e.g. `US`. + """) + country?: string; + + @doc(""" + Free text input for the region of the user, e.g. `California`. + """) + region?: string; + + @doc(""" + Free text input for the city of the user, e.g. `San Francisco`. + """) + city?: string; + + @doc(""" + The [IANA timezone](https://timeapi.io/documentation/iana-timezones) + of the user, e.g. `America/Los_Angeles`. + """) + timezone?: string; +} + +@doc(""" + The ranker to use for the file search. If not specified will use the `auto` ranker. + """) +union FileSearchRanker { + "auto", + "default_2024_08_21", +} + +union ModelIdsShared { + string, + "gpt-4.1", + "gpt-4.1-mini", + "gpt-4.1-nano", + "gpt-4.1-2025-04-14", + "gpt-4.1-mini-2025-04-14", + "gpt-4.1-nano-2025-04-14", + "o4-mini", + "o4-mini-2025-04-16", + "o3", + "o3-2025-04-16", + "o3-mini", + "o3-mini-2025-01-31", + "o1", + "o1-2024-12-17", + "o1-preview", + "o1-preview-2024-09-12", + "o1-mini", + "o1-mini-2024-09-12", + "gpt-4o", + "gpt-4o-2024-11-20", + "gpt-4o-2024-08-06", + "gpt-4o-2024-05-13", + "gpt-4o-audio-preview", + "gpt-4o-audio-preview-2024-10-01", + "gpt-4o-audio-preview-2024-12-17", + "gpt-4o-audio-preview-2025-06-03", + "gpt-4o-mini-audio-preview", + "gpt-4o-mini-audio-preview-2024-12-17", + "gpt-4o-search-preview", + "gpt-4o-mini-search-preview", + "gpt-4o-search-preview-2025-03-11", + "gpt-4o-mini-search-preview-2025-03-11", + "chatgpt-4o-latest", + "codex-mini-latest", + "gpt-4o-mini", + "gpt-4o-mini-2024-07-18", + "gpt-4-turbo", + "gpt-4-turbo-2024-04-09", + "gpt-4-0125-preview", + "gpt-4-turbo-preview", + "gpt-4-1106-preview", + "gpt-4-vision-preview", + "gpt-4", + "gpt-4-0314", + "gpt-4-0613", + "gpt-4-32k", + "gpt-4-32k-0314", + "gpt-4-32k-0613", + "gpt-3.5-turbo", + "gpt-3.5-turbo-16k", + "gpt-3.5-turbo-0301", + "gpt-3.5-turbo-0613", + "gpt-3.5-turbo-1106", + "gpt-3.5-turbo-0125", + "gpt-3.5-turbo-16k-0613", +} + +/** A log probability object. */ +model LogProbProperties { + /** The token that was used to generate the log probability. */ + token: string; + + /** The log probability of the token. */ + logprob: float32; + + /** The bytes that were used to generate the log probability. */ + bytes: int32[]; +} + +union VoiceIdsShared { + string, + "alloy", + "ash", + "ballad", + "coral", + "echo", + "fable", + "onyx", + "nova", + "sage", + "shimmer", + "verse", +} + +@doc(""" + Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service: + - If set to 'auto', and the Project is Scale tier enabled, the system + will utilize scale tier credits until they are exhausted. + - If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarantee. + - If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarantee. + - If set to 'flex', the request will be processed with the Flex Processing service tier. [Learn more](/docs/guides/flex-processing). + - When not set, the default behavior is 'auto'. + + When this parameter is set, the response body will include the `service_tier` utilized. + """) +union ServiceTier { + "auto", + "default", + "flex", + "scale", +} diff --git a/specification/base/typespec/completions/main.tsp b/specification/base/typespec/completions/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/completions/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/completions/models.tsp b/specification/base/typespec/completions/models.tsp new file mode 100644 index 000000000..c13e53d3d --- /dev/null +++ b/specification/base/typespec/completions/models.tsp @@ -0,0 +1,184 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../common"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from CreateCompletionResponse.choices +alias CreateCompletionResponseChoice = { + @doc(""" + The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, + `length` if the maximum number of tokens specified in the request was reached, + or `content_filter` if content was omitted due to a flag from our content filters. + """) + finish_reason: "stop" | "length" | "content_filter"; + + index: int32; + logprobs: { + text_offset?: int32[]; + token_logprobs?: float32[]; + tokens?: string[]; + top_logprobs?: Record[]; + } | null; + text: string; +}; + +model CreateCompletionRequest { + /** ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them. */ + @extension("x-oaiTypeLabel", "string") + `model`: string | "gpt-3.5-turbo-instruct" | "davinci-002" | "babbage-002"; + + /** + * The prompt(s) to generate completions for, encoded as a string, array of strings, array of tokens, or array of token arrays. + * + * Note that <|endoftext|> is the document separator that the model sees during training, so if a prompt is not specified the model will generate as if from the beginning of a new document. + */ + prompt: string | string[] | int32[] | int32[][] | null = "<|endoftext|>"; + + @doc(""" + Generates `best_of` completions server-side and returns the "best" (the one with the highest log probability per token). Results cannot be streamed. + + When used with `n`, `best_of` controls the number of candidate completions and `n` specifies how many to return – `best_of` must be greater than `n`. + + **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. + """) + @minValue(0) + @maxValue(20) + best_of?: int32 | null = 1; + + /** Echo back the prompt in addition to the completion */ + echo?: boolean | null = false; + + /** + * Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. + * + * [See more information about frequency and presence penalties.](/docs/guides/text-generation) + */ + @minValue(-2) + @maxValue(2) + frequency_penalty?: float32 | null = 0; + + @doc(""" + Modify the likelihood of specified tokens appearing in the completion. + + Accepts a JSON object that maps tokens (specified by their token ID in the GPT tokenizer) to an associated bias value from -100 to 100. You can use this [tokenizer tool](/tokenizer?view=bpe) to convert text to token IDs. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. + + As an example, you can pass `{"50256": -100}` to prevent the <|endoftext|> token from being generated. + """) + @extension("x-oaiTypeLabel", "map") + logit_bias?: Record | null = null; + + @doc(""" + Include the log probabilities on the `logprobs` most likely output tokens, as well the chosen tokens. For example, if `logprobs` is 5, the API will return a list of the 5 most likely tokens. The API will always return the `logprob` of the sampled token, so there may be up to `logprobs+1` elements in the response. + + The maximum value for `logprobs` is 5. + """) + @minValue(0) + @maxValue(5) + logprobs?: int32 | null = null; + + @doc(""" + The maximum number of [tokens](/tokenizer) that can be generated in the completion. + + The token count of your prompt plus `max_tokens` cannot exceed the model's context length. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. + """) + @minValue(0) + max_tokens?: int32 | null = 16; + + @doc(""" + How many completions to generate for each prompt. + + **Note:** Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for `max_tokens` and `stop`. + """) + @minValue(1) + @maxValue(128) + n?: int32 | null = 1; + + /** + * Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. + * + * [See more information about frequency and presence penalties.](/docs/guides/text-generation) + */ + @minValue(-2) + @maxValue(2) + presence_penalty?: float32 | null = 0; + + @doc(""" + If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. + + Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. + """) + seed?: int64 | null; + + stop?: StopConfiguration | null = null; + + @doc(""" + Whether to stream back partial progress. If set, tokens will be sent as data-only [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format) as they become available, with the stream terminated by a `data: [DONE]` message. [Example Python code](https://cookbook.openai.com/examples/how_to_stream_completions). + """) + stream?: boolean | null = false; + + stream_options?: ChatCompletionStreamOptions | null = null; + + @doc(""" + The suffix that comes after a completion of inserted text. + + This parameter is only supported for `gpt-3.5-turbo-instruct`. + """) + suffix?: string | null = null; + + @doc(""" + What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. + + We generally recommend altering this or `top_p` but not both. + """) + @minValue(0) + @maxValue(2) + temperature?: float32 | null = 1; + + @doc(""" + An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + + We generally recommend altering this or `temperature` but not both. + """) + @minValue(0) + @maxValue(1) + top_p?: float32 | null = 1; + + /** A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids). */ + user?: string; +} + +/** Represents a completion response from the API. Note: both the streamed and non-streamed response objects share the same shape (unlike the chat endpoint). */ +model CreateCompletionResponse { + /** A unique identifier for the completion. */ + id: string; + + /** The list of completion choices the model generated for the input prompt. */ + choices: CreateCompletionResponseChoice[]; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the completion was created. */ + @encode("unixTimestamp", int32) + created: utcDateTime; + + /** The model used for completion. */ + `model`: string; + + @doc(""" + This fingerprint represents the backend configuration that the model runs with. + + Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. + """) + system_fingerprint?: string; + + /** The object type, which is always "text_completion" */ + object: "text_completion"; + + usage?: CompletionUsage; +} diff --git a/specification/base/typespec/completions/operations.tsp b/specification/base/typespec/completions/operations.tsp new file mode 100644 index 000000000..3f5255804 --- /dev/null +++ b/specification/base/typespec/completions/operations.tsp @@ -0,0 +1,22 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/completions") +interface Completions { + @post + @operationId("createCompletion") + @tag("Completions") + @summary("Creates a completion for the provided prompt and parameters.") + createCompletion( + @header accept: "application/json", + @body requestBody: CreateCompletionRequest, + ): CreateCompletionResponse | ErrorResponse; +} diff --git a/specification/base/typespec/containers/main.tsp b/specification/base/typespec/containers/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/containers/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/containers/models.tsp b/specification/base/typespec/containers/models.tsp new file mode 100644 index 000000000..0826d4221 --- /dev/null +++ b/specification/base/typespec/containers/models.tsp @@ -0,0 +1,130 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +model ContainerFileListResource { + /** The type of object returned, must be 'list'. */ + object: "list"; + + /** A list of container files. */ + data: ContainerFileResource[]; + + /** The ID of the first file in the list. */ + first_id: string; + + /** The ID of the last file in the list. */ + last_id: string; + + /** Whether there are more files available. */ + has_more: boolean; +} + +model ContainerFileResource { + /** Unique identifier for the file. */ + id: string; + + @doc(""" + The type of this object (`container.file`). + """) + object: string; + + /** The container this file belongs to. */ + container_id: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** Unix timestamp (in seconds) when the file was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** Size of the file in bytes. */ + bytes: int32; + + /** Path of the file in the container. */ + path: string; + + @doc(""" + Source of the file (e.g., `user`, `assistant`). + """) + source: string; +} + +model ContainerListResource { + /** The type of object returned, must be 'list'. */ + object: "list"; + + /** A list of containers. */ + data: ContainerResource[]; + + /** The ID of the first container in the list. */ + first_id: string; + + /** The ID of the last container in the list. */ + last_id: string; + + /** Whether there are more containers available. */ + has_more: boolean; +} + +model ContainerResource { + /** Unique identifier for the container. */ + id: string; + + /** The type of this object. */ + object: string; + + /** Name of the container. */ + name: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** Unix timestamp (in seconds) when the container was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** Status of the container (e.g., active, deleted). */ + status: string; + + /** + * The container will expire after this time period. + * The anchor is the reference point for the expiration. + * The minutes is the number of minutes after the anchor before the container expires. + */ + expires_after?: { + /** The reference point for the expiration. */ + anchor?: "last_active_at"; + + /** The number of minutes after the anchor before the container expires. */ + minutes?: int32; + }; +} + +model CreateContainerBody { + /** Name of the container to create. */ + name: string; + + /** IDs of files to copy to the container. */ + file_ids?: string[]; + + /** Container expiration time in seconds relative to the 'anchor' time. */ + expires_after?: { + /** Time anchor for the expiration time. Currently only 'last_active_at' is supported. */ + anchor: "last_active_at"; + + minutes: int32; + }; +} + +model CreateContainerFileBody { + // Tool customization: Apply HttpPart for property in multipart request model + /** Name of the file to create. */ + file_id?: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + /** The File object (not file name) to be uploaded. */ + file?: HttpPart; +} diff --git a/specification/base/typespec/containers/operations.tsp b/specification/base/typespec/containers/operations.tsp new file mode 100644 index 000000000..b60d92aa3 --- /dev/null +++ b/specification/base/typespec/containers/operations.tsp @@ -0,0 +1,114 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/containers") +@tag("Containers") +interface Containers { + @get + @operationId("ListContainers") + listContainers( + ...PageLimitQueryParameter, + ...PageOrderQueryParameter, + ...PageAfterQueryParameter, + ): ContainerListResource | ErrorResponse; + + @post + @operationId("CreateContainer") + createContainer( + @body + body: CreateContainerBody, + ): ContainerResource | ErrorResponse; + + @get + @route("{container_id}") + @operationId("RetrieveContainer") + retrieveContainer( + @path + container_id: string, + ): ContainerResource | ErrorResponse; + + @delete + @route("{container_id}") + @operationId("DeleteContainer") + deleteContainer( + @path + container_id: string, + ): { + id: string; + object: "container.deleted"; + deleted: true; + } | ErrorResponse; + + @post + @route("{container_id}/files") + @operationId("CreateContainerFile") + createContainerFile( + @path + container_id: string, + + @header + contentType: "multipart/form-data", + + @multipartBody + body: CreateContainerFileBody, + ): ContainerFileResource | ErrorResponse; + + @get + @route("{container_id}/files") + @operationId("ListContainerFiles") + listContainerFiles( + @path + container_id: string, + + ...PageLimitQueryParameter, + ...PageOrderQueryParameter, + ...PageAfterQueryParameter, + ): ContainerFileListResource | ErrorResponse; + + @get + @route("{container_id}/files/{file_id}") + @operationId("RetrieveContainerFile") + retrieveContainerFile( + @path + container_id: string, + + @path + file_id: string, + ): ContainerFileResource | ErrorResponse; + + @delete + @route("{container_id}/files/{file_id}") + @operationId("DeleteContainerFile") + deleteContainerFile( + @path + container_id: string, + + @path + file_id: string, + ): { + id: string; + object: "container.file.deleted"; + deleted: true; + } | ErrorResponse; + + @get + @route("{container_id}/files/{file_id}/content") + @operationId("RetrieveContainerFileContent") + retrieveContainerFileContent( + @path + container_id: string, + + @path + file_id: string, + ): { + @encode("base64") @body file_content: bytes; + } | ErrorResponse; +} diff --git a/specification/base/typespec/embeddings/main.tsp b/specification/base/typespec/embeddings/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/embeddings/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/embeddings/models.tsp b/specification/base/typespec/embeddings/models.tsp new file mode 100644 index 000000000..e881b891c --- /dev/null +++ b/specification/base/typespec/embeddings/models.tsp @@ -0,0 +1,69 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +model CreateEmbeddingRequest { + /** Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for all embedding models), cannot be an empty string, and any array must be 2048 dimensions or less. [Example Python code](https://cookbook.openai.com/examples/how_to_count_tokens_with_tiktoken) for counting tokens. In addition to the per-input token limit, all embedding models enforce a maximum of 300,000 tokens summed across all inputs in a single request. */ + input: string | string[] | int32[] | int32[][]; + + /** ID of the model to use. You can use the [List models](/docs/api-reference/models/list) API to see all of your available models, or see our [Model overview](/docs/models) for descriptions of them. */ + @extension("x-oaiTypeLabel", "string") + `model`: + | string + | "text-embedding-ada-002" + | "text-embedding-3-small" + | "text-embedding-3-large"; + + @doc(""" + The format to return the embeddings in. Can be either `float` or [`base64`](https://pypi.org/project/pybase64/). + """) + encoding_format?: "float" | "base64" = "float"; + + @doc(""" + The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models. + """) + @minValue(1) + dimensions?: int32; + + /** A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids). */ + user?: string; +} + +model CreateEmbeddingResponse { + /** The list of embeddings generated by the model. */ + data: Embedding[]; + + /** The name of the model used to generate the embedding. */ + `model`: string; + + /** The object type, which is always "list". */ + object: "list"; + + /** The usage information for the request. */ + usage: { + /** The number of tokens used by the prompt. */ + prompt_tokens: int32; + + /** The total number of tokens used by the request. */ + total_tokens: int32; + }; +} + +/** Represents an embedding vector returned by embedding endpoint. */ +model Embedding { + /** The index of the embedding in the list of embeddings. */ + index: int32; + + // Tool customization: apply missing string union for embedding response values + /** The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the [embedding guide](/docs/guides/embeddings). */ + embedding: float[] | string; + + /** The object type, which is always "embedding". */ + object: "embedding"; +} diff --git a/specification/base/typespec/embeddings/operations.tsp b/specification/base/typespec/embeddings/operations.tsp new file mode 100644 index 000000000..b3495f10b --- /dev/null +++ b/specification/base/typespec/embeddings/operations.tsp @@ -0,0 +1,22 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/embeddings") +interface Embeddings { + @post + @operationId("createEmbedding") + @tag("Embeddings") + @summary("Creates an embedding vector representing the input text.") + createEmbedding( + @header accept: "application/json", + @body requestBody: CreateEmbeddingRequest, + ): CreateEmbeddingResponse | ErrorResponse; +} diff --git a/specification/base/typespec/evals/custom.tsp b/specification/base/typespec/evals/custom.tsp new file mode 100644 index 000000000..cec4442ed --- /dev/null +++ b/specification/base/typespec/evals/custom.tsp @@ -0,0 +1,111 @@ +import "../graders/models.tsp"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union EvalItemContentType { + input_text: "input_text", + output_text: "output_text", +} + +@discriminator("type") +model EvalItemContent { + type: EvalItemContentType; +} + +model EvalItemContentInputText extends EvalItemContent { + type: EvalItemContentType.input_text; + text: string; +} + +model EvalItemContentOutputText extends EvalItemContent { + type: EvalItemContentType.output_text; + text: string; +} + +union EvalDataSourceConfigType { + custom: "custom", + logs: "logs", + stored_completions: "stored_completions", +} + +@discriminator("type") +model EvalDataSourceConfigParams { + type: EvalDataSourceConfigType; +} + +@discriminator("type") +model EvalDataSourceConfigResource { + type: EvalDataSourceConfigType; +} + +union EvalRunDataContentSourceType { + file_id: "file_id", + file_content: "file_content", + stored_completions: "stored_completions", + responses: "responses", +} + +@discriminator("type") +model EvalRunDataContentSource { + type: EvalRunDataContentSourceType; +} + +union EvalRunDataSourceType { + jsonl: "jsonl", + completions: "completions", + responses: "responses", +} + +@discriminator("type") +model EvalRunDataSourceParams { + type: EvalRunDataSourceType; +} + +model EvalRunDataSourceResource { + type: EvalRunDataSourceType; +} + +model EvalRunDataSourceJsonlResource extends EvalRunDataSourceResource { + type: EvalRunDataSourceType.jsonl; +} + +model EvalRunDataSourceCompletionsResource extends EvalRunDataSourceResource { + type: EvalRunDataSourceType.completions; +} + +model EvalRunDataSourceResponsesResource extends EvalRunDataSourceResource { + type: EvalRunDataSourceType.responses; +} + +@discriminator("type") +model EvalGraderParams { + type: GraderType; +} + +@discriminator("type") +model EvalGraderResource { + type: GraderType; +} + +// Customization note: as of 2025-05-21, the origin specification only formally splits input (request) and output +// (response) models for the [Create]EvalLabelModelGrader component[s]. For compatibility and clarity, this +// reprojection chooses to split all EvalGrader components into input and output models, sharing details via +// spread. + +model EvalGraderStringCheckParams extends EvalGraderParams { + ...EvalGraderStringCheckResource; +} + +model EvalGraderTextSimilarityParams extends EvalGraderParams { + ...EvalGraderTextSimilarityResource; +} + +model EvalGraderPythonParams extends EvalGraderParams { + ...EvalGraderPythonResource; +} + +model EvalGraderScoreModelParams extends EvalGraderParams { + ...EvalGraderScoreModelResource; +} diff --git a/specification/base/typespec/evals/main.tsp b/specification/base/typespec/evals/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/evals/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/evals/models.tsp b/specification/base/typespec/evals/models.tsp new file mode 100644 index 000000000..c8377d47a --- /dev/null +++ b/specification/base/typespec/evals/models.tsp @@ -0,0 +1,807 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../chat"; +import "../common"; +import "../responses"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from EvalRunFileContentDataContentSource.content +alias EvalRunFileContentDataContentSourceContent = { + item: Record; + sample?: Record; +}; + +// Tool generated type. Extracts from EvalRun.per_model_usage +alias EvalRunPerModelUsage = { + /** The name of the model. */ + model_name: string; + + /** The number of invocations. */ + invocation_count: int32; + + /** The number of prompt tokens used. */ + prompt_tokens: int32; + + /** The number of completion tokens generated. */ + completion_tokens: int32; + + /** The total number of tokens used. */ + total_tokens: int32; + + /** The number of tokens retrieved from cache. */ + cached_tokens: int32; +}; + +// Tool generated type. Extracts from EvalRun.per_testing_criteria_results +alias EvalRunPerTestingCriteriaResult = { + /** A description of the testing criteria. */ + testing_criteria: string; + + /** Number of tests passed for this criteria. */ + passed: int32; + + /** Number of tests failed for this criteria. */ + failed: int32; +}; + +// Tool generated type. Extracts from EvalRunOutputItem.sample.input +alias EvalRunOutputItemSampleInput = { + /** The role of the message sender (e.g., system, user, developer). */ + role: string; + + /** The content of the message. */ + content: string; +}; + +// Tool generated type. Extracts from EvalRunOutputItem.sample.output +alias EvalRunOutputItemSampleOutput = { + /** The role of the message (e.g. "system", "assistant", "user"). */ + role?: string; + + /** The content of the message. */ + content?: string; +}; + +model CreateEvalRequest { + /** The name of the evaluation. */ + name?: string; + + ...MetadataPropertyForRequest; + + // Tool customization: Use discriminated type + /** The configuration for the data source used for the evaluation runs. Dictates the schema of the data used in the evaluation. */ + data_source_config: EvalDataSourceConfigParams; + + // Tool customization: Use discriminated type + @doc(""" + A list of graders for all eval runs in this group. Graders can reference variables in the data source using double curly braces notation, like `{{item.variable_name}}`. To reference the model's output, use the `sample` namespace (ie, `{{sample.output_text}}`). + """) + testing_criteria: EvalGraderParams[]; +} + +/** + * An Eval object with a data source config and testing criteria. + * An Eval represents a task to be done for your LLM integration. + * Like: + * - Improve the quality of my chatbot + * - See how well my chatbot handles customer support + * - Check if o4-mini is better at my usecase than gpt-4o + */ +model Eval { + /** The object type. */ + object: "eval" = "eval"; + + /** Unique identifier for the evaluation. */ + id: string; + + /** The name of the evaluation. */ + name: string; + + // Tool customization: Use discriminated type + /** Configuration of data sources used in runs of the evaluation. */ + data_source_config: EvalDataSourceConfigResource; + + // Tool customization: Use discriminated type + /** A list of testing criteria. */ + testing_criteria: EvalGraderResource[] | null = null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the eval was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + ...MetadataPropertyForResponse; +} + +// Tool customization (apply_discriminator): Apply discriminated type +/** + * A CustomDataSourceConfig object that defines the schema for the data source used for the evaluation runs. + * This schema is used to define the shape of the data that will be: + * - Used to define your testing criteria and + * - What data is required when creating a run + */ +model EvalCustomDataSourceConfigParams extends EvalDataSourceConfigParams { + @doc(""" + The type of data source. Always `custom`. + """) + type: EvalDataSourceConfigType.custom; + + /** The json schema for each row in the data source. */ + item_schema: Record; + + /** Whether the eval should expect you to populate the sample namespace (ie, by generating responses off of your data source) */ + include_sample_schema?: boolean = false; +} + +@doc(""" + A chat message that makes up the prompt or context. May include variable references to the `item` namespace, ie {{item.name}}. + """) +union CreateEvalItem { + { + /** The role of the message (e.g. "system", "assistant", "user"). */ + role: string, + + /** The content of the message. */ + content: string, + }, + EvalItem, +} + +// Tool customization (apply_discriminator): Apply discriminated type +/** A JsonlRunDataSource object with that specifies a JSONL file that matches the eval */ +model EvalJsonlRunDataSourceParams extends EvalRunDataSourceParams { + @doc(""" + The type of data source. Always `jsonl`. + """) + type: EvalRunDataSourceType.jsonl; + + // Tool customization: Use updated discriminated type union + @doc(""" + Determines what populates the `item` namespace in the data source. + """) + source: EvalRunFileContentDataContentSource | EvalRunFileIdDataContentSource; +} + +// Tool customization (apply_discriminator): Apply discriminated type +/** A CompletionsRunDataSource object describing a model sampling configuration. */ +model EvalCompletionsRunDataSourceParams extends EvalRunDataSourceParams { + @doc(""" + The type of run data source. Always `completions`. + """) + type: EvalRunDataSourceType.completions; + + @doc(""" + Used when sampling from a model. Dictates the structure of the messages passed into the model. Can either be a reference to a prebuilt trajectory (ie, `item.input_trajectory`), or a template with variable references to the `item` namespace. + """) + input_messages?: { + @doc(""" + The type of input messages. Always `template`. + """) + type: "template"; + + @doc(""" + A list of chat messages forming the prompt or context. May include variable references to the `item` namespace, ie {{item.name}}. + """) + template: (EasyInputMessage | EvalItem)[]; + } | { + @doc(""" + The type of input messages. Always `item_reference`. + """) + type: "item_reference"; + + @doc(""" + A reference to a variable in the `item` namespace. Ie, "item.input_trajectory" + """) + item_reference: string; + }; + + sampling_params?: { + /** A higher temperature increases randomness in the outputs. */ + temperature?: float32 = 1; + + /** The maximum number of tokens in the generated output. */ + max_completion_tokens?: int32; + + /** An alternative to temperature for nucleus sampling; 1.0 includes all tokens. */ + top_p?: float32 = 1; + + /** A seed value to initialize the randomness, during sampling. */ + seed?: int32 = 42; + + // Tool customization: Employ discriminated type base + @doc(""" + An object specifying the format that the model must output. + + Setting to `{ "type": "json_schema", "json_schema": {...} }` enables + Structured Outputs which ensures the model will match your supplied JSON + schema. Learn more in the [Structured Outputs + guide](/docs/guides/structured-outputs). + + Setting to `{ "type": "json_object" }` enables the older JSON mode, which + ensures the message the model generates is valid JSON. Using `json_schema` + is preferred for models that support it. + """) + response_format?: ResponseTextFormatConfiguration; + + /** A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. A max of 128 functions are supported. */ + tools?: ChatCompletionTool[]; + }; + + /** The name of the model to use for generating completions (e.g. "o3-mini"). */ + `model`?: string; + + // Tool customization: Use updated discriminated type union + @doc(""" + Determines what populates the `item` namespace in this run's data source. + """) + source: EvalRunFileContentDataContentSource | EvalRunFileIdDataContentSource | EvalRunStoredCompletionsDataContentSource; +} + +// Tool customization (apply_discriminator): Apply discriminated type +/** A ResponsesRunDataSource object describing a model sampling configuration. */ +model EvalResponsesRunDataSourceParams extends EvalRunDataSourceParams { + @doc(""" + The type of run data source. Always `responses`. + """) + type: EvalRunDataSourceType.responses; + + @doc(""" + Used when sampling from a model. Dictates the structure of the messages passed into the model. Can either be a reference to a prebuilt trajectory (ie, `item.input_trajectory`), or a template with variable references to the `item` namespace. + """) + input_messages?: { + @doc(""" + The type of input messages. Always `template`. + """) + type: "template"; + + @doc(""" + A list of chat messages forming the prompt or context. May include variable references to the `item` namespace, ie {{item.name}}. + """) + template: ({ + /** The role of the message (e.g. "system", "assistant", "user"). */ + role: string; + + /** The content of the message. */ + content: string; + } | EvalItem)[]; + } | { + @doc(""" + The type of input messages. Always `item_reference`. + """) + type: "item_reference"; + + @doc(""" + A reference to a variable in the `item` namespace. Ie, "item.name" + """) + item_reference: string; + }; + + sampling_params?: { + /** A higher temperature increases randomness in the outputs. */ + temperature?: float32 = 1; + + /** The maximum number of tokens in the generated output. */ + max_completion_tokens?: int32; + + /** An alternative to temperature for nucleus sampling; 1.0 includes all tokens. */ + top_p?: float32 = 1; + + /** A seed value to initialize the randomness, during sampling. */ + seed?: int32 = 42; + + @doc(""" + An array of tools the model may call while generating a response. You + can specify which tool to use by setting the `tool_choice` parameter. + + The two categories of tools you can provide the model are: + + - **Built-in tools**: Tools that are provided by OpenAI that extend the + model's capabilities, like [web search](/docs/guides/tools-web-search) + or [file search](/docs/guides/tools-file-search). Learn more about + [built-in tools](/docs/guides/tools). + - **Function calls (custom tools)**: Functions that are defined by you, + enabling the model to call your own code. Learn more about + [function calling](/docs/guides/function-calling). + """) + tools?: Tool[]; + + /** + * Configuration options for a text response from the model. Can be plain + * text or structured JSON data. Learn more: + * - [Text inputs and outputs](/docs/guides/text) + * - [Structured Outputs](/docs/guides/structured-outputs) + */ + text?: { + // Tool customization: Employ discriminated type base + format?: ResponseTextFormatConfiguration; + }; + }; + + /** The name of the model to use for generating completions (e.g. "o3-mini"). */ + `model`?: string; + + // Tool customization: Use updated discriminated type union + @doc(""" + Determines what populates the `item` namespace in this run's data source. + """) + source: EvalRunFileContentDataContentSource | EvalRunFileIdDataContentSource | EvalRunResponsesDataContentSource; +} + +// Tool customization (apply_discriminator): Apply discriminated type +@doc(""" + A data source config which specifies the metadata property of your logs query. + This is usually metadata like `usecase=chatbot` or `prompt-version=v2`, etc. + """) +model EvalLogsDataSourceConfigParams extends EvalDataSourceConfigParams { + @doc(""" + The type of data source. Always `logs`. + """) + type: EvalDataSourceConfigType.logs; + + ...MetadataPropertyForRequest; +} + +model CreateEvalRunRequest { + /** The name of the run. */ + name?: string; + + ...MetadataPropertyForRequest; + + // Tool customization: Use discriminated type + /** Details about the run's data source. */ + data_source: EvalRunDataSourceParams; +} + +/** An object representing an error response from the Eval API. */ +model EvalApiError { + /** The error code. */ + code: string; + + /** The error message. */ + message: string; +} + +// Tool customization (apply_discriminator): Apply discriminated type +@doc(""" + A CustomDataSourceConfig which specifies the schema of your `item` and optionally `sample` namespaces. + The response schema defines the shape of the data that will be: + - Used to define your testing criteria and + - What data is required when creating a run + """) +model EvalCustomDataSourceConfigResource extends EvalDataSourceConfigResource { + @doc(""" + The type of data source. Always `custom`. + """) + type: EvalDataSourceConfigType.custom; + + /** + * The json schema for the run data source items. + * Learn how to build JSON schemas [here](https://json-schema.org/). + */ + schema: Record; +} + +@doc(""" + A message input to the model with a role indicating instruction following + hierarchy. Instructions given with the `developer` or `system` role take + precedence over instructions given with the `user` role. Messages with the + `assistant` role are presumed to have been generated by the model in previous + interactions. + """) +model EvalItem { + @doc(""" + The role of the message input. One of `user`, `assistant`, `system`, or + `developer`. + """) + role: "user" | "assistant" | "system" | "developer"; + + // Tool customization: Use distinct evals item content definitions + /** Text inputs to the model - can contain template strings. */ + content: string | EvalItemContent; + + @doc(""" + The type of the message input. Always `message`. + """) + type?: "message"; +} + +// Tool customization (apply_discriminator): Apply discriminated type +model EvalRunFileContentDataContentSource extends EvalRunDataContentSource { + @doc(""" + The type of jsonl source. Always `file_content`. + """) + type: EvalRunDataContentSourceType.file_content; + + /** The content of the jsonl file. */ + content: EvalRunFileContentDataContentSourceContent[]; +} + +// Tool customization (apply_discriminator): Apply discriminated type +model EvalRunFileIdDataContentSource extends EvalRunDataContentSource { + @doc(""" + The type of jsonl source. Always `file_id`. + """) + type: EvalRunDataContentSourceType.file_id; + + /** The identifier of the file. */ + id: string; +} + +// Tool customization: Conform to spread inherited base +model EvalGraderLabelModelResource extends EvalGraderResource { + ...GraderLabelModel; +} + +// Tool customization: Conform to spread inherited base +model EvalGraderStringCheckResource { + ...GraderStringCheck; +} + +// Tool customization: Conform to spread inherited base +model EvalGraderTextSimilarityResource extends EvalGraderResource { + ...GraderTextSimilarity; + + /** The threshold for the score. */ + pass_threshold: float32; +} + +/** An object representing a list of evals. */ +model EvalList { + /** The type of this object. It is always set to "list". */ + object: "list" = "list"; + + /** An array of eval objects. */ + data: Eval[]; + + /** The identifier of the first eval in the data array. */ + first_id: string; + + /** The identifier of the last eval in the data array. */ + last_id: string; + + /** Indicates whether there are more evals available. */ + has_more: boolean; +} + +// Tool customization: Conform to spread inherited base +model EvalGraderPythonResource extends EvalGraderResource { + ...GraderPython; + + /** The threshold for the score. */ + pass_threshold?: float32; +} + +// Tool customization (apply_discriminator): Apply discriminated type +/** A EvalResponsesSource object describing a run data source configuration. */ +model EvalRunResponsesDataContentSource extends EvalRunDataContentSource { + @doc(""" + The type of run data source. Always `responses`. + """) + type: EvalRunDataContentSourceType.responses; + + ...MetadataPropertyForRequest; + + /** The name of the model to find responses for. This is a query parameter used to select responses. */ + `model`?: string | null; + + /** Optional string to search the 'instructions' field. This is a query parameter used to select responses. */ + instructions_search?: string | null; + + /** Only include items created after this timestamp (inclusive). This is a query parameter used to select responses. */ + @minValue(0) + created_after?: int32 | null; + + /** Only include items created before this timestamp (inclusive). This is a query parameter used to select responses. */ + @minValue(0) + created_before?: int32 | null; + + /** Optional reasoning effort parameter. This is a query parameter used to select responses. */ + reasoning_effort?: ReasoningEffort | null = "medium"; + + /** Sampling temperature. This is a query parameter used to select responses. */ + temperature?: float32 | null; + + /** Nucleus sampling parameter. This is a query parameter used to select responses. */ + top_p?: float32 | null; + + /** List of user identifiers. This is a query parameter used to select responses. */ + users?: string[] | null; + + /** List of tool names. This is a query parameter used to select responses. */ + tools?: string[] | null; +} + +/** A schema representing an evaluation run. */ +model EvalRun { + /** The type of the object. Always "eval.run". */ + object: "eval.run" = "eval.run"; + + /** Unique identifier for the evaluation run. */ + id: string; + + /** The identifier of the associated evaluation. */ + eval_id: string; + + /** The status of the evaluation run. */ + status: string; + + /** The model that is evaluated, if applicable. */ + `model`: string; + + /** The name of the evaluation run. */ + name: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** Unix timestamp (in seconds) when the evaluation run was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The URL to the rendered evaluation run report on the UI dashboard. */ + report_url: string; + + /** Counters summarizing the outcomes of the evaluation run. */ + result_counts: { + /** Total number of executed output items. */ + total: int32; + + /** Number of output items that resulted in an error. */ + errored: int32; + + /** Number of output items that failed to pass the evaluation. */ + failed: int32; + + /** Number of output items that passed the evaluation. */ + passed: int32; + }; + + /** Usage statistics for each model during the evaluation run. */ + per_model_usage: EvalRunPerModelUsage[]; + + /** Results per testing criteria applied during the evaluation run. */ + per_testing_criteria_results: EvalRunPerTestingCriteriaResult[]; + + // Tool customization: Use split output model with discriminated type + /** Information about the run's data source. */ + data_source: EvalRunDataSourceResource; + + ...MetadataPropertyForResponse; + error: EvalApiError; +} + +/** An object representing a list of runs for an evaluation. */ +model EvalRunList { + /** The type of this object. It is always set to "list". */ + object: "list" = "list"; + + /** An array of eval run objects. */ + data: EvalRun[]; + + /** The identifier of the first eval run in the data array. */ + first_id: string; + + /** The identifier of the last eval run in the data array. */ + last_id: string; + + /** Indicates whether there are more evals available. */ + has_more: boolean; +} + +/** A schema representing an evaluation run output item. */ +model EvalRunOutputItem { + /** The type of the object. Always "eval.run.output_item". */ + object: "eval.run.output_item" = "eval.run.output_item"; + + /** Unique identifier for the evaluation run output item. */ + id: string; + + /** The identifier of the evaluation run associated with this output item. */ + run_id: string; + + /** The identifier of the evaluation group. */ + eval_id: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** Unix timestamp (in seconds) when the evaluation run was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The status of the evaluation run. */ + status: string; + + /** The identifier for the data source item. */ + datasource_item_id: int32; + + /** Details of the input data source item. */ + datasource_item: Record; + + /** A list of results from the evaluation run. */ + results: Record[]; + + /** A sample containing the input and output of the evaluation run. */ + sample: { + /** An array of input messages. */ + input: EvalRunOutputItemSampleInput[]; + + /** An array of output messages. */ + output: EvalRunOutputItemSampleOutput[]; + + /** The reason why the sample generation was finished. */ + finish_reason: string; + + /** The model used for generating the sample. */ + `model`: string; + + /** Token usage details for the sample. */ + usage: { + /** The total number of tokens used. */ + total_tokens: int32; + + /** The number of completion tokens generated. */ + completion_tokens: int32; + + /** The number of prompt tokens used. */ + prompt_tokens: int32; + + /** The number of tokens retrieved from cache. */ + cached_tokens: int32; + }; + + error: EvalApiError; + + /** The sampling temperature used. */ + temperature: float32; + + /** The maximum number of tokens allowed for completion. */ + max_completion_tokens: int32; + + /** The top_p value used for sampling. */ + top_p: float32; + + /** The seed used for generating the sample. */ + seed: int32; + }; +} + +/** An object representing a list of output items for an evaluation run. */ +model EvalRunOutputItemList { + /** The type of this object. It is always set to "list". */ + object: "list" = "list"; + + /** An array of eval run output item objects. */ + data: EvalRunOutputItem[]; + + /** The identifier of the first eval run output item in the data array. */ + first_id: string; + + /** The identifier of the last eval run output item in the data array. */ + last_id: string; + + /** Indicates whether there are more eval run output items available. */ + has_more: boolean; +} + +// Tool customization (apply_discriminator): Apply common discriminated base +/** + * A LabelModelGrader object which uses a model to assign labels to each item + * in the evaluation. + */ +model EvalGraderLabelModelParams extends EvalGraderParams { + @doc(""" + The object type, which is always `label_model`. + """) + type: GraderType.label_model; + + /** The name of the grader. */ + name: string; + + /** The model to use for the evaluation. Must support structured outputs. */ + `model`: string; + + @doc(""" + A list of chat messages forming the prompt or context. May include variable references to the `item` namespace, ie {{item.name}}. + """) + input: CreateEvalItem[]; + + /** The labels to classify to each item in the evaluation. */ + labels: string[]; + + /** The labels that indicate a passing result. Must be a subset of labels. */ + passing_labels: string[]; +} + +// Tool customization: Conform to spread inherited base +model EvalGraderScoreModelResource extends EvalGraderResource { + ...GraderScoreModel; + + /** The threshold for the score. */ + pass_threshold?: float32; +} + +// Tool customization (apply_discriminator): Apply discriminated type +/** Deprecated in favor of LogsDataSourceConfig. */ +#suppress "deprecated" "Warning unnecessary for spec description of deprecation" +#deprecated "This field is marked as deprecated." +model EvalStoredCompletionsDataSourceConfigParams + extends EvalDataSourceConfigParams { + @doc(""" + The type of data source. Always `stored_completions`. + """) + type: EvalDataSourceConfigType.stored_completions; + + /** Metadata filters for the stored completions data source. */ + metadata?: Record; +} + +// Tool customization (apply_discriminator): Apply discriminated type +/** Deprecated in favor of LogsDataSourceConfig. */ +#suppress "deprecated" "Warning unnecessary for spec description of deprecation" +#deprecated "This field is marked as deprecated." +model EvalStoredCompletionsDataSourceConfigResource + extends EvalDataSourceConfigResource { + @doc(""" + The type of data source. Always `stored_completions`. + """) + type: EvalDataSourceConfigType.stored_completions; + + ...MetadataPropertyForResponse; + + /** + * The json schema for the run data source items. + * Learn how to build JSON schemas [here](https://json-schema.org/). + */ + schema: Record; +} + +// Tool customization (apply_discriminator): Apply discriminated type +/** A StoredCompletionsRunDataSource configuration describing a set of filters */ +model EvalRunStoredCompletionsDataContentSource + extends EvalRunDataContentSource { + @doc(""" + The type of source. Always `stored_completions`. + """) + type: EvalRunDataContentSourceType.stored_completions; + + ...MetadataPropertyForResponse; + + /** An optional model to filter by (e.g., 'gpt-4o'). */ + `model`?: string | null; + + /** An optional Unix timestamp to filter items created after this time. */ + created_after?: int32 | null; + + /** An optional Unix timestamp to filter items created before this time. */ + created_before?: int32 | null; + + /** An optional maximum number of items to return. */ + limit?: int32 | null; +} + +// Tool customization (apply_discriminator): Apply discriminated type +@doc(""" + A LogsDataSourceConfig which specifies the metadata property of your logs query. + This is usually metadata like `usecase=chatbot` or `prompt-version=v2`, etc. + The schema returned by this data source config is used to defined what variables are available in your evals. + `item` and `sample` are both defined when using this data source config. + """) +model EvalLogsDataSourceConfigResource extends EvalDataSourceConfigResource { + @doc(""" + The type of data source. Always `logs`. + """) + type: EvalDataSourceConfigType.logs; + + ...MetadataPropertyForResponse; + + /** + * The json schema for the run data source items. + * Learn how to build JSON schemas [here](https://json-schema.org/). + */ + schema: Record; +} diff --git a/specification/base/typespec/evals/operations.tsp b/specification/base/typespec/evals/operations.tsp new file mode 100644 index 000000000..62cf82feb --- /dev/null +++ b/specification/base/typespec/evals/operations.tsp @@ -0,0 +1,238 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/evals") +interface Evals { + @get + @operationId("listEvals") + @tag("Evals") + @summary("List evaluations for a project.") + listEvals( + /** + * Identifier for the last eval from the previous pagination request. + */ + @query after?: string, + + /** + * A limit on the number of evals to be returned in a single pagination response. + */ + @query limit?: int32 = 20, + + /** + * Sort order for evals by timestamp. Use `asc` for ascending order or + * `desc` for descending order. + */ + @query order?: "asc" | "desc" = "asc", + + /** + * Evals can be ordered by creation time or last updated time. Use + * `created_at` for creation time or `updated_at` for last updated + * time. + */ + @query order_by?: "created_at" | "updated_at" = "created_at", + ): EvalList; + + /** + * Create the structure of an evaluation that can be used to test a model's + * performance. + * + * An evaluation is a set of testing criteria and a datasource. After + * creating an evaluation, you can run it on different models and model + * parameters. We support several types of graders and datasources. + * + * For more information, see the [Evals guide](/docs/guides/evals). + */ + @post + @operationId("createEval") + @tag("Evals") + createEval(@body body: CreateEvalRequest): { + @statusCode statusCode: 201; + ...Eval; + } | EvalsErrorResponse; + + @get + @route("{eval_id}") + @operationId("getEval") + @tag("Evals") + @summary("Retrieve an evaluation by its ID.") + getEval(@path eval_id: string): Eval | EvalsErrorResponse; + + /** + * Update select, mutable properties of a specified evaluation. + * + * @param eval_id The ID of the evaluation to update. + */ + @post + @route("{eval_id}") + @operationId("updateEval") + @tag("Evals") + updateEval( + @path eval_id: string, + @body body: { + name?: string; + metadata?: MetadataPropertyForRequest; + }, + ): Eval | EvalsErrorResponse; + + /** + * Delete a specified evaluation. + * + * @param eval_id The ID of the evaluation to delete. + */ + @delete + @route("{eval_id}") + @operationId("deleteEval") + @tag("Evals") + deleteEval(@path eval_id: string): { + object: "eval.deleted"; + deleted: boolean; + eval_id: string; + } | EvalsErrorResponse; + + /** + * Retrieve a list of runs for a specified evaluation. + * + * @param eval_id The ID of the evaluation to retrieve runs for. + * @param after Identifier for the last run from the previous pagination request. + * @param limit A limit on the number of runs to be returned in a single pagination response. + * @param order Sort order for runs by timestamp. Use `asc` for ascending order or `desc` for descending order. + * @param status Filter runs by their status. Possible values are `queued`, `in_progress`, `completed`, `canceled`, and `failed`. + */ + @get + @route("{eval_id}/runs") + @operationId("getEvalRuns") + @tag("Evals") + @summary("") + getEvalRuns( + @path eval_id: string, + @query after?: string, + @query limit?: int32 = 20, + @query order?: "asc" | "desc" = "asc", + @query status?: + | "queued" + | "in_progress" + | "completed" + | "canceled" + | "failed", + ): EvalRunList | EvalsErrorResponse; + + /** + * Create a new evaluation run, beginning the grading process. + * + * @param eval_id The ID of the evaluation to run. + */ + @post + @route("{eval_id}/runs") + @operationId("createEvalRun") + @tag("Evals") + createEvalRun(@path eval_id: string, @body body: CreateEvalRunRequest): { + @statusCode statusCode: 201; + ...EvalRun; + } | EvalsErrorResponse; + + /** + * Retrieve a specific evaluation run by its ID. + * + * @param eval_id The ID of the evaluation the run belongs to. + * @param run_id The ID of the evaluation run to retrieve. + */ + @get + @route("{eval_id}/runs/{run_id}") + @operationId("getEvalRun") + @tag("Evals") + getEvalRun( + @path eval_id: string, + @path run_id: string, + ): EvalRun | EvalsErrorResponse; + + /** + * Cancel a specific evaluation run by its ID. + * + * @param eval_id The ID of the evaluation the run belongs to. + * @param run_id The ID of the evaluation run to cancel. + */ + @post + @route("{eval_id}/runs/{run_id}") + @operationId("cancelEvalRun") + @tag("Evals") + cancelEvalRun( + @path eval_id: string, + @path run_id: string, + ): EvalRun | EvalsErrorResponse; + + /** + * Delete a specific evaluation run by its ID. + * + * @param eval_id The ID of the evaluation the run belongs to. + * @param run_id The ID of the evaluation run to delete. + */ + @delete + @route("{eval_id}/runs/{run_id}") + @operationId("deleteEvalRun") + @tag("Evals") + deleteEvalRun(@path eval_id: string, @path run_id: string): { + object: "eval_run.deleted"; + deleted: boolean; + eval_run_id: string; + } | EvalsErrorNotFoundResponse; + + /** + * Get a list of output items for a specified evaluation run. + * + * @param eval_id The ID of the evaluation the run belongs to. + * @param run_id The ID of the evaluation run to retrieve output items for. + * @param after Identifier for the last output item from the previous pagination request. + * @param limit A limit on the number of output items to be returned in a single pagination response. + * @param status Filter output items by their status. Possible values are `fail` and `pass`. + * @param order Sort order for output items by timestamp. Use `asc` for ascending order or `desc` for descending order. + */ + @get + @route("{eval_id}/runs/{run_id}/output_items") + @operationId("getEvalRunOutputItems") + @tag("Evals") + getEvalRunOutputItems( + @path eval_id: string, + @path run_id: string, + @query after?: string, + @query limit?: int32 = 20, + @query status?: "fail" | "pass", + @query order?: "asc" | "desc" = "asc", + ): EvalRunOutputItemList | EvalsErrorResponse; + + /** + * Retrieve a specific output item from an evaluation run by its ID. + * + * @param eval_id The ID of the evaluation the run belongs to. + * @param run_id The ID of the evaluation run the output item belongs to. + * @param output_item_id The ID of the output item to retrieve. + */ + @get + @route("{eval_id}/runs/{run_id}/output_items/{output_item_id}") + @operationId("getEvalRunOutputItem") + @tag("Evals") + getEvalRunOutputItem( + @path eval_id: string, + @path run_id: string, + @path output_item_id: string, + ): EvalRunOutputItem; +} + +@error +model EvalsErrorResponse { + @statusCode statusCode: 400; + ...Error; +} + +@error +model EvalsErrorNotFoundResponse { + @statusCode statusCode: 404; + ...Error; +} diff --git a/specification/base/typespec/files/main.tsp b/specification/base/typespec/files/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/files/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/files/models.tsp b/specification/base/typespec/files/models.tsp new file mode 100644 index 000000000..ed8f4a494 --- /dev/null +++ b/specification/base/typespec/files/models.tsp @@ -0,0 +1,102 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +model CreateFileRequest { + // Tool customization: Apply HttpPart for property in multipart request model + /** The File object (not file name) to be uploaded. */ + file: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The intended purpose of the uploaded file. One of: - `assistants`: Used in the Assistants API - `batch`: Used in the Batch API - `fine-tune`: Used for fine-tuning - `vision`: Images used for vision fine-tuning - `user_data`: Flexible file type for any purpose - `evals`: Used for eval data sets + """) + purpose: HttpPart< + | "assistants" + | "batch" + | "fine-tune" + | "vision" + | "user_data" + | "evals">; +} + +model ListFilesResponse { + // Tool customization: apply the strict 'list' object value instead of open 'string' + object: "list"; + + data: OpenAIFile[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model DeleteFileResponse { + id: string; + object: "file"; + deleted: boolean; +} + +@doc(""" + The `File` object represents a document that has been uploaded to OpenAI. + """) +model OpenAIFile { + /** The file identifier, which can be referenced in the API endpoints. */ + id: string; + + // Tool customization: file response values can have null byte counts + /** The size of the file, in bytes. */ + bytes: int64 | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the file was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the file will expire. */ + @encode("unixTimestamp", int32) + expires_at?: utcDateTime; + + /** The name of the file. */ + filename: string; + + @doc(""" + The object type, which is always `file`. + """) + object: "file"; + + // Tool customization: Add missing user_data and evals purposes + @doc(""" + The intended purpose of the file. Supported values are `assistants`, `assistants_output`, `batch`, `batch_output`, `fine-tune`, `fine-tune-results` and `vision`. + """) + purpose: + | "assistants" + | "assistants_output" + | "batch" + | "batch_output" + | "fine-tune" + | "fine-tune-results" + | "vision" + | "user_data" + | "evals"; + + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @doc(""" + Deprecated. The current status of the file, which can be either `uploaded`, `processed`, or `error`. + """) + status: "uploaded" | "processed" | "error"; + + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @doc(""" + Deprecated. For details on why a fine-tuning training file failed validation, see the `error` field on `fine_tuning.job`. + """) + status_details?: string; +} diff --git a/specification/base/typespec/files/operations.tsp b/specification/base/typespec/files/operations.tsp new file mode 100644 index 000000000..52099a35f --- /dev/null +++ b/specification/base/typespec/files/operations.tsp @@ -0,0 +1,78 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("files") +@tag("Files") +interface Files { + @get + @operationId("listFiles") + @summary("Returns a list of files that belong to the user's organization.") + listFiles( + @header accept: "application/json", + + // TODO: This is just a string in the OpenAPI spec. + /** Only return files with the given purpose. */ + @query purpose?: string, + ): ListFilesResponse | ErrorResponse; + + @post + @operationId("createFile") + @summary(""" + Upload a file that can be used across various endpoints. The size of all the files uploaded by + one organization can be up to 100 GB. + + The size of individual files can be a maximum of 512 MB or 2 million tokens for Assistants. See + the [Assistants Tools guide](/docs/assistants/tools) to learn more about the types of files + supported. The Fine-tuning API only supports `.jsonl` files. + + Please [contact us](https://help.openai.com/) if you need to increase these storage limits. + """) + createFile( + @header accept: "application/json", + @header contentType: "multipart/form-data", + @multipartBody requestBody: CreateFileRequest, + ): OpenAIFile | ErrorResponse; + + @route("{file_id}") + @delete + @operationId("deleteFile") + @summary("Delete a file") + deleteFile( + @header accept: "application/json", + + /** The ID of the file to use for this request. */ + @path file_id: string, + ): DeleteFileResponse | ErrorResponse; + + @route("{file_id}") + @get + @operationId("retrieveFile") + @summary("Returns information about a specific file.") + retrieveFile( + @header accept: "application/json", + + /** The ID of the file to use for this request. */ + @path file_id: string, + ): OpenAIFile | ErrorResponse; + + @route("{file_id}/content") + @get + @operationId("downloadFile") + @summary("Returns the contents of the specified file.") + // TODO: The OpenAPI spec says this returns a plain string but in reality it is returning + // the file content as bytes. + downloadFile( + @header accept: "application/json", + + /** The ID of the file to use for this request. */ + @path file_id: string, + ): bytes | ErrorResponse; +} diff --git a/specification/base/typespec/fine-tuning/custom.tsp b/specification/base/typespec/fine-tuning/custom.tsp new file mode 100644 index 000000000..71980a430 --- /dev/null +++ b/specification/base/typespec/fine-tuning/custom.tsp @@ -0,0 +1,61 @@ +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union CreateFineTuningJobRequestHyperparametersBatchSizeChoiceEnum { + auto: "auto", +} +union CreateFineTuningJobRequestHyperparametersBatchSizeOption { + CreateFineTuningJobRequestHyperparametersBatchSizeChoiceEnum, + int32, +} + +union CreateFineTuningJobRequestHyperparametersLearningRateMultiplierChoiceEnum { + auto: "auto", +} +union CreateFineTuningJobRequestHyperparametersLearningRateMultiplierOption { + CreateFineTuningJobRequestHyperparametersLearningRateMultiplierChoiceEnum, + float32, +} + +union CreateFineTuningJobRequestHyperparametersNEpochsChoiceEnum { + auto: "auto", +} +union CreateFineTuningJobRequestHyperparametersNEpochsOption { + CreateFineTuningJobRequestHyperparametersNEpochsChoiceEnum, + int32, +} + +union CreateFineTuningJobRequestHyperparametersBetaChoiceEnum { + auto: "auto", +} +union CreateFineTuningJobRequestHyperparametersBetaOption { + CreateFineTuningJobRequestHyperparametersLearningRateMultiplierChoiceEnum, + int32, +} + +@discriminator("type") +model CreateFineTuningJobRequestIntegration { + type: string | "wandb"; +} + +model CreateFineTuningJobRequestWandbIntegration + extends CreateFineTuningJobRequestIntegration { + type: "wandb"; + wandb: { + project: string; + name?: string | null; + entity?: string | null; + tags?: string[]; + }; +} + +@discriminator("type") +model FineTuningIntegration { + type: string | "wandb"; +} + +model FineTuningJobsPageToken { + limit?: int32; + after?: string; +} diff --git a/specification/base/typespec/fine-tuning/main.tsp b/specification/base/typespec/fine-tuning/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/fine-tuning/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/fine-tuning/models.tsp b/specification/base/typespec/fine-tuning/models.tsp new file mode 100644 index 000000000..7ed15d0fc --- /dev/null +++ b/specification/base/typespec/fine-tuning/models.tsp @@ -0,0 +1,531 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../chat"; +import "../common"; +import "../graders"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +model CreateFineTuningJobRequest { + /** + * The name of the model to fine-tune. You can select one of the + * [supported models](/docs/guides/fine-tuning#which-models-can-be-fine-tuned). + */ + @extension("x-oaiTypeLabel", "string") + `model`: + | string + | "babbage-002" + | "davinci-002" + | "gpt-3.5-turbo" + | "gpt-4o-mini"; + + @doc(""" + The ID of an uploaded file that contains training data. + + See [upload file](/docs/api-reference/files/create) for how to upload a file. + + Your dataset must be formatted as a JSONL file. Additionally, you must upload your file with the purpose `fine-tune`. + + The contents of the file should differ depending on if the model uses the [chat](/docs/api-reference/fine-tuning/chat-input), [completions](/docs/api-reference/fine-tuning/completions-input) format, or if the fine-tuning method uses the [preference](/docs/api-reference/fine-tuning/preference-input) format. + + See the [fine-tuning guide](/docs/guides/model-optimization) for more details. + """) + training_file: string; + + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @doc(""" + The hyperparameters used for the fine-tuning job. + This value is now deprecated in favor of `method`, and should be passed in under the `method` parameter. + """) + hyperparameters?: { + /** + * Number of examples in each batch. A larger batch size means that model parameters + * are updated less frequently, but with lower variance. + */ + batch_size?: "auto" | int32 = "auto"; + + /** + * Scaling factor for the learning rate. A smaller learning rate may be useful to avoid + * overfitting. + */ + learning_rate_multiplier?: "auto" | float32 = "auto"; + + /** + * The number of epochs to train the model for. An epoch refers to one full cycle + * through the training dataset. + */ + n_epochs?: "auto" | int32 = "auto"; + }; + + @doc(""" + A string of up to 64 characters that will be added to your fine-tuned model name. + + For example, a `suffix` of "custom-model-name" would produce a model name like `ft:gpt-4o-mini:openai:custom-model-name:7p4lURel`. + """) + @minLength(1) + @maxLength(64) + suffix?: string | null = null; + + @doc(""" + The ID of an uploaded file that contains validation data. + + If you provide this file, the data is used to generate validation + metrics periodically during fine-tuning. These metrics can be viewed in + the fine-tuning results file. + The same data should not be present in both train and validation files. + + Your dataset must be formatted as a JSONL file. You must upload your file with the purpose `fine-tune`. + + See the [fine-tuning guide](/docs/guides/model-optimization) for more details. + """) + validation_file?: string | null; + + // Tool customization: establish a discriminated type basis + /** A list of integrations to enable for your fine-tuning job. */ + integrations?: CreateFineTuningJobRequestIntegration[] | null; + + /** + * The seed controls the reproducibility of the job. Passing in the same seed and job parameters should produce the same results, but may differ in rare cases. + * If a seed is not specified, one will be generated for you. + */ + @minValue(0) + @maxValue(2147483647) + seed?: int32 | null; + + method?: FineTuneMethod; + ...MetadataPropertyForRequest; +} + +model ListPaginatedFineTuningJobsResponse { + data: FineTuningJob[]; + has_more: boolean; + object: "list"; +} + +model ListFineTuningJobEventsResponse { + data: FineTuningJobEvent[]; + object: "list"; + has_more: boolean; +} + +model ListFineTuningJobCheckpointsResponse { + data: FineTuningJobCheckpoint[]; + object: "list"; + first_id?: string | null; + last_id?: string | null; + has_more: boolean; +} + +// Tool customization: Represent undocumented response 'user_provided_suffix' property +@doc(""" + The `fine_tuning.job` object represents a fine-tuning job that has been created through the API. + """) +model FineTuningJob { + /** The descriptive suffix applied to the job, as specified in the job creation request. */ + user_provided_suffix?: string | null; + + /** The object identifier, which can be referenced in the API endpoints. */ + id: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the fine-tuning job was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + @doc(""" + For fine-tuning jobs that have `failed`, this will contain more information on the cause of the failure. + """) + error: { + /** A machine-readable error code. */ + code: string; + + /** A human-readable error message. */ + message: string; + + @doc(""" + The parameter that was invalid, usually `training_file` or `validation_file`. This field will be null if the failure was not parameter-specific. + """) + param: string | null; + } | null; + + /** The name of the fine-tuned model that is being created. The value will be null if the fine-tuning job is still running. */ + fine_tuned_model: string | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the fine-tuning job was finished. The value will be null if the fine-tuning job is still running. */ + @encode("unixTimestamp", int32) + finished_at: utcDateTime | null; + + @doc(""" + The hyperparameters used for the fine-tuning job. This value will only be returned when running `supervised` jobs. + """) + hyperparameters: { + /** + * Number of examples in each batch. A larger batch size means that model parameters + * are updated less frequently, but with lower variance. + */ + batch_size?: "auto" | int32 | null = "auto"; + + /** + * Scaling factor for the learning rate. A smaller learning rate may be useful to avoid + * overfitting. + */ + learning_rate_multiplier?: "auto" | float32 = "auto"; + + /** + * The number of epochs to train the model for. An epoch refers to one full cycle + * through the training dataset. + */ + n_epochs?: "auto" | int32 = "auto"; + }; + + /** The base model that is being fine-tuned. */ + `model`: string; + + /** The object type, which is always "fine_tuning.job". */ + object: "fine_tuning.job"; + + /** The organization that owns the fine-tuning job. */ + organization_id: string; + + /** The compiled results file ID(s) for the fine-tuning job. You can retrieve the results with the [Files API](/docs/api-reference/files/retrieve-contents). */ + result_files: string[]; + + @doc(""" + The current status of the fine-tuning job, which can be either `validating_files`, `queued`, `running`, `succeeded`, `failed`, or `cancelled`. + """) + status: + | "validating_files" + | "queued" + | "running" + | "succeeded" + | "failed" + | "cancelled"; + + /** The total number of billable tokens processed by this fine-tuning job. The value will be null if the fine-tuning job is still running. */ + trained_tokens: int32 | null; + + /** The file ID used for training. You can retrieve the training data with the [Files API](/docs/api-reference/files/retrieve-contents). */ + training_file: string; + + /** The file ID used for validation. You can retrieve the validation results with the [Files API](/docs/api-reference/files/retrieve-contents). */ + validation_file: string | null; + + /** A list of integrations to enable for this fine-tuning job. */ + // Tool note: can't automatically apply to nullable: @maxItems(5) + integrations?: FineTuningIntegration[] | null; + + /** The seed used for the fine-tuning job. */ + seed: int32; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the fine-tuning job is estimated to finish. The value will be null if the fine-tuning job is not running. */ + @encode("unixTimestamp", int32) + estimated_finish?: utcDateTime | null; + + method?: FineTuneMethod; + ...MetadataPropertyForResponse; +} + +// Tool customization (apply_discriminator): Convert to instantiation of discriminated type +model FineTuningIntegrationWandb extends FineTuningIntegration { + /** The type of the integration being enabled for the fine-tuning job */ + type: "wandb"; + + /** + * The settings for your integration with Weights and Biases. This payload specifies the project that + * metrics will be sent to. Optionally, you can set an explicit display name for your run, add tags + * to your run, and set a default entity (team, username, etc) to be associated with your run. + */ + wandb: { + /** The name of the project that the new run will be created under. */ + project: string; + + /** A display name to set for the run. If not set, we will use the Job ID as the name. */ + name?: string | null; + + /** + * The entity to use for the run. This allows you to set the team or username of the WandB user that you would + * like associated with the run. If not set, the default entity for the registered WandB API key is used. + */ + entity?: string | null; + + /** + * A list of tags to be attached to the newly created run. These tags are passed through directly to WandB. Some + * default tags are generated by OpenAI: "openai/finetune", "openai/{base-model}", "openai/{ftjob-abcdef}". + */ + tags?: string[]; + }; +} + +/** Fine-tuning job event object */ +model FineTuningJobEvent { + /** The object type, which is always "fine_tuning.job.event". */ + object: "fine_tuning.job.event"; + + /** The object identifier. */ + id: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the fine-tuning job was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The log level of the event. */ + level: "info" | "warn" | "error"; + + /** The message of the event. */ + message: string; + + /** The type of event. */ + type?: "message" | "metrics"; + + /** The data associated with the event. */ + data?: unknown; +} + +@doc(""" + The `fine_tuning.job.checkpoint` object represents a model checkpoint for a fine-tuning job that is ready to use. + """) +model FineTuningJobCheckpoint { + /** The checkpoint identifier, which can be referenced in the API endpoints. */ + id: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the checkpoint was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The name of the fine-tuned checkpoint model that is created. */ + fine_tuned_model_checkpoint: string; + + /** The step number that the checkpoint was created at. */ + step_number: int32; + + /** Metrics at the step number during the fine-tuning job. */ + metrics: { + step?: float32; + train_loss?: float32; + train_mean_token_accuracy?: float32; + valid_loss?: float32; + valid_mean_token_accuracy?: float32; + full_valid_loss?: float32; + full_valid_mean_token_accuracy?: float32; + }; + + /** The name of the fine-tuning job that this checkpoint was created from. */ + fine_tuning_job_id: string; + + /** The object type, which is always "fine_tuning.job.checkpoint". */ + object: "fine_tuning.job.checkpoint"; +} + +model FineTuneChatCompletionRequestAssistantMessage { + /** Controls whether the assistant message is trained against (0 or 1) */ + weight?: "0" | "1"; + + ...ChatCompletionRequestAssistantMessage; +} + +/** The per-line training example of a fine-tuning input file for chat models using the supervised method. */ +model FineTuneChatRequestInput { + #suppress "deprecated" "Warning unnecessary for inner spec representation of deprecated type" + @minItems(1) + messages?: ( + | ChatCompletionRequestSystemMessage + | ChatCompletionRequestUserMessage + | FineTuneChatCompletionRequestAssistantMessage + | ChatCompletionRequestToolMessage + | ChatCompletionRequestFunctionMessage)[]; + + /** A list of tools the model may generate JSON inputs for. */ + tools?: ChatCompletionTool[]; + + parallel_tool_calls?: ParallelToolCalls = true; + + /** A list of functions the model may generate JSON inputs for. */ + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @minItems(1) + @maxItems(128) + functions?: ChatCompletionFunctions[]; +} + +/** Configuration for the DPO fine-tuning method. */ +model FineTuneDPOMethod { + hyperparameters?: FineTuneDPOHyperparameters; +} + +/** The method used for fine-tuning. */ +model FineTuneMethod { + @doc(""" + The type of method. Is either `supervised`, `dpo`, or `reinforcement`. + """) + type: "supervised" | "dpo" | "reinforcement"; + + supervised?: FineTuneSupervisedMethod; + dpo?: FineTuneDPOMethod; + reinforcement?: FineTuneReinforcementMethod; +} + +/** The per-line training example of a fine-tuning input file for chat models using the dpo method. */ +model FineTunePreferenceRequestInput { + input?: { + #suppress "deprecated" "Warning unnecessary for inner spec representation of deprecated type" + @minItems(1) + messages?: ( + | ChatCompletionRequestSystemMessage + | ChatCompletionRequestUserMessage + | FineTuneChatCompletionRequestAssistantMessage + | ChatCompletionRequestToolMessage + | ChatCompletionRequestFunctionMessage)[]; + + /** A list of tools the model may generate JSON inputs for. */ + tools?: ChatCompletionTool[]; + + parallel_tool_calls?: ParallelToolCalls = true; + }; + + /** The preferred completion message for the output. */ + @maxItems(1) + preferred_output?: ChatCompletionRequestAssistantMessage[]; + + /** The non-preferred completion message for the output. */ + @maxItems(1) + non_preferred_output?: ChatCompletionRequestAssistantMessage[]; +} + +/** Configuration for the supervised fine-tuning method. */ +model FineTuneSupervisedMethod { + hyperparameters?: FineTuneSupervisedHyperparameters; +} + +/** The hyperparameters used for the DPO fine-tuning job. */ +model FineTuneDPOHyperparameters { + /** The beta value for the DPO method. A higher beta value will increase the weight of the penalty between the policy and reference model. */ + beta?: "auto" | float32 = "auto"; + + /** Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance. */ + batch_size?: "auto" | int32 = "auto"; + + /** Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting. */ + learning_rate_multiplier?: "auto" | float32 = "auto"; + + /** The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. */ + n_epochs?: "auto" | int32 = "auto"; +} + +/** The hyperparameters used for the reinforcement fine-tuning job. */ +model FineTuneReinforcementHyperparameters { + /** Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance. */ + batch_size?: "auto" | int32 = "auto"; + + /** Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting. */ + learning_rate_multiplier?: "auto" | float32 = "auto"; + + /** The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. */ + n_epochs?: "auto" | int32 = "auto"; + + /** Level of reasoning effort. */ + reasoning_effort?: "default" | "low" | "medium" | "high" = "default"; + + /** Multiplier on amount of compute used for exploring search space during training. */ + compute_multiplier?: "auto" | float32 = "auto"; + + /** The number of training steps between evaluation runs. */ + eval_interval?: "auto" | int32 = "auto"; + + /** Number of evaluation samples to generate per training step. */ + eval_samples?: "auto" | int32 = "auto"; +} + +/** Configuration for the reinforcement fine-tuning method. */ +model FineTuneReinforcementMethod { + /** The grader used for the fine-tuning job. */ + grader: + | GraderStringCheck + | GraderTextSimilarity + | GraderPython + | GraderScoreModel + | GraderMulti; + + hyperparameters?: FineTuneReinforcementHyperparameters; +} + +@doc(""" + Per-line training example for reinforcement fine-tuning. Note that `messages` and `tools` are the only reserved keywords. Any other arbitrary key-value data can be included on training datapoints and will be available to reference during grading under the `{{ item.XXX }}` template variable. + """) +model FineTuneReinforcementRequestInput { + @minItems(1) + messages: ( + | ChatCompletionRequestDeveloperMessage + | ChatCompletionRequestUserMessage + | FineTuneChatCompletionRequestAssistantMessage + | ChatCompletionRequestToolMessage)[]; + + /** A list of tools the model may generate JSON inputs for. */ + tools?: ChatCompletionTool[]; +} + +/** The hyperparameters used for the fine-tuning job. */ +model FineTuneSupervisedHyperparameters { + /** Number of examples in each batch. A larger batch size means that model parameters are updated less frequently, but with lower variance. */ + batch_size?: "auto" | int32 = "auto"; + + /** Scaling factor for the learning rate. A smaller learning rate may be useful to avoid overfitting. */ + learning_rate_multiplier?: "auto" | float32 = "auto"; + + /** The number of epochs to train the model for. An epoch refers to one full cycle through the training dataset. */ + n_epochs?: "auto" | int32 = "auto"; +} + +model CreateFineTuningCheckpointPermissionRequest { + /** The project identifiers to grant access to. */ + project_ids: string[]; +} + +model DeleteFineTuningCheckpointPermissionResponse { + /** The ID of the fine-tuned model checkpoint permission that was deleted. */ + id: string; + + /** The object type, which is always "checkpoint.permission". */ + object: "checkpoint.permission"; + + /** Whether the fine-tuned model checkpoint permission was successfully deleted. */ + deleted: boolean; +} + +@doc(""" + The `checkpoint.permission` object represents a permission for a fine-tuned model checkpoint. + """) +model FineTuningCheckpointPermission { + /** The permission identifier, which can be referenced in the API endpoints. */ + id: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the permission was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The project identifier that the permission is for. */ + project_id: string; + + /** The object type, which is always "checkpoint.permission". */ + object: "checkpoint.permission"; +} + +model ListFineTuningCheckpointPermissionResponse { + data: FineTuningCheckpointPermission[]; + object: "list"; + first_id?: string | null; + last_id?: string | null; + has_more: boolean; +} diff --git a/specification/base/typespec/fine-tuning/operations.tsp b/specification/base/typespec/fine-tuning/operations.tsp new file mode 100644 index 000000000..bdf7b1445 --- /dev/null +++ b/specification/base/typespec/fine-tuning/operations.tsp @@ -0,0 +1,173 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("fine_tuning") +@tag("Fine-tuning") +interface FineTuning { + @get + @route("checkpoints/{fine_tuned_model_checkpoint}/permissions") + @operationId("listFineTuningCheckpointPermissions") + @summary(""" + NOTE: This endpoint requires an admin API key. + Organization owners can use this endpoint to view all permissions for a fine-tuned model checkpoint. + """) + listFineTuningCheckpointPermissions( + /** The ID of the fine-tuned model checkpoint to get permissions for. */ + @path fine_tuned_model_checkpoint: string, + + ...PageAfterQueryParameter, + ...PageLimitQueryParameter, + ...PageOrderQueryParameter, + + /** The ID of the project to get permissions for. */ + @query project_id?: string, + ): ListFineTuningCheckpointPermissionResponse | ErrorResponse; + + @post + @route("checkpoints/{fine_tuned_model_checkpoint}/permissions") + @operationId("createFineTuningCheckpointPermission") + @summary(""" + NOTE: This endpoint requires an admin API key. + This enables organization owners to share fine-tuned models with other projects in their organization. + """) + createFineTuningCheckpointPermission( + /** The ID of the fine-tuned model checkpoint to create a permission for. */ + @path fine_tuned_model_checkpoint: string, + + ...CreateFineTuningCheckpointPermissionRequest, + ): ListFineTuningCheckpointPermissionResponse | ErrorResponse; + + @delete + @route("checkpoints/{fine_tuned_model_checkpoint}/permissions/{permission_id}") + @operationId("deleteFineTuningCheckpointPermission") + @summary(""" + NOTE: This endpoint requires an admin API key. + Organization owners can use this endpoint to delete a permission for a fine-tuned model checkpoint. + """) + deleteFineTuningCheckpointPermission( + /** The ID of the fine-tuned model checkpoint to delete a permission for. */ + @path fine_tuned_model_checkpoint: string, + + /** The ID of the permission to delete. */ + @path permission_id: string, + ): DeleteFineTuningCheckpointPermissionResponse | ErrorResponse; + + @route("jobs") + @post + @operationId("createFineTuningJob") + @summary(""" + Creates a fine-tuning job which begins the process of creating a new model from a given dataset. + + Response includes details of the enqueued job including job status and the name of the fine-tuned models once complete. + + [Learn more about fine-tuning](/docs/guides/fine-tuning) + """) + createFineTuningJob( + @header accept: "application/json", + @body requestBody: CreateFineTuningJobRequest, + ): FineTuningJob | ErrorResponse; + + @route("jobs") + @get + @operationId("listPaginatedFineTuningJobs") + @summary("List your organization's fine-tuning jobs") + listPaginatedFineTuningJobs( + @header accept: "application/json", + + /** Identifier for the last job from the previous pagination request. */ + @query after?: string, + + /** Number of fine-tuning jobs to retrieve. */ + @query limit?: int32 = 20, + ): ListPaginatedFineTuningJobsResponse | ErrorResponse; + + @route("jobs/{fine_tuning_job_id}") + @get + @operationId("retrieveFineTuningJob") + @summary(""" + Get info about a fine-tuning job. + + [Learn more about fine-tuning](/docs/guides/fine-tuning) + """) + retrieveFineTuningJob( + @header accept: "application/json", + + /** The ID of the fine-tuning job. */ + @path fine_tuning_job_id: string, + ): FineTuningJob | ErrorResponse; + + @route("jobs/{fine_tuning_job_id}/cancel") + @post + @operationId("cancelFineTuningJob") + @summary("Immediately cancel a fine-tune job.") + cancelFineTuningJob( + @header accept: "application/json", + + /** The ID of the fine-tuning job to cancel. */ + @path fine_tuning_job_id: string, + ): FineTuningJob | ErrorResponse; + + @route("jobs/{fine_tuning_job_id}/checkpoints") + @get + @operationId("listFineTuningJobCheckpoints") + @summary("List the checkpoints for a fine-tuning job.") + listFineTuningJobCheckpoints( + @header accept: "application/json", + + /** The ID of the fine-tuning job to get checkpoints for. */ + @path fine_tuning_job_id: string, + + /** Identifier for the last checkpoint ID from the previous pagination request. */ + @query after?: string, + + /** Number of checkpoints to retrieve. */ + @query limit?: int32 = 10, + ): ListFineTuningJobCheckpointsResponse | ErrorResponse; + + @route("jobs/{fine_tuning_job_id}/events") + @get + @operationId("listFineTuningEvents") + @summary("Get status updates for a fine-tuning job.") + listFineTuningEvents( + @header accept: "application/json", + + /** The ID of the fine-tuning job to get events for. */ + @path fine_tuning_job_id: string, + + /** Identifier for the last event from the previous pagination request. */ + @query after?: string, + + /** Number of events to retrieve. */ + @query limit?: int32 = 20, + ): ListFineTuningJobEventsResponse | ErrorResponse; + + @post + @route("jobs/{fine_tuning_job_id}/pause") + @operationId("pauseFineTuningJob") + @summary(""" + Pause a fine-tune job. + """) + pauseFineTuningJob( + /** The ID of the fine-tuning job to pause. */ + @path fine_tuning_job_id: string, + ): FineTuningJob | ErrorResponse; + + @post + @route("jobs/{fine_tuning_job_id}/resume") + @operationId("resumeFineTuningJob") + @summary(""" + Resume a paused fine-tune job. + """) + resumeFineTuningJob( + /** The ID of the fine-tuning job to resume. */ + @path fine_tuning_job_id: string, + ): FineTuningJob | ErrorResponse; +} diff --git a/specification/base/typespec/graders/custom.tsp b/specification/base/typespec/graders/custom.tsp new file mode 100644 index 000000000..0f7f0d0d4 --- /dev/null +++ b/specification/base/typespec/graders/custom.tsp @@ -0,0 +1,15 @@ +namespace OpenAI; + +union GraderType { + string_check: "string_check", + text_similarity: "text_similarity", + score_model: "score_model", + label_model: "label_model", + python: "python", + multi: "multi", +} + +@discriminator("type") +model Grader { + type: GraderType; +} diff --git a/specification/base/typespec/graders/main.tsp b/specification/base/typespec/graders/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/graders/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/graders/models.tsp b/specification/base/typespec/graders/models.tsp new file mode 100644 index 000000000..8bf3b72f5 --- /dev/null +++ b/specification/base/typespec/graders/models.tsp @@ -0,0 +1,232 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../evals"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool customization (apply_discriminator): Use discriminated type +/** + * A LabelModelGrader object which uses a model to assign labels to each item + * in the evaluation. + */ +model GraderLabelModel extends Grader { + @doc(""" + The object type, which is always `label_model`. + """) + type: GraderType.label_model; + + /** The name of the grader. */ + name: string; + + /** The model to use for the evaluation. Must support structured outputs. */ + `model`: string; + + input: EvalItem[]; + + /** The labels to assign to each item in the evaluation. */ + labels: string[]; + + /** The labels that indicate a passing result. Must be a subset of labels. */ + passing_labels: string[]; +} + +// Tool customization (apply_discriminator): Use discriminated type +/** A MultiGrader object combines the output of multiple graders to produce a single score. */ +model GraderMulti extends Grader { + @doc(""" + The object type, which is always `multi`. + """) + type: GraderType.multi; + + /** The name of the grader. */ + name: string; + + graders: + | GraderStringCheck + | GraderTextSimilarity + | GraderPython + | GraderScoreModel + | GraderLabelModel; + + /** A formula to calculate the output based on grader results. */ + calculate_output: string; +} + +// Tool customization (apply_discriminator): Use discriminated type +/** A PythonGrader object that runs a python script on the input. */ +model GraderPython extends Grader { + @doc(""" + The object type, which is always `python`. + """) + type: GraderType.python; + + /** The name of the grader. */ + name: string; + + /** The source code of the python script. */ + source: string; + + /** The image tag to use for the python script. */ + image_tag?: string; +} + +// Tool customization (apply_discriminator): Use discriminated type +/** A ScoreModelGrader object that uses a model to assign a score to the input. */ +model GraderScoreModel extends Grader { + @doc(""" + The object type, which is always `score_model`. + """) + type: GraderType.score_model; + + /** The name of the grader. */ + name: string; + + /** The model to use for the evaluation. */ + `model`: string; + + /** The sampling parameters for the model. */ + sampling_params?: unknown; + + /** The input text. This may include template strings. */ + input: EvalItem[]; + + @doc(""" + The range of the score. Defaults to `[0, 1]`. + """) + range?: float32[]; +} + +// Tool customization (apply_discriminator): Use discriminated type +/** A StringCheckGrader object that performs a string comparison between input and reference using a specified operation. */ +model GraderStringCheck extends Grader { + @doc(""" + The object type, which is always `string_check`. + """) + type: GraderType.string_check; + + /** The name of the grader. */ + name: string; + + /** The input text. This may include template strings. */ + input: string; + + /** The reference text. This may include template strings. */ + reference: string; + + @doc(""" + The string check operation to perform. One of `eq`, `ne`, `like`, or `ilike`. + """) + operation: "eq" | "ne" | "like" | "ilike"; +} + +// Tool customization (apply_discriminator): Use discriminated type +/** A TextSimilarityGrader object which grades text based on similarity metrics. */ +model GraderTextSimilarity extends Grader { + /** The type of grader. */ + type: GraderType.text_similarity; + + /** The name of the grader. */ + name: string; + + /** The text being graded. */ + input: string; + + /** The text being graded against. */ + reference: string; + + @doc(""" + The evaluation metric to use. One of `fuzzy_match`, `bleu`, `gleu`, `meteor`, `rouge_1`, `rouge_2`, `rouge_3`, `rouge_4`, `rouge_5`, or `rouge_l`. + """) + evaluation_metric: + | "fuzzy_match" + | "bleu" + | "gleu" + | "meteor" + | "rouge_1" + | "rouge_2" + | "rouge_3" + | "rouge_4" + | "rouge_5" + | "rouge_l"; +} + +model RunGraderRequest { + /** The grader used for the fine-tuning job. */ + grader: + | GraderStringCheck + | GraderTextSimilarity + | GraderPython + | GraderScoreModel + | GraderMulti; + + @doc(""" + The dataset item provided to the grader. This will be used to populate + the `item` namespace. See [the guide](/docs/guides/graders) for more details. + """) + item?: unknown; + + @doc(""" + The model sample to be evaluated. This value will be used to populate + the `sample` namespace. See [the guide](/docs/guides/graders) for more details. + The `output_json` variable will be populated if the model sample is a + valid JSON string. + """) + model_sample: string; +} + +model RunGraderResponse { + reward: float32; + metadata: { + name: string; + type: string; + errors: { + formula_parse_error: boolean; + sample_parse_error: boolean; + truncated_observation_error: boolean; + unresponsive_reward_error: boolean; + invalid_variable_error: boolean; + other_error: boolean; + python_grader_server_error: boolean; + python_grader_server_error_type: string | null; + python_grader_runtime_error: boolean; + python_grader_runtime_error_details: string | null; + model_grader_server_error: boolean; + model_grader_refusal_error: boolean; + model_grader_parse_error: boolean; + model_grader_server_error_details: string | null; + }; + execution_time: float32; + scores: unknown; + token_usage: int32 | null; + sampled_model_name: string | null; + }; + sub_rewards: unknown; + model_grader_token_usage_per_model: unknown; +} + +model ValidateGraderRequest { + /** The grader used for the fine-tuning job. */ + grader: + | GraderStringCheck + | GraderTextSimilarity + | GraderPython + | GraderScoreModel + | GraderMulti; +} + +model ValidateGraderResponse { + /** The grader used for the fine-tuning job. */ + grader?: + | GraderStringCheck + | GraderTextSimilarity + | GraderPython + | GraderScoreModel + | GraderMulti; +} diff --git a/specification/base/typespec/graders/operations.tsp b/specification/base/typespec/graders/operations.tsp new file mode 100644 index 000000000..c6e313e9c --- /dev/null +++ b/specification/base/typespec/graders/operations.tsp @@ -0,0 +1,26 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("fine_tuning/alpha/graders") +@tag("Fine-tuning") +interface Graders { + @post + @route("run") + @operationId("runGrader") + @summary("Run a grader.") + runGrader(@body request: RunGraderRequest): RunGraderResponse; + + @post + @route("validate") + @operationId("validateGrader") + @summary("Validate a grader.") + validateGrader(@body request: ValidateGraderRequest): ValidateGraderResponse; +} diff --git a/specification/base/typespec/images/custom.tsp b/specification/base/typespec/images/custom.tsp new file mode 100644 index 000000000..0921a9c8e --- /dev/null +++ b/specification/base/typespec/images/custom.tsp @@ -0,0 +1,9 @@ +import "../common"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@minValue(1) +@maxValue(10) +scalar OneToTenInt extends int32; diff --git a/specification/base/typespec/images/main.tsp b/specification/base/typespec/images/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/images/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/images/models.tsp b/specification/base/typespec/images/models.tsp new file mode 100644 index 000000000..edcb063e3 --- /dev/null +++ b/specification/base/typespec/images/models.tsp @@ -0,0 +1,272 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +model CreateImageRequest { + @doc(""" + A text description of the desired image(s). The maximum length is 32000 characters for `gpt-image-1`, 1000 characters for `dall-e-2` and 4000 characters for `dall-e-3`. + """) + prompt: string; + + @doc(""" + The model to use for image generation. One of `dall-e-2`, `dall-e-3`, or `gpt-image-1`. Defaults to `dall-e-2` unless a parameter specific to `gpt-image-1` is used. + """) + @extension("x-oaiTypeLabel", "string") + `model`?: + | string + | "dall-e-2" + | "dall-e-3" + | "gpt-image-1" + | null = "dall-e-2"; + + @doc(""" + The number of images to generate. Must be between 1 and 10. For `dall-e-3`, only `n=1` is supported. + """) + @minValue(1) + @maxValue(10) + n?: int32 | null = 1; + + @doc(""" + The quality of the image that will be generated. + + - `auto` (default value) will automatically select the best quality for the given model. + - `high`, `medium` and `low` are supported for `gpt-image-1`. + - `hd` and `standard` are supported for `dall-e-3`. + - `standard` is the only option for `dall-e-2`. + """) + quality?: + | "standard" + | "hd" + | "low" + | "medium" + | "high" + | "auto" + | null = "auto"; + + @doc(""" + The format in which generated images with `dall-e-2` and `dall-e-3` are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. This parameter isn't supported for `gpt-image-1` which will always return base64-encoded images. + """) + response_format?: "url" | "b64_json" | null = "url"; + + @doc(""" + The format in which the generated images are returned. This parameter is only supported for `gpt-image-1`. Must be one of `png`, `jpeg`, or `webp`. + """) + output_format?: "png" | "jpeg" | "webp" | null = "png"; + + @doc(""" + The compression level (0-100%) for the generated images. This parameter is only supported for `gpt-image-1` with the `webp` or `jpeg` output formats, and defaults to 100. + """) + output_compression?: int32 | null = 100; + + @doc(""" + The size of the generated images. Must be one of `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto` (default value) for `gpt-image-1`, one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`, and one of `1024x1024`, `1792x1024`, or `1024x1792` for `dall-e-3`. + """) + size?: + | "auto" + | "1024x1024" + | "1536x1024" + | "1024x1536" + | "256x256" + | "512x512" + | "1792x1024" + | "1024x1792" + | null = "auto"; + + @doc(""" + Control the content-moderation level for images generated by `gpt-image-1`. Must be either `low` for less restrictive filtering or `auto` (default value). + """) + moderation?: "low" | "auto" | null = "auto"; + + @doc(""" + Allows to set transparency for the background of the generated image(s). + This parameter is only supported for `gpt-image-1`. Must be one of + `transparent`, `opaque` or `auto` (default value). When `auto` is used, the + model will automatically determine the best background for the image. + + If `transparent`, the output format needs to support transparency, so it + should be set to either `png` (default value) or `webp`. + """) + background?: "transparent" | "opaque" | "auto" | null = "auto"; + + @doc(""" + The style of the generated images. This parameter is only supported for `dall-e-3`. Must be one of `vivid` or `natural`. Vivid causes the model to lean towards generating hyper-real and dramatic images. Natural causes the model to produce more natural, less hyper-real looking images. + """) + style?: "vivid" | "natural" | null = "vivid"; + + /** A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids). */ + user?: string; +} + +model CreateImageEditRequest { + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The image(s) to edit. Must be a supported image file or an array of images. + + For `gpt-image-1`, each image should be a `png`, `webp`, or `jpg` file less + than 50MB. You can provide up to 16 images. + + For `dall-e-2`, you can only provide one image, and it should be a square + `png` file less than 4MB. + """) + image: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + A text description of the desired image(s). The maximum length is 1000 characters for `dall-e-2`, and 32000 characters for `gpt-image-1`. + """) + prompt: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where `image` should be edited. If there are multiple images provided, the mask will be applied on the first image. Must be a valid PNG file, less than 4MB, and have the same dimensions as `image`. + """) + mask?: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + Allows to set transparency for the background of the generated image(s). + This parameter is only supported for `gpt-image-1`. Must be one of + `transparent`, `opaque` or `auto` (default value). When `auto` is used, the + model will automatically determine the best background for the image. + + If `transparent`, the output format needs to support transparency, so it + should be set to either `png` (default value) or `webp`. + """) + background?: HttpPart<"transparent" | "opaque" | "auto" | null>; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The model to use for image generation. Only `dall-e-2` and `gpt-image-1` are supported. Defaults to `dall-e-2` unless a parameter specific to `gpt-image-1` is used. + """) + @extension("x-oaiTypeLabel", "string") + `model`?: HttpPart; + + // Tool customization: Use scenario-specific composed union and apply HttpPart for property in multipart request model + /** The number of images to generate. Must be between 1 and 10. */ + n?: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The size of the generated images. Must be one of `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto` (default value) for `gpt-image-1`, and one of `256x256`, `512x512`, or `1024x1024` for `dall-e-2`. + """) + size?: HttpPart< + | "256x256" + | "512x512" + | "1024x1024" + | "1536x1024" + | "1024x1536" + | "auto" + | null>; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. This parameter is only supported for `dall-e-2`, as `gpt-image-1` will always return base64-encoded images. + """) + response_format?: HttpPart<"url" | "b64_json" | null>; + + // Tool customization: Apply HttpPart for property in multipart request model + /** A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids). */ + user?: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The quality of the image that will be generated. `high`, `medium` and `low` are only supported for `gpt-image-1`. `dall-e-2` only supports `standard` quality. Defaults to `auto`. + """) + quality?: HttpPart<"standard" | "low" | "medium" | "high" | "auto" | null>; +} + +model CreateImageVariationRequest { + // Tool customization: Apply HttpPart for property in multipart request model + /** The image to use as the basis for the variation(s). Must be a valid PNG file, less than 4MB, and square. */ + image: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The model to use for image generation. Only `dall-e-2` is supported at this time. + """) + @extension("x-oaiTypeLabel", "string") + `model`?: HttpPart; + + // Tool customization: Use scenario-specific composed union and apply HttpPart for property in multipart request model + /** The number of images to generate. Must be between 1 and 10. */ + n?: HttpPart; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The format in which the generated images are returned. Must be one of `url` or `b64_json`. URLs are only valid for 60 minutes after the image has been generated. + """) + response_format?: HttpPart<"url" | "b64_json" | null>; + + // Tool customization: Apply HttpPart for property in multipart request model + @doc(""" + The size of the generated images. Must be one of `256x256`, `512x512`, or `1024x1024`. + """) + size?: HttpPart<"256x256" | "512x512" | "1024x1024" | null>; + + // Tool customization: Apply HttpPart for property in multipart request model + /** A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. [Learn more](/docs/guides/safety-best-practices#end-user-ids). */ + user?: HttpPart; +} + +/** The response from the image generation endpoint. */ +model ImagesResponse { + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) of when the image was created. */ + @encode("unixTimestamp", int32) + created: utcDateTime; + + /** The list of generated images. */ + data?: Image[]; + + @doc(""" + For `gpt-image-1` only, the token usage information for the image generation. + """) + usage?: { + /** The total number of tokens (images and text) used for the image generation. */ + total_tokens: int32; + + /** The number of tokens (images and text) in the input prompt. */ + input_tokens: int32; + + /** The number of image tokens in the output image. */ + output_tokens: int32; + + /** The input tokens detailed information for the image generation. */ + input_tokens_details: { + /** The number of text tokens in the input prompt. */ + text_tokens: int32; + + /** The number of image tokens in the input prompt. */ + image_tokens: int32; + }; + }; +} + +/** Represents the content or the URL of an image generated by the OpenAI API. */ +model Image { + // Tool customization: base64 input uses an encoded bytes type + @doc(""" + The base64-encoded JSON of the generated image. Default value for `gpt-image-1`, and only present if `response_format` is set to `b64_json` for `dall-e-2` and `dall-e-3`. + """) + @encode("base64", string) + b64_json?: bytes; + + // Tool customization: url uses the url type + @doc(""" + When using `dall-e-2` or `dall-e-3`, the URL of the generated image if `response_format` is set to `url` (default value). Unsupported for `gpt-image-1`. + """) + url?: url; + + @doc(""" + For `dall-e-3` only, the revised prompt that was used to generate the image. + """) + revised_prompt?: string; +} diff --git a/specification/base/typespec/images/operations.tsp b/specification/base/typespec/images/operations.tsp new file mode 100644 index 000000000..4a73eea92 --- /dev/null +++ b/specification/base/typespec/images/operations.tsp @@ -0,0 +1,45 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common/models.tsp"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/images") +interface Images { + @route("generations") + @post + @operationId("createImage") + @tag("Images") + @summary("Creates an image given a prompt") + createImage( + @header accept: "application/json", + @body requestBody: CreateImageRequest, + ): ImagesResponse | ErrorResponse; + + @route("edits") + @post + @operationId("createImageEdit") + @tag("Images") + @summary("Creates an edited or extended image given an original image and a prompt.") + createImageEdit( + @header accept: "application/json", + @header contentType: "multipart/form-data", + @multipartBody requestBody: CreateImageEditRequest, + ): ImagesResponse | ErrorResponse; + + @route("variations") + @post + @operationId("createImageVariation") + @tag("Images") + @summary("Creates an edited or extended image given an original image and a prompt.") + createImageVariation( + @header accept: "application/json", + @header contentType: "multipart/form-data", + @multipartBody requestBody: CreateImageVariationRequest, + ): ImagesResponse | ErrorResponse; +} diff --git a/specification/base/typespec/main.tsp b/specification/base/typespec/main.tsp new file mode 100644 index 000000000..2cc2be670 --- /dev/null +++ b/specification/base/typespec/main.tsp @@ -0,0 +1,22 @@ +import "./administration"; +import "./audio"; +import "./assistants"; +import "./batch"; +import "./chat"; +import "./completions"; +import "./containers"; +import "./embeddings"; +import "./evals"; +import "./files"; +import "./fine-tuning"; +import "./graders"; +import "./images"; +import "./messages"; +import "./models"; +import "./moderations"; +import "./realtime"; +import "./runs"; +import "./threads"; +import "./responses"; +import "./vector-stores"; +import "./uploads"; diff --git a/specification/base/typespec/messages/custom.tsp b/specification/base/typespec/messages/custom.tsp new file mode 100644 index 000000000..0225d873f --- /dev/null +++ b/specification/base/typespec/messages/custom.tsp @@ -0,0 +1,54 @@ +import "../assistants"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union MessageContentType { + /** The content is a text message. */ + text: "text", + + /** The content is an image file. */ + image_file: "image_file", + + /** The content is an image URL. */ + image_url: "image_url", + + /** The content is a refusal message. */ + refusal: "refusal", +} + +/** + * Represents a single piece of content in an Assistants API message. + */ +@discriminator("type") +model MessageContent { + type: MessageContentType; +} + +union MessageContentTextAnnotationType { + string, + file_citation: "file_citation", + file_path: "file_path", +} + +@discriminator("type") +model MessageContentTextObjectAnnotation { + /** The discriminated type identifier for the content item. */ + type: MessageContentTextAnnotationType; +} + +/** + * Represents a single piece of incremental content in an Assistants API streaming response. + */ +@discriminator("type") +model MessageDeltaContent { + /** The discriminated type identifier for the content item. */ + type: MessageContentType; +} + +@discriminator("type") +model MessageDeltaTextContentAnnotation { + /** The discriminated type identifier for the content item. */ + type: MessageContentTextAnnotationType; +} diff --git a/specification/base/typespec/messages/main.tsp b/specification/base/typespec/messages/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/messages/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/messages/models.tsp b/specification/base/typespec/messages/models.tsp new file mode 100644 index 000000000..ff42c8c77 --- /dev/null +++ b/specification/base/typespec/messages/models.tsp @@ -0,0 +1,418 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../assistants"; +import "../common"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from CreateMessageRequest.attachments +alias CreateMessageRequestAttachment = { + /** The ID of the file to attach to the message. */ + file_id: string; + + /** The tools to add this file to. */ + tools: (AssistantToolsCode | AssistantToolsFileSearchTypeOnly)[]; +}; + +// Tool generated type. Extracts from MessageObject.attachments +alias MessageObjectAttachment = { + /** The ID of the file to attach to the message. */ + file_id?: string; + + /** The tools to add this file to. */ + tools?: (AssistantToolsCode | AssistantToolsFileSearchTypeOnly)[]; +}; + +model CreateMessageRequest { + @doc(""" + The role of the entity that is creating the message. Allowed values include: + - `user`: Indicates the message is sent by an actual user and should be used in most cases to represent user-generated messages. + - `assistant`: Indicates the message is generated by the assistant. Use this value to insert messages from the assistant into the conversation. + """) + role: "user" | "assistant"; + + // Tool customization: use abstract base model for message request content items + content: MessageContent[]; + + /** A list of files attached to the message, and the tools they should be added to. */ + attachments?: CreateMessageRequestAttachment[] | null; + + ...MetadataPropertyForRequest; +} + +model ModifyMessageRequest { + ...MetadataPropertyForRequest; +} + +model ListMessagesResponse { + // Tool customization: add a clear enum enforcement of constrained 'object' label + object: "list"; + + data: MessageObject[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model DeleteMessageResponse { + id: string; + deleted: boolean; + object: "thread.message.deleted"; +} + +/** Represents a message within a [thread](/docs/api-reference/threads). */ +model MessageObject { + /** The identifier, which can be referenced in API endpoints. */ + id: string; + + @doc(""" + The object type, which is always `thread.message`. + """) + object: "thread.message"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the message was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The [thread](/docs/api-reference/threads) ID that this message belongs to. */ + thread_id: string; + + @doc(""" + The status of the message, which can be either `in_progress`, `incomplete`, or `completed`. + """) + status: "in_progress" | "incomplete" | "completed"; + + /** On an incomplete message, details about why the message is incomplete. */ + incomplete_details: { + /** The reason the message is incomplete. */ + reason: + | "content_filter" + | "max_tokens" + | "run_cancelled" + | "run_expired" + | "run_failed"; + } | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the message was completed. */ + @encode("unixTimestamp", int32) + completed_at: utcDateTime | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the message was marked as incomplete. */ + @encode("unixTimestamp", int32) + incomplete_at: utcDateTime | null; + + @doc(""" + The entity that produced the message. One of `user` or `assistant`. + """) + role: "user" | "assistant"; + + // Tool customization: use abstract base model for message response content items + /** The content of the message in array of text and/or images. */ + content: MessageContent[]; + + /** If applicable, the ID of the [assistant](/docs/api-reference/assistants) that authored this message. */ + assistant_id: string | null; + + @doc(""" + The ID of the [run](/docs/api-reference/runs) associated with the creation of this message. Value is `null` when messages are created manually using the create message or create thread endpoints. + """) + run_id: string | null; + + /** A list of files attached to the message, and the tools they were added to. */ + attachments: MessageObjectAttachment[] | null; + + ...MetadataPropertyForResponse; +} + +// Tool customization (apply_discriminator): apply a common model base for all assistants message content items +/** References an image [File](/docs/api-reference/files) in the content of a message. */ +model MessageContentImageFileObject extends MessageContent { + @doc(""" + Always `image_file`. + """) + type: MessageContentType.image_file; + + image_file: { + @doc(""" + The [File](/docs/api-reference/files) ID of the image in the message content. Set `purpose="vision"` when uploading the File if you need to later display the file content. + """) + file_id: string; + + @doc(""" + Specifies the detail level of the image if specified by the user. `low` uses fewer tokens, you can opt in to high resolution using `high`. + """) + detail?: "auto" | "low" | "high" = "auto"; + }; +} + +// Tool customization (apply_discriminator): apply a common model base for all assistants message content items +/** The text content that is part of a message. */ +model MessageContentTextObject extends MessageContent { + @doc(""" + Always `text`. + """) + type: MessageContentType.text; + + // Tool customization: Use readonly to aggregate request/response representations of text content + text: string | { + value: string; + + @visibility(Lifecycle.Read) + annotations: MessageContentTextObjectAnnotation[]; + }; +} + +// Tool customization (apply_discriminator): apply a common model base for all assistants message content items +/** The refusal content generated by the assistant. */ +model MessageContentRefusalObject extends MessageContent { + @doc(""" + Always `refusal`. + """) + type: MessageContentType.refusal; + + refusal: string; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files. */ +model MessageContentTextAnnotationsFileCitationObject + extends MessageContentTextObjectAnnotation { + @doc(""" + Always `file_citation`. + """) + type: MessageContentTextAnnotationType.file_citation; + + /** The text in the message content that needs to be replaced. */ + text: string; + + file_citation: { + /** The ID of the specific File the citation is from. */ + file_id: string; + }; + + @minValue(0) + start_index: int32; + + @minValue(0) + end_index: int32; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +@doc(""" + A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file. + """) +model MessageContentTextAnnotationsFilePathObject + extends MessageContentTextObjectAnnotation { + @doc(""" + Always `file_path`. + """) + type: MessageContentTextAnnotationType.file_path; + + /** The text in the message content that needs to be replaced. */ + text: string; + + file_path: { + /** The ID of the file that was generated. */ + file_id: string; + }; + + @minValue(0) + start_index: int32; + + @minValue(0) + end_index: int32; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** References an image [File](/docs/api-reference/files) in the content of a message. */ +model MessageDeltaContentImageFileObject extends MessageDeltaContent { + /** The index of the content part in the message. */ + index: int32; + + @doc(""" + Always `image_file`. + """) + type: MessageContentType.image_file; + + image_file?: { + @doc(""" + The [File](/docs/api-reference/files) ID of the image in the message content. Set `purpose="vision"` when uploading the File if you need to later display the file content. + """) + file_id?: string; + + @doc(""" + Specifies the detail level of the image if specified by the user. `low` uses fewer tokens, you can opt in to high resolution using `high`. + """) + detail?: "auto" | "low" | "high" = "auto"; + }; +} + +// Tool customization (apply_discriminator): apply a common model base for all assistants message content items +/** References an image URL in the content of a message. */ +model MessageContentImageUrlObject extends MessageContent { + /** The type of the content part. */ + type: MessageContentType.image_url; + + image_url: { + // Tool customization: url uses the url type + /** The external URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp. */ + url: url; + + @doc(""" + Specifies the detail level of the image. `low` uses fewer tokens, you can opt in to high resolution using `high`. Default value is `auto` + """) + detail?: "auto" | "low" | "high" = "auto"; + }; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** References an image URL in the content of a message. */ +model MessageDeltaContentImageUrlObject extends MessageDeltaContent { + /** The index of the content part in the message. */ + index: int32; + + @doc(""" + Always `image_url`. + """) + type: MessageContentType.image_url; + + image_url?: { + // Tool customization: url uses the url type + /** The URL of the image, must be a supported image types: jpeg, jpg, png, gif, webp. */ + url?: url; + + @doc(""" + Specifies the detail level of the image. `low` uses fewer tokens, you can opt in to high resolution using `high`. + """) + detail?: "auto" | "low" | "high" = "auto"; + }; +} + +/** Represents a message delta i.e. any changed fields on a message during streaming. */ +model MessageDeltaObject { + /** The identifier of the message, which can be referenced in API endpoints. */ + id: string; + + @doc(""" + The object type, which is always `thread.message.delta`. + """) + object: "thread.message.delta"; + + /** The delta containing the fields that have changed on the Message. */ + delta: { + @doc(""" + The entity that produced the message. One of `user` or `assistant`. + """) + role?: "user" | "assistant"; + + // Tool customization: replace unioned types with a custom, common base + /** The content of the message in array of text and/or images. */ + content?: MessageDeltaContent[]; + }; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** The text content that is part of a message. */ +model MessageDeltaContentTextObject extends MessageDeltaContent { + /** The index of the content part in the message. */ + index: int32; + + @doc(""" + Always `text`. + """) + type: MessageContentType.text; + + text?: { + /** The data that makes up the text. */ + value?: string; + + // Tool customization: replace unioned types with a custom, common base + annotations?: MessageDeltaTextContentAnnotation[]; + }; +} + +// Tool customization: stub aggregated request-only content type (merged with readonly to MessageContentTextObject) +alias MessageRequestContentTextObject = MessageContentTextObject; + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** A citation within the message that points to a specific quote from a specific File associated with the assistant or the message. Generated when the assistant uses the "file_search" tool to search files. */ +model MessageDeltaContentTextAnnotationsFileCitationObject + extends MessageDeltaTextContentAnnotation { + /** The index of the annotation in the text content part. */ + index: int32; + + @doc(""" + Always `file_citation`. + """) + type: MessageContentTextAnnotationType.file_citation; + + /** The text in the message content that needs to be replaced. */ + text?: string; + + file_citation?: { + /** The ID of the specific File the citation is from. */ + file_id?: string; + + /** The specific quote in the file. */ + quote?: string; + }; + + @minValue(0) + start_index?: int32; + + @minValue(0) + end_index?: int32; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +@doc(""" + A URL for the file that's generated when the assistant used the `code_interpreter` tool to generate a file. + """) +model MessageDeltaContentTextAnnotationsFilePathObject + extends MessageDeltaTextContentAnnotation { + /** The index of the annotation in the text content part. */ + index: int32; + + @doc(""" + Always `file_path`. + """) + type: MessageContentTextAnnotationType.file_path; + + /** The text in the message content that needs to be replaced. */ + text?: string; + + file_path?: { + /** The ID of the file that was generated. */ + file_id?: string; + }; + + @minValue(0) + start_index?: int32; + + @minValue(0) + end_index?: int32; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** The refusal content that is part of a message. */ +model MessageDeltaContentRefusalObject extends MessageDeltaContent { + /** The index of the refusal part in the message. */ + index: int32; + + @doc(""" + Always `refusal`. + """) + type: MessageContentType.refusal; + + refusal?: string; +} diff --git a/specification/base/typespec/messages/operations.tsp b/specification/base/typespec/messages/operations.tsp new file mode 100644 index 000000000..df4ebf365 --- /dev/null +++ b/specification/base/typespec/messages/operations.tsp @@ -0,0 +1,91 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/threads/{thread_id}/messages") +interface Messages { + @post + @operationId("createMessage") + @tag("Assistants") + @summary("Create a message.") + createMessage( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the [thread](/docs/api-reference/threads) to create a message for. */ + @path thread_id: string, + + @body requestBody: CreateMessageRequest, + ): MessageObject | ErrorResponse; + + @get + @operationId("listMessages") + @tag("Assistants") + @summary("Returns a list of messages for a given thread.") + listMessages( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the [thread](/docs/api-reference/threads) the messages belong to. */ + @path thread_id: string, + + ...CommonPageQueryParameters, + ): ListMessagesResponse | ErrorResponse; + + @route("{message_id}") + @get + @operationId("getMessage") + @tag("Assistants") + @summary("Retrieve a message.") + getMessage( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the [thread](/docs/api-reference/threads) to which this message belongs. */ + @path thread_id: string, + + /** The ID of the message to retrieve. */ + @path message_id: string, + ): MessageObject | ErrorResponse; + + @route("{message_id}") + @post + @operationId("modifyMessage") + @tag("Assistants") + @summary("Modifies a message.") + modifyMessage( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the thread to which this message belongs. */ + @path thread_id: string, + + /** The ID of the message to modify. */ + @path message_id: string, + + @body requestBody: ModifyMessageRequest, + ): MessageObject | ErrorResponse; + + @route("{message_id}") + @delete + @operationId("deleteMessage") + @tag("Assistants") + @summary("Deletes a message.") + deleteMessage( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the thread to which this message belongs. */ + @path thread_id: string, + + /** The ID of the message to delete. */ + @path message_id: string, + ): DeleteMessageResponse | ErrorResponse; +} diff --git a/specification/base/typespec/models/main.tsp b/specification/base/typespec/models/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/models/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/models/models.tsp b/specification/base/typespec/models/models.tsp new file mode 100644 index 000000000..73633bbaa --- /dev/null +++ b/specification/base/typespec/models/models.tsp @@ -0,0 +1,39 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +model ListModelsResponse { + object: "list"; + data: Model[]; +} + +model DeleteModelResponse { + id: string; + deleted: boolean; + + // Tool customization: add a clear enum enforcement of constrained 'object' label + object: "model"; +} + +/** Describes an OpenAI model offering that can be used with the API. */ +model Model { + /** The model identifier, which can be referenced in the API endpoints. */ + id: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) when the model was created. */ + @encode("unixTimestamp", int32) + created: utcDateTime; + + /** The object type, which is always "model". */ + object: "model"; + + /** The organization that owns the model. */ + owned_by: string; +} diff --git a/specification/base/typespec/models/operations.tsp b/specification/base/typespec/models/operations.tsp new file mode 100644 index 000000000..056a88169 --- /dev/null +++ b/specification/base/typespec/models/operations.tsp @@ -0,0 +1,53 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/models") +interface Models { + @get + @operationId("listModels") + @tag("Models") + @summary(""" + Lists the currently available models, and provides basic information about each one such as the + owner and availability. + """) + listModels( + @header accept: "application/json", + ): ListModelsResponse | ErrorResponse; + + @route("{model}") + @get + @operationId("retrieveModel") + @tag("Models") + @summary(""" + Retrieves a model instance, providing basic information about the model such as the owner and + permissioning. + """) + retrieveModel( + @header accept: "application/json", + + /** The ID of the model to use for this request. */ + @path `model`: string, + ): Model | ErrorResponse; + + @route("{model}") + @delete + @operationId("deleteModel") + @tag("Models") + @summary(""" + Delete a fine-tuned model. You must have the Owner role in your organization to delete a model. + """) + deleteModel( + @header accept: "application/json", + + /** The model to delete */ + @path `model`: string, + ): DeleteModelResponse | ErrorResponse; +} diff --git a/specification/base/typespec/moderations/custom.tsp b/specification/base/typespec/moderations/custom.tsp new file mode 100644 index 000000000..73b2fbeb2 --- /dev/null +++ b/specification/base/typespec/moderations/custom.tsp @@ -0,0 +1,140 @@ +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union ModerationAppliedInputType { + string, + text: "text", + image: "image", +} + +model CreateModerationResponseResult { + /** Whether any of the below categories are flagged. */ + flagged: boolean; + + /** A list of the categories, and whether they are flagged or not. */ + categories: { + /** Content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. Hateful content aimed at non-protected groups (e.g., chess players) is harassment. */ + hate: boolean; + + /** Hateful content that also includes violence or serious harm towards the targeted group based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. */ + `hate/threatening`: boolean; + + /** Content that expresses, incites, or promotes harassing language towards any target. */ + harassment: boolean; + + /** Harassment content that also includes violence or serious harm towards any target. */ + `harassment/threatening`: boolean; + + /** Content that includes instructions or advice that facilitate the planning or execution of wrongdoing, or that gives advice or instruction on how to commit illicit acts. For example, "how to shoplift" would fit this category. */ + illicit: boolean; + + /** Content that includes instructions or advice that facilitate the planning or execution of wrongdoing that also includes violence, or that gives advice or instruction on the procurement of any weapon. */ + `illicit/violent`: boolean; + + /** Content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders. */ + `self-harm`: boolean; + + /** Content where the speaker expresses that they are engaging or intend to engage in acts of self-harm, such as suicide, cutting, and eating disorders. */ + `self-harm/intent`: boolean; + + /** Content that encourages performing acts of self-harm, such as suicide, cutting, and eating disorders, or that gives instructions or advice on how to commit such acts. */ + `self-harm/instructions`: boolean; + + /** Content meant to arouse sexual excitement, such as the description of sexual activity, or that promotes sexual services (excluding sex education and wellness). */ + sexual: boolean; + + /** Sexual content that includes an individual who is under 18 years old. */ + `sexual/minors`: boolean; + + /** Content that depicts death, violence, or physical injury. */ + violence: boolean; + + /** Content that depicts death, violence, or physical injury in graphic detail. */ + `violence/graphic`: boolean; + }; + + /** A list of the categories along with their scores as predicted by model. */ + category_scores: { + /** The score for the category 'hate'. */ + hate: float32; + + /** The score for the category 'hate/threatening'. */ + `hate/threatening`: float32; + + /** The score for the category 'harassment'. */ + harassment: float32; + + /** The score for the category 'harassment/threatening'. */ + `harassment/threatening`: float32; + + /** The score for the category 'illicit'. */ + illicit: float32; + + /** The score for the category 'illicit/violent'. */ + `illicit/violent`: float32; + + /** The score for the category 'self-harm'. */ + `self-harm`: float32; + + /** The score for the category 'self-harm/intent'. */ + `self-harm/intent`: float32; + + /** The score for the category 'self-harm/instructions'. */ + `self-harm/instructions`: float32; + + /** The score for the category 'sexual'. */ + sexual: float32; + + /** The score for the category 'sexual/minors'. */ + `sexual/minors`: float32; + + /** The score for the category 'violence'. */ + violence: float32; + + /** The score for the category 'violence/graphic'. */ + `violence/graphic`: float32; + }; + + /** A list of the categories along with the input type(s) that the score applies to. */ + category_applied_input_types: { + /** The applied input type(s) for the category 'hate'. */ + hate: ModerationAppliedInputType.text[]; + + /** The applied input type(s) for the category 'hate/threatening'. */ + `hate/threatening`: ModerationAppliedInputType.text[]; + + /** The applied input type(s) for the category 'harassment'. */ + harassment: ModerationAppliedInputType.text[]; + + /** The applied input type(s) for the category 'harassment/threatening'. */ + `harassment/threatening`: ModerationAppliedInputType.text[]; + + /** The applied input type(s) for the category 'illicit'. */ + illicit: ModerationAppliedInputType.text[]; + + /** The applied input type(s) for the category 'illicit/violent'. */ + `illicit/violent`: ModerationAppliedInputType.text[]; + + /** The applied input type(s) for the category 'self-harm'. */ + `self-harm`: (ModerationAppliedInputType.text | ModerationAppliedInputType.image)[]; + + /** The applied input type(s) for the category 'self-harm/intent'. */ + `self-harm/intent`: (ModerationAppliedInputType.text | ModerationAppliedInputType.image)[]; + + /** The applied input type(s) for the category 'self-harm/instructions'. */ + `self-harm/instructions`: (ModerationAppliedInputType.text | ModerationAppliedInputType.image)[]; + + /** The applied input type(s) for the category 'sexual'. */ + sexual: (ModerationAppliedInputType.text | ModerationAppliedInputType.image)[]; + + /** The applied input type(s) for the category 'sexual/minors'. */ + `sexual/minors`: ModerationAppliedInputType.text[]; + + /** The applied input type(s) for the category 'violence'. */ + violence: (ModerationAppliedInputType.text | ModerationAppliedInputType.image)[]; + + /** The applied input type(s) for the category 'violence/graphic'. */ + `violence/graphic`: (ModerationAppliedInputType.text | ModerationAppliedInputType.image)[]; + }; +} diff --git a/specification/base/typespec/moderations/main.tsp b/specification/base/typespec/moderations/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/moderations/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/moderations/models.tsp b/specification/base/typespec/moderations/models.tsp new file mode 100644 index 000000000..832d77600 --- /dev/null +++ b/specification/base/typespec/moderations/models.tsp @@ -0,0 +1,64 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +model CreateModerationRequest { + /** + * Input (or inputs) to classify. Can be a single string, an array of strings, or + * an array of multi-modal input objects similar to other models. + */ + input: string | string[] | ({ + @doc(""" + Always `image_url`. + """) + type: "image_url"; + + /** Contains either an image URL or a data URL for a base64 encoded image. */ + image_url: { + /** Either a URL of the image or the base64 encoded image data. */ + url: string; + }; + } | { + @doc(""" + Always `text`. + """) + type: "text"; + + /** A string of text to classify. */ + text: string; + })[]; + + /** + * The content moderation model you would like to use. Learn more in + * [the moderation guide](/docs/guides/moderation), and learn about + * available models [here](/docs/models#moderation). + */ + @extension("x-oaiTypeLabel", "string") + `model`?: + | string + | "omni-moderation-latest" + | "omni-moderation-2024-09-26" + | "text-moderation-latest" + | "text-moderation-stable" = "omni-moderation-latest"; +} + +/** Represents if a given text input is potentially harmful. */ +model CreateModerationResponse { + /** The unique identifier for the moderation request. */ + id: string; + + /** The model used to generate the moderation results. */ + `model`: string; + + // Tool customization: Employ shared applied input type definitions via customized result items + /** A list of moderation objects. */ + results: CreateModerationResponseResult[]; +} diff --git a/specification/base/typespec/moderations/operations.tsp b/specification/base/typespec/moderations/operations.tsp new file mode 100644 index 000000000..828720af9 --- /dev/null +++ b/specification/base/typespec/moderations/operations.tsp @@ -0,0 +1,22 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/moderations") +interface Moderations { + @post + @operationId("createModeration") + @tag("Moderations") + @summary("Classifies if text is potentially harmful.") + createModeration( + @header accept: "application/json", + @body requestBody: CreateModerationRequest, + ): CreateModerationResponse | ErrorResponse; +} diff --git a/specification/base/typespec/realtime/custom.tsp b/specification/base/typespec/realtime/custom.tsp new file mode 100644 index 000000000..366597395 --- /dev/null +++ b/specification/base/typespec/realtime/custom.tsp @@ -0,0 +1,164 @@ +import "./custom/events.tsp"; +import "./custom/items.tsp"; +import "./custom/tools.tsp"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +model RealtimeRequestSession { + ...RealtimeSessionBase; + modalities?: RealtimeModality[]; + instructions?: string; + `model`?: + | "gpt-4o-realtime-preview" + | "gpt-4o-realtime-preview-2024-10-01" + | "gpt-4o-realtime-preview-2024-12-17" + | "gpt-4o-mini-realtime-preview" + | "gpt-4o-mini-realtime-preview-2024-12-17"; + voice?: VoiceIdsShared; + input_audio_format?: RealtimeAudioFormat = RealtimeAudioFormat.pcm16; + output_audio_format?: RealtimeAudioFormat = RealtimeAudioFormat.pcm16; + input_audio_transcription?: RealtimeAudioInputTranscriptionSettings | null; + turn_detection?: RealtimeTurnDetection | null; + input_audio_noise_reduction?: RealtimeAudioNoiseReduction; + tools?: RealtimeTool[]; + tool_choice?: RealtimeToolChoice; + temperature?: float32; + max_response_output_tokens?: int32 | "inf"; +} + +model RealtimeResponseSession { + ...RealtimeSessionBase; + object: "realtime.session"; + id: string; + `model`: string; + modalities: RealtimeModality[]; + instructions: string; + voice: VoiceIdsShared; + input_audio_format: RealtimeAudioFormat; + output_audio_format: RealtimeAudioFormat; + input_audio_transcription: RealtimeAudioInputTranscriptionSettings | null; + turn_detection: RealtimeTurnDetection; + input_audio_noise_reduction: RealtimeAudioNoiseReduction; + tools: RealtimeTool[]; + tool_choice: RealtimeToolChoice; + temperature: float32; + max_response_output_tokens: int32 | "inf" | null; +} + +union RealtimeAudioFormat { + string, + pcm16: "pcm16", + g711_ulaw: "g711_ulaw", + g711_alaw: "g711_alaw", +} + +union RealtimeAudioInputTranscriptionModel { + string, + whisper_1: "whisper-1", +} + +model RealtimeAudioInputTranscriptionSettings { + `model`?: RealtimeAudioInputTranscriptionModel = RealtimeAudioInputTranscriptionModel.whisper_1; + language?: string; + prompt?: string; +} + +union RealtimeModality { + string, + text: "text", + audio: "audio", +} + +union RealtimeTurnDetectionType { + string, + + /** + * Indicates that server-side voice activity detection (VAD) should be enabled, allowing the server to determine when + * add_user_audio commands present ends of speech and should be automatically committed. + * + * The API will also detect when the user begins talking, sending a generation_canceled command. + */ + server_vad: "server_vad", + + semantic_vad: "semantic_vad", +} + +@discriminator("type") +model RealtimeTurnDetection { + type: RealtimeTurnDetectionType; + + /** + * Whether or not to automatically generate a response when VAD is enabled. true by default. + */ + create_response?: boolean = true; + + /** + * Whether or not to automatically interrupt any ongoing response with output to the default conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + */ + interrupt_response?: boolean = true; +} + +model RealtimeServerVadTurnDetection extends RealtimeTurnDetection { + type: RealtimeTurnDetectionType.server_vad; + + /** + * Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A higher threshold will require louder audio to activate the model, and thus might perform better in noisy environments. + */ + threshold?: float32 = 0.5; + + // @encode("milliseconds", int32) + /** + * Amount of audio to include before the VAD detected speech (in milliseconds). Defaults to 300ms. + */ + prefix_padding_ms?: duration; // = 300ms + + // @encode("milliseconds", int32) + /** + * Duration of silence to detect speech stop (in milliseconds). Defaults to 500ms. With shorter values the model will respond more quickly, but may jump in on short pauses from the user. + */ + silence_duration_ms?: duration; // = 500ms +} + +model RealtimeSemanticVadTurnDetection extends RealtimeTurnDetection { + type: RealtimeTurnDetectionType.semantic_vad; + + /** + * Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. + */ + eagerness?: "low" | "medium" | "high" | "auto" = "auto"; +} + +model RealtimeServerEventRateLimitsUpdatedRateLimitsItem { + /** The rate limit property name that this item includes information about. */ + name: string; + + /** The maximum configured limit for this rate limit property. */ + limit: int32; + + /** The remaining quota available against the configured limit for this rate limit property. */ + remaining: int32; + + /** The remaining time, in seconds, until this rate limit property is reset. */ + @encode("seconds", float32) + reset_seconds: duration; +} + +union RealtimeAudioNoiseReductionType { + near_field: "near_field", + far_field: "far_field", +} + +@discriminator("type") +model RealtimeAudioNoiseReduction { + type: RealtimeAudioNoiseReductionType; +} + +model RealtimeAudioNearFieldNoiseReduction extends RealtimeAudioNoiseReduction { + type: RealtimeAudioNoiseReductionType.near_field; +} + +model RealtimeAudioFarFieldNoiseReduction extends RealtimeAudioNoiseReduction { + type: RealtimeAudioNoiseReductionType.far_field; +} diff --git a/specification/base/typespec/realtime/custom/content_parts.tsp b/specification/base/typespec/realtime/custom/content_parts.tsp new file mode 100644 index 000000000..8c8bcb1e5 --- /dev/null +++ b/specification/base/typespec/realtime/custom/content_parts.tsp @@ -0,0 +1,36 @@ +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union RealtimeContentPartType { + string, + input_text: "input_text", + input_audio: "input_audio", + text: "text", + audio: "audio", +} + +@discriminator("type") +model RealtimeContentPart { + type: RealtimeContentPartType; +} + +model RealtimeRequestTextContentPart extends RealtimeContentPart { + type: RealtimeContentPartType.input_text; + text: string; +} + +model RealtimeRequestAudioContentPart extends RealtimeContentPart { + type: RealtimeContentPartType.input_audio; + transcript?: string; +} + +model RealtimeResponseTextContentPart extends RealtimeContentPart { + type: RealtimeContentPartType.text; + text: string; +} + +model RealtimeResponseAudioContentPart extends RealtimeContentPart { + type: RealtimeContentPartType.audio; + transcript: string | null; +} diff --git a/specification/base/typespec/realtime/custom/events.tsp b/specification/base/typespec/realtime/custom/events.tsp new file mode 100644 index 000000000..3517a14ea --- /dev/null +++ b/specification/base/typespec/realtime/custom/events.tsp @@ -0,0 +1,57 @@ +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union RealtimeClientEventType { + string, + session_update: "session.update", + input_audio_buffer_append: "input_audio_buffer.append", + input_audio_buffer_commit: "input_audio_buffer.commit", + input_audio_buffer_clear: "input_audio_buffer.clear", + output_audio_buffer_clear: "output_audio_buffer.clear", + conversation_item_create: "conversation.item.create", + conversation_item_retrieve: "conversation.item.retrieve", + conversation_item_truncate: "conversation.item.truncate", + conversation_item_delete: "conversation.item.delete", + response_create: "response.create", + response_cancel: "response.cancel", + transcription_session_update: "transcription_session.update", +} + +union RealtimeServerEventType { + string, + error: "error", + session_created: "session.created", + session_updated: "session.updated", + conversation_created: "conversation.created", + conversation_item_input_audio_transcription_completed: "conversation.item.input_audio_transcription.completed", + conversation_item_input_audio_transcription_delta: "conversation.item.input_audio_transcription.delta", + conversation_item_input_audio_transcription_failed: "conversation.item.input_audio_transcription.failed", + conversation_item_created: "conversation.item.created", + conversation_item_retrieved: "conversation.item.retrieved", + conversation_item_truncated: "conversation.item.truncated", + conversation_item_deleted: "conversation.item.deleted", + input_audio_buffer_committed: "input_audio_buffer.committed", + input_audio_buffer_cleared: "input_audio_buffer.cleared", + input_audio_buffer_speech_started: "input_audio_buffer.speech_started", + input_audio_buffer_speech_stopped: "input_audio_buffer.speech_stopped", + output_audio_buffer_cleared: "output_audio_buffer.cleared", + output_audio_buffer_started: "output_audio_buffer.started", + output_audio_buffer_stopped: "output_audio_buffer.stopped", + response_created: "response.created", + response_done: "response.done", + response_output_item_added: "response.output_item.added", + response_output_item_done: "response.output_item.done", + response_content_part_added: "response.content_part.added", + response_content_part_done: "response.content_part.done", + response_text_delta: "response.text.delta", + response_text_done: "response.text.done", + response_audio_transcript_delta: "response.audio_transcript.delta", + response_audio_transcript_done: "response.audio_transcript.done", + response_audio_delta: "response.audio.delta", + response_audio_done: "response.audio.done", + response_function_call_arguments_delta: "response.function_call_arguments.delta", + response_function_call_arguments_done: "response.function_call_arguments.done", + transcription_session_updated: "transcription_session.updated", + rate_limits_updated: "rate_limits.updated", +} diff --git a/specification/base/typespec/realtime/custom/items.tsp b/specification/base/typespec/realtime/custom/items.tsp new file mode 100644 index 000000000..43ae09ef2 --- /dev/null +++ b/specification/base/typespec/realtime/custom/items.tsp @@ -0,0 +1,109 @@ +import "./content_parts.tsp"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@discriminator("type") +model RealtimeConversationRequestItem { + ...RealtimeConversationItemBase; + type: RealtimeItemType; + id?: string; +} + +@discriminator("role") +model RealtimeRequestMessageItem extends RealtimeConversationRequestItem { + type: RealtimeItemType.message; + role: RealtimeMessageRole; + status?: RealtimeItemStatus; +} + +model RealtimeRequestSystemMessageItem extends RealtimeRequestMessageItem { + role: RealtimeMessageRole.system; + content: RealtimeRequestTextContentPart[]; +} + +model RealtimeRequestUserMessageItem extends RealtimeRequestMessageItem { + role: RealtimeMessageRole.user; + content: (RealtimeRequestTextContentPart | RealtimeRequestAudioContentPart)[]; +} + +model RealtimeRequestAssistantMessageItem extends RealtimeRequestMessageItem { + role: RealtimeMessageRole.assistant; + content: RealtimeRequestTextContentPart[]; +} + +model RealtimeRequestFunctionCallItem extends RealtimeConversationRequestItem { + type: RealtimeItemType.function_call; + name: string; + call_id: string; + arguments: string; + status?: RealtimeItemStatus; +} + +model RealtimeRequestFunctionCallOutputItem + extends RealtimeConversationRequestItem { + type: RealtimeItemType.function_call_output; + call_id: string; + output: string; +} + +// TODO: representation of a doubly-discriminated type with an absent second discriminator +// (first discriminator: type = message; second discriminator: no role present) + +model RealtimeRequestMessageReferenceItem { // extends RealtimeConversationRequestItem { + type: RealtimeItemType.message; + id: string; +} + +@discriminator("type") +model RealtimeConversationResponseItem { + ...RealtimeConversationItemBase; + object: "realtime.item"; + type: RealtimeItemType; + id: string | null; +} + +model RealtimeResponseMessageItem extends RealtimeConversationResponseItem { + type: RealtimeItemType.message; + role: RealtimeMessageRole; + content: RealtimeContentPart[]; + status: RealtimeItemStatus; +} + +model RealtimeResponseFunctionCallItem + extends RealtimeConversationResponseItem { + type: RealtimeItemType.function_call; + name: string; + call_id: string; + arguments: string; + status: RealtimeItemStatus; +} + +model RealtimeResponseFunctionCallOutputItem + extends RealtimeConversationResponseItem { + type: RealtimeItemType.function_call_output; + call_id: string; + output: string; +} + +union RealtimeItemType { + string, + message: "message", + function_call: "function_call", + function_call_output: "function_call_output", +} + +union RealtimeItemStatus { + string, + in_progress: "in_progress", + completed: "completed", + incomplete: "incomplete", +} + +union RealtimeMessageRole { + string, + system: "system", + user: "user", + assistant: "assistant", +} diff --git a/specification/base/typespec/realtime/custom/tools.tsp b/specification/base/typespec/realtime/custom/tools.tsp new file mode 100644 index 000000000..a874e5b5e --- /dev/null +++ b/specification/base/typespec/realtime/custom/tools.tsp @@ -0,0 +1,73 @@ +using TypeSpec.OpenAPI; + +namespace OpenAI; + +/** + * The supported tool type discriminators for realtime tools. + * Currently, only 'function' tools are supported. + */ +union RealtimeToolType { + string, + function: "function", +} + +/** + * The base representation of a realtime tool definition. + */ +@discriminator("type") +model RealtimeTool { + type: RealtimeToolType; +} + +/** + * The definition of a function tool as used by the realtime endpoint. + */ +model RealtimeFunctionTool extends RealtimeTool { + type: RealtimeToolType.function; + name: string; + description?: string; + parameters?: unknown; +} + +/** + * The combined set of available representations for a realtime tool_choice parameter, encompassing both string + * literal options like 'auto' as well as structured references to defined tools. + */ +union RealtimeToolChoice { + RealtimeToolChoiceLiteral, + RealtimeToolChoiceObject, +} + +/** + * The available set of mode-level, string literal tool_choice options for the realtime endpoint. + */ +union RealtimeToolChoiceLiteral { + string, + + /** Specifies that the model should freely determine which tool or tools, if any, to call. */ + auto: "auto", + + /** Specifies that the model should call no tools whatsoever. */ + none: "none", + + /** Specifies that the model should call at least one tool. */ + required: "required", +} + +/** + * A base representation for a realtime tool_choice selecting a named tool. + */ +@discriminator("type") +model RealtimeToolChoiceObject { + type: RealtimeToolType; +} + +/** + * The representation of a realtime tool_choice selecting a named function tool. + */ +model RealtimeToolChoiceFunctionObject extends RealtimeToolChoiceObject { + type: RealtimeToolType.function; + function: { + name: string; + }; +} diff --git a/specification/base/typespec/realtime/main.tsp b/specification/base/typespec/realtime/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/realtime/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/realtime/models.tsp b/specification/base/typespec/realtime/models.tsp new file mode 100644 index 000000000..81b33f78d --- /dev/null +++ b/specification/base/typespec/realtime/models.tsp @@ -0,0 +1,1970 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../common"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from RealtimeConversationItemWithReference.content +alias RealtimeConversationItemWithReferenceContent = { + @doc(""" + The content type (`input_text`, `input_audio`, `item_reference`, `text`). + """) + type?: "input_audio" | "input_text" | "item_reference" | "text"; + + @doc(""" + The text content, used for `input_text` and `text` content types. + """) + text?: string; + + @doc(""" + ID of a previous conversation item to reference (for `item_reference` + content types in `response.create` events). These can reference both + client and server created items. + """) + id?: string; + + @doc(""" + Base64-encoded audio bytes, used for `input_audio` content type. + """) + audio?: string; + + @doc(""" + The transcript of the audio, used for `input_audio` content type. + """) + transcript?: string; +}; + +// Tool customization: Adjust union to be a discriminated type base +/** A realtime client event. */ +@discriminator("type") +model RealtimeClientEvent { + /** The type of event. */ + type: RealtimeClientEventType; + + event_id?: string; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + Send this event to update the session’s default configuration. + The client may send this event at any time to update any field, + except for `voice`. However, note that once a session has been + initialized with a particular `model`, it can’t be changed to + another model using `session.update`. + + When the server receives a `session.update`, it will respond + with a `session.updated` event showing the full, effective configuration. + Only the fields that are present are updated. To clear a field like + `instructions`, pass an empty string. + """) +model RealtimeClientEventSessionUpdate extends RealtimeClientEvent { + @doc(""" + The event type, must be `session.update`. + """) + type: RealtimeClientEventType.session_update; + + // Tool customization: apply enriched request-specific model + session: RealtimeRequestSession; +} + +// Tool customization: establish custom, enriched discriminated type hierarchy +/** The item to add to the conversation. */ +model RealtimeConversationItemBase { + /** Customized to enriched RealtimeConversation{Request,Response}Item models */ +} + +/** The response resource. */ +model RealtimeResponse { + /** The unique ID of the response. */ + id?: string; + + @doc(""" + The object type, must be `realtime.response`. + """) + object?: "realtime.response"; + + @doc(""" + The final status of the response (`completed`, `cancelled`, `failed`, or + `incomplete`). + """) + status?: "completed" | "cancelled" | "failed" | "incomplete"; + + /** Additional details about the status. */ + status_details?: { + @doc(""" + The type of error that caused the response to fail, corresponding + with the `status` field (`completed`, `cancelled`, `incomplete`, + `failed`). + """) + type?: "completed" | "cancelled" | "failed" | "incomplete"; + + @doc(""" + The reason the Response did not complete. For a `cancelled` Response, + one of `turn_detected` (the server VAD detected a new start of speech) + or `client_cancelled` (the client sent a cancel event). For an + `incomplete` Response, one of `max_output_tokens` or `content_filter` + (the server-side safety filter activated and cut off the response). + """) + reason?: + | "turn_detected" + | "client_cancelled" + | "max_output_tokens" + | "content_filter"; + + @doc(""" + A description of the error that caused the response to fail, + populated when the `status` is `failed`. + """) + error?: { + /** The type of error. */ + type?: string; + + /** Error code, if any. */ + code?: string; + }; + }; + + // Tool customization: apply enriched response-specific type + /** The list of output items generated by the response. */ + output?: RealtimeConversationResponseItem[]; + + ...MetadataPropertyForResponse; + + /** + * Usage statistics for the Response, this will correspond to billing. A + * Realtime API session will maintain a conversation context and append new + * Items to the Conversation, thus output from previous turns (text and + * audio tokens) will become the input for later turns. + */ + usage?: { + /** + * The total number of tokens in the Response including input and output + * text and audio tokens. + */ + total_tokens?: int32; + + /** + * The number of input tokens used in the Response, including text and + * audio tokens. + */ + input_tokens?: int32; + + /** + * The number of output tokens sent in the Response, including text and + * audio tokens. + */ + output_tokens?: int32; + + /** Details about the input tokens used in the Response. */ + input_token_details?: { + /** The number of cached tokens used in the Response. */ + cached_tokens?: int32; + + /** The number of text tokens used in the Response. */ + text_tokens?: int32; + + /** The number of audio tokens used in the Response. */ + audio_tokens?: int32; + }; + + /** Details about the output tokens used in the Response. */ + output_token_details?: { + /** The number of text tokens used in the Response. */ + text_tokens?: int32; + + /** The number of audio tokens used in the Response. */ + audio_tokens?: int32; + }; + }; + + @doc(""" + Which conversation the response is added to, determined by the `conversation` + field in the `response.create` event. If `auto`, the response will be added to + the default conversation and the value of `conversation_id` will be an id like + `conv_1234`. If `none`, the response will not be added to any conversation and + the value of `conversation_id` will be `null`. If responses are being triggered + by server VAD, the response will be added to the default conversation, thus + the `conversation_id` will be an id like `conv_1234`. + """) + conversation_id?: string; + + @doc(""" + The voice the model used to respond. + Current voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, + `onyx`, `nova`, `sage`, `shimmer`, and `verse`. + """) + voice?: VoiceIdsShared; + + @doc(""" + The set of modalities the model used to respond. If there are multiple modalities, + the model will pick one, for example if `modalities` is `["text", "audio"]`, the model + could be responding in either text or audio. + """) + modalities?: ("text" | "audio")[]; + + @doc(""" + The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + """) + output_audio_format?: "pcm16" | "g711_ulaw" | "g711_alaw"; + + /** Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8. */ + temperature?: float32; + + /** + * Maximum number of output tokens for a single assistant response, + * inclusive of tool calls, that was used in this response. + */ + max_output_tokens?: int32 | "inf"; +} + +// Tool customization (apply_discriminator): apply discriminated type base +/** + * Send this event to append audio bytes to the input audio buffer. The audio + * buffer is temporary storage you can write to and later commit. In Server VAD + * mode, the audio buffer is used to detect speech and the server will decide + * when to commit. When Server VAD is disabled, you must commit the audio buffer + * manually. + * + * The client may choose how much audio to place in each event up to a maximum + * of 15 MiB, for example streaming smaller chunks from the client may allow the + * VAD to be more responsive. Unlike made other client events, the server will + * not send a confirmation response to this event. + */ +model RealtimeClientEventInputAudioBufferAppend extends RealtimeClientEvent { + @doc(""" + The event type, must be `input_audio_buffer.append`. + """) + type: RealtimeClientEventType.input_audio_buffer_append; + + // Tool customization: use encoded type for audio data + @doc(""" + Base64-encoded audio bytes. This must be in the format specified by the + `input_audio_format` field in the session configuration. + """) + @encode("base64") + audio: bytes; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + Send this event to commit the user input audio buffer, which will create a + new user message item in the conversation. This event will produce an error + if the input audio buffer is empty. When in Server VAD mode, the client does + not need to send this event, the server will commit the audio buffer + automatically. + + Committing the input audio buffer will trigger input audio transcription + (if enabled in session configuration), but it will not create a response + from the model. The server will respond with an `input_audio_buffer.committed` + event. + """) +model RealtimeClientEventInputAudioBufferCommit extends RealtimeClientEvent { + @doc(""" + The event type, must be `input_audio_buffer.commit`. + """) + type: RealtimeClientEventType.input_audio_buffer_commit; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + Send this event to clear the audio bytes in the buffer. The server will + respond with an `input_audio_buffer.cleared` event. + """) +model RealtimeClientEventInputAudioBufferClear extends RealtimeClientEvent { + @doc(""" + The event type, must be `input_audio_buffer.clear`. + """) + type: RealtimeClientEventType.input_audio_buffer_clear; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + **WebRTC Only:** Emit to cut off the current audio response. This will trigger the server to + stop generating audio and emit a `output_audio_buffer.cleared` event. This + event should be preceded by a `response.cancel` client event to stop the + generation of the current response. + [Learn more](/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc). + """) +model RealtimeClientEventOutputAudioBufferClear extends RealtimeClientEvent { + @doc(""" + The event type, must be `output_audio_buffer.clear`. + """) + type: RealtimeClientEventType.output_audio_buffer_clear; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + Add a new Item to the Conversation's context, including messages, function + calls, and function call responses. This event can be used both to populate a + "history" of the conversation and to add new items mid-stream, but has the + current limitation that it cannot populate assistant audio messages. + + If successful, the server will respond with a `conversation.item.created` + event, otherwise an `error` event will be sent. + """) +model RealtimeClientEventConversationItemCreate extends RealtimeClientEvent { + @doc(""" + The event type, must be `conversation.item.create`. + """) + type: RealtimeClientEventType.conversation_item_create; + + @doc(""" + The ID of the preceding item after which the new item will be inserted. + If not set, the new item will be appended to the end of the conversation. + If set to `root`, the new item will be added to the beginning of the conversation. + If set to an existing ID, it allows an item to be inserted mid-conversation. If the + ID cannot be found, an error will be returned and the item will not be added. + """) + previous_item_id?: string; + + // Tool customization: apply enriched item definition hierarchy + item: RealtimeConversationRequestItem; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + Send this event to truncate a previous assistant message’s audio. The server + will produce audio faster than realtime, so this event is useful when the user + interrupts to truncate audio that has already been sent to the client but not + yet played. This will synchronize the server's understanding of the audio with + the client's playback. + + Truncating audio will delete the server-side text transcript to ensure there + is not text in the context that hasn't been heard by the user. + + If successful, the server will respond with a `conversation.item.truncated` + event. + """) +model RealtimeClientEventConversationItemTruncate extends RealtimeClientEvent { + @doc(""" + The event type, must be `conversation.item.truncate`. + """) + type: RealtimeClientEventType.conversation_item_truncate; + + /** + * The ID of the assistant message item to truncate. Only assistant message + * items can be truncated. + */ + item_id: string; + + /** The index of the content part to truncate. Set this to 0. */ + content_index: int32; + + /** + * Inclusive duration up to which audio is truncated, in milliseconds. If + * the audio_end_ms is greater than the actual audio duration, the server + * will respond with an error. + */ + audio_end_ms: int32; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + Send this event when you want to remove any item from the conversation + history. The server will respond with a `conversation.item.deleted` event, + unless the item does not exist in the conversation history, in which case the + server will respond with an error. + """) +model RealtimeClientEventConversationItemDelete extends RealtimeClientEvent { + @doc(""" + The event type, must be `conversation.item.delete`. + """) + type: RealtimeClientEventType.conversation_item_delete; + + /** The ID of the item to delete. */ + item_id: string; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + This event instructs the server to create a Response, which means triggering + model inference. When in Server VAD mode, the server will create Responses + automatically. + + A Response will include at least one Item, and may have two, in which case + the second will be a function call. These Items will be appended to the + conversation history. + + The server will respond with a `response.created` event, events for Items + and content created, and finally a `response.done` event to indicate the + Response is complete. + + The `response.create` event includes inference configuration like + `instructions`, and `temperature`. These fields will override the Session's + configuration for this Response only. + """) +model RealtimeClientEventResponseCreate extends RealtimeClientEvent { + @doc(""" + The event type, must be `response.create`. + """) + type: RealtimeClientEventType.response_create; + + response?: RealtimeResponseCreateParams; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + Send this event to cancel an in-progress response. The server will respond + with a `response.cancelled` event or an error if there is no response to + cancel. + """) +model RealtimeClientEventResponseCancel extends RealtimeClientEvent { + @doc(""" + The event type, must be `response.cancel`. + """) + type: RealtimeClientEventType.response_cancel; + + /** + * A specific response ID to cancel - if not provided, will cancel an + * in-progress response in the default conversation. + */ + response_id?: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** + * Returned when an error occurs, which could be a client problem or a server + * problem. Most errors are recoverable and the session will stay open, we + * recommend to implementors to monitor and log error messages by default. + */ +model RealtimeServerEventError extends RealtimeServerEvent { + @doc(""" + The event type, must be `error`. + """) + type: RealtimeServerEventType.error; + + /** Details of the error. */ + error: { + /** The type of error (e.g., "invalid_request_error", "server_error"). */ + type: string; + + /** Error code, if any. */ + code?: string | null; + + /** A human-readable error message. */ + message: string; + + /** Parameter related to the error, if any. */ + param?: string | null; + + /** The event_id of the client event that caused the error, if applicable. */ + event_id?: string | null; + }; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** + * Returned when a Session is created. Emitted automatically when a new + * connection is established as the first server event. This event will contain + * the default Session configuration. + */ +model RealtimeServerEventSessionCreated extends RealtimeServerEvent { + @doc(""" + The event type, must be `session.created`. + """) + type: RealtimeServerEventType.session_created; + + // Tool customization: apply enriched response-specific model + session: RealtimeResponseSession; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when a session is updated with a `session.update` event, unless + there is an error. + """) +model RealtimeServerEventSessionUpdated extends RealtimeServerEvent { + @doc(""" + The event type, must be `session.updated`. + """) + type: RealtimeServerEventType.session_updated; + + // Tool customization: apply enriched response-specific model + session: RealtimeResponseSession; +} + +// Tool customization: establish base for enriched request/response split models +/** Realtime session object configuration. */ +model RealtimeSessionBase {} + +// Tool customization: Adjust union to be a discriminated type base +/** A realtime server event. */ +@discriminator("type") +model RealtimeServerEvent { + /** The type of event. */ + type: RealtimeServerEventType; + + event_id?: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** Returned when a conversation is created. Emitted right after session creation. */ +model RealtimeServerEventConversationCreated extends RealtimeServerEvent { + @doc(""" + The event type, must be `conversation.created`. + """) + type: RealtimeServerEventType.conversation_created; + + /** The conversation resource. */ + conversation: { + /** The unique ID of the conversation. */ + id?: string; + + @doc(""" + The object type, must be `realtime.conversation`. + """) + object?: string; + }; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when an input audio buffer is committed, either by the client or + automatically in server VAD mode. The `item_id` property is the ID of the user + message item that will be created, thus a `conversation.item.created` event + will also be sent to the client. + """) +model RealtimeServerEventInputAudioBufferCommitted extends RealtimeServerEvent { + @doc(""" + The event type, must be `input_audio_buffer.committed`. + """) + type: RealtimeServerEventType.input_audio_buffer_committed; + + /** The ID of the preceding item after which the new item will be inserted. */ + previous_item_id: string; + + /** The ID of the user message item that will be created. */ + item_id: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when the input audio buffer is cleared by the client with a + `input_audio_buffer.clear` event. + """) +model RealtimeServerEventInputAudioBufferCleared extends RealtimeServerEvent { + @doc(""" + The event type, must be `input_audio_buffer.cleared`. + """) + type: RealtimeServerEventType.input_audio_buffer_cleared; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Sent by the server when in `server_vad` mode to indicate that speech has been + detected in the audio buffer. This can happen any time audio is added to the + buffer (unless speech is already detected). The client may want to use this + event to interrupt audio playback or provide visual feedback to the user. + + The client should expect to receive a `input_audio_buffer.speech_stopped` event + when speech stops. The `item_id` property is the ID of the user message item + that will be created when speech stops and will also be included in the + `input_audio_buffer.speech_stopped` event (unless the client manually commits + the audio buffer during VAD activation). + """) +model RealtimeServerEventInputAudioBufferSpeechStarted + extends RealtimeServerEvent { + @doc(""" + The event type, must be `input_audio_buffer.speech_started`. + """) + type: RealtimeServerEventType.input_audio_buffer_speech_started; + + @doc(""" + Milliseconds from the start of all audio written to the buffer during the + session when speech was first detected. This will correspond to the + beginning of audio sent to the model, and thus includes the + `prefix_padding_ms` configured in the Session. + """) + audio_start_ms: int32; + + /** The ID of the user message item that will be created when speech stops. */ + item_id: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned in `server_vad` mode when the server detects the end of speech in + the audio buffer. The server will also send an `conversation.item.created` + event with the user message item that is created from the audio buffer. + """) +model RealtimeServerEventInputAudioBufferSpeechStopped + extends RealtimeServerEvent { + @doc(""" + The event type, must be `input_audio_buffer.speech_stopped`. + """) + type: RealtimeServerEventType.input_audio_buffer_speech_stopped; + + @doc(""" + Milliseconds since the session started when speech stopped. This will + correspond to the end of audio sent to the model, and thus includes the + `min_silence_duration_ms` configured in the Session. + """) + audio_end_ms: int32; + + /** The ID of the user message item that will be created. */ + item_id: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + **WebRTC Only:** Emitted when the output audio buffer is cleared. This happens either in VAD + mode when the user has interrupted (`input_audio_buffer.speech_started`), + or when the client has emitted the `output_audio_buffer.clear` event to manually + cut off the current audio response. + [Learn more](/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc). + """) +model RealtimeServerEventOutputAudioBufferCleared extends RealtimeServerEvent { + @doc(""" + The event type, must be `output_audio_buffer.cleared`. + """) + type: RealtimeServerEventType.output_audio_buffer_cleared; + + /** The unique ID of the response that produced the audio. */ + response_id: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + **WebRTC Only:** Emitted when the server begins streaming audio to the client. This event is + emitted after an audio content part has been added (`response.content_part.added`) + to the response. + [Learn more](/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc). + """) +model RealtimeServerEventOutputAudioBufferStarted extends RealtimeServerEvent { + @doc(""" + The event type, must be `output_audio_buffer.started`. + """) + type: RealtimeServerEventType.output_audio_buffer_started; + + /** The unique ID of the response that produced the audio. */ + response_id: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + **WebRTC Only:** Emitted when the output audio buffer has been completely drained on the server, + and no more audio is forthcoming. This event is emitted after the full response + data has been sent to the client (`response.done`). + [Learn more](/docs/guides/realtime-conversations#client-and-server-events-for-audio-in-webrtc). + """) +model RealtimeServerEventOutputAudioBufferStopped extends RealtimeServerEvent { + @doc(""" + The event type, must be `output_audio_buffer.stopped`. + """) + type: RealtimeServerEventType.output_audio_buffer_stopped; + + /** The unique ID of the response that produced the audio. */ + response_id: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when a conversation item is created. There are several scenarios that produce this event: + - The server is generating a Response, which if successful will produce + either one or two Items, which will be of type `message` + (role `assistant`) or type `function_call`. + - The input audio buffer has been committed, either by the client or the + server (in `server_vad` mode). The server will take the content of the + input audio buffer and add it to a new user message Item. + - The client has sent a `conversation.item.create` event to add a new Item + to the Conversation. + """) +model RealtimeServerEventConversationItemCreated extends RealtimeServerEvent { + @doc(""" + The event type, must be `conversation.item.created`. + """) + type: RealtimeServerEventType.conversation_item_created; + + /** + * The ID of the preceding item in the Conversation context, allows the + * client to understand the order of the conversation. + */ + previous_item_id: string; + + // Tool customization: apply enriched item definition hierarchy + item: RealtimeConversationResponseItem; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + This event is the output of audio transcription for user audio written to the + user audio buffer. Transcription begins when the input audio buffer is + committed by the client or server (in `server_vad` mode). Transcription runs + asynchronously with Response creation, so this event may come before or after + the Response events. + + Realtime API models accept audio natively, and thus input transcription is a + separate process run on a separate ASR (Automatic Speech Recognition) model, + currently always `whisper-1`. Thus the transcript may diverge somewhat from + the model's interpretation, and should be treated as a rough guide. + """) +model RealtimeServerEventConversationItemInputAudioTranscriptionCompleted + extends RealtimeServerEvent { + @doc(""" + The event type, must be + `conversation.item.input_audio_transcription.completed`. + """) + type: RealtimeServerEventType.conversation_item_input_audio_transcription_completed; + + /** The ID of the user message item containing the audio. */ + item_id: string; + + /** The index of the content part containing the audio. */ + content_index: int32; + + /** The transcribed text. */ + transcript: string; + + /** The log probabilities of the transcription. */ + logprobs?: LogProbProperties[] | null; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when input audio transcription is configured, and a transcription + request for a user message failed. These events are separate from other + `error` events so that the client can identify the related Item. + """) +model RealtimeServerEventConversationItemInputAudioTranscriptionFailed + extends RealtimeServerEvent { + @doc(""" + The event type, must be + `conversation.item.input_audio_transcription.failed`. + """) + type: RealtimeServerEventType.conversation_item_input_audio_transcription_failed; + + /** The ID of the user message item. */ + item_id: string; + + /** The index of the content part containing the audio. */ + content_index: int32; + + /** Details of the transcription error. */ + error: { + /** The type of error. */ + type?: string; + + /** Error code, if any. */ + code?: string; + + /** A human-readable error message. */ + message?: string; + + /** Parameter related to the error, if any. */ + param?: string; + }; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when an earlier assistant audio message item is truncated by the + client with a `conversation.item.truncate` event. This event is used to + synchronize the server's understanding of the audio with the client's playback. + + This action will truncate the audio and remove the server-side text transcript + to ensure there is no text in the context that hasn't been heard by the user. + """) +model RealtimeServerEventConversationItemTruncated extends RealtimeServerEvent { + @doc(""" + The event type, must be `conversation.item.truncated`. + """) + type: RealtimeServerEventType.conversation_item_truncated; + + /** The ID of the assistant message item that was truncated. */ + item_id: string; + + /** The index of the content part that was truncated. */ + content_index: int32; + + /** The duration up to which the audio was truncated, in milliseconds. */ + audio_end_ms: int32; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when an item in the conversation is deleted by the client with a + `conversation.item.delete` event. This event is used to synchronize the + server's understanding of the conversation history with the client's view. + """) +model RealtimeServerEventConversationItemDeleted extends RealtimeServerEvent { + @doc(""" + The event type, must be `conversation.item.deleted`. + """) + type: RealtimeServerEventType.conversation_item_deleted; + + /** The ID of the item that was deleted. */ + item_id: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when a new Response is created. The first event of response creation, + where the response is in an initial state of `in_progress`. + """) +model RealtimeServerEventResponseCreated extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.created`. + """) + type: RealtimeServerEventType.response_created; + + response: RealtimeResponse; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when a Response is done streaming. Always emitted, no matter the + final state. The Response object included in the `response.done` event will + include all output Items in the Response but will omit the raw audio data. + """) +model RealtimeServerEventResponseDone extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.done`. + """) + type: RealtimeServerEventType.response_done; + + response: RealtimeResponse; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** Returned when a new Item is created during Response generation. */ +model RealtimeServerEventResponseOutputItemAdded extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.output_item.added`. + """) + type: RealtimeServerEventType.response_output_item_added; + + /** The ID of the Response to which the item belongs. */ + response_id: string; + + /** The index of the output item in the Response. */ + output_index: int32; + + // Tool customization: apply enriched item definition hierarchy + item: RealtimeConversationResponseItem; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** + * Returned when an Item is done streaming. Also emitted when a Response is + * interrupted, incomplete, or cancelled. + */ +model RealtimeServerEventResponseOutputItemDone extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.output_item.done`. + """) + type: RealtimeServerEventType.response_output_item_done; + + /** The ID of the Response to which the item belongs. */ + response_id: string; + + /** The index of the output item in the Response. */ + output_index: int32; + + // Tool customization: apply enriched item definition hierarchy + item: RealtimeConversationResponseItem; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** + * Returned when a new content part is added to an assistant message item during + * response generation. + */ +model RealtimeServerEventResponseContentPartAdded extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.content_part.added`. + """) + type: RealtimeServerEventType.response_content_part_added; + + /** The ID of the response. */ + response_id: string; + + /** The ID of the item to which the content part was added. */ + item_id: string; + + /** The index of the output item in the response. */ + output_index: int32; + + /** The index of the content part in the item's content array. */ + content_index: int32; + + // Tool customization: apply detailed content part type + /** The content part that was added. */ + part: RealtimeContentPart; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** + * Returned when a content part is done streaming in an assistant message item. + * Also emitted when a Response is interrupted, incomplete, or cancelled. + */ +model RealtimeServerEventResponseContentPartDone extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.content_part.done`. + """) + type: RealtimeServerEventType.response_content_part_done; + + /** The ID of the response. */ + response_id: string; + + /** The ID of the item. */ + item_id: string; + + /** The index of the output item in the response. */ + output_index: int32; + + /** The index of the content part in the item's content array. */ + content_index: int32; + + // Tool customization: apply detailed content part type + /** The content part that is done. */ + part: RealtimeContentPart; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** Returned when the text value of a "text" content part is updated. */ +model RealtimeServerEventResponseTextDelta extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.text.delta`. + """) + type: RealtimeServerEventType.response_text_delta; + + /** The ID of the response. */ + response_id: string; + + /** The ID of the item. */ + item_id: string; + + /** The index of the output item in the response. */ + output_index: int32; + + /** The index of the content part in the item's content array. */ + content_index: int32; + + /** The text delta. */ + delta: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** + * Returned when the text value of a "text" content part is done streaming. Also + * emitted when a Response is interrupted, incomplete, or cancelled. + */ +model RealtimeServerEventResponseTextDone extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.text.done`. + """) + type: RealtimeServerEventType.response_text_done; + + /** The ID of the response. */ + response_id: string; + + /** The ID of the item. */ + item_id: string; + + /** The index of the output item in the response. */ + output_index: int32; + + /** The index of the content part in the item's content array. */ + content_index: int32; + + /** The final text content. */ + text: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** Returned when the model-generated transcription of audio output is updated. */ +model RealtimeServerEventResponseAudioTranscriptDelta + extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.audio_transcript.delta`. + """) + type: RealtimeServerEventType.response_audio_transcript_delta; + + /** The ID of the response. */ + response_id: string; + + /** The ID of the item. */ + item_id: string; + + /** The index of the output item in the response. */ + output_index: int32; + + /** The index of the content part in the item's content array. */ + content_index: int32; + + /** The transcript delta. */ + delta: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** + * Returned when the model-generated transcription of audio output is done + * streaming. Also emitted when a Response is interrupted, incomplete, or + * cancelled. + */ +model RealtimeServerEventResponseAudioTranscriptDone + extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.audio_transcript.done`. + """) + type: RealtimeServerEventType.response_audio_transcript_done; + + /** The ID of the response. */ + response_id: string; + + /** The ID of the item. */ + item_id: string; + + /** The index of the output item in the response. */ + output_index: int32; + + /** The index of the content part in the item's content array. */ + content_index: int32; + + /** The final transcript of the audio. */ + transcript: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** Returned when the model-generated audio is updated. */ +model RealtimeServerEventResponseAudioDelta extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.audio.delta`. + """) + type: RealtimeServerEventType.response_audio_delta; + + /** The ID of the response. */ + response_id: string; + + /** The ID of the item. */ + item_id: string; + + /** The index of the output item in the response. */ + output_index: int32; + + /** The index of the content part in the item's content array. */ + content_index: int32; + + // Tool customization: use encoded type for audio data + /** Base64-encoded audio data delta. */ + @encode("base64") + delta: bytes; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** + * Returned when the model-generated audio is done. Also emitted when a Response + * is interrupted, incomplete, or cancelled. + */ +model RealtimeServerEventResponseAudioDone extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.audio.done`. + """) + type: RealtimeServerEventType.response_audio_done; + + /** The ID of the response. */ + response_id: string; + + /** The ID of the item. */ + item_id: string; + + /** The index of the output item in the response. */ + output_index: int32; + + /** The index of the content part in the item's content array. */ + content_index: int32; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** Returned when the model-generated function call arguments are updated. */ +model RealtimeServerEventResponseFunctionCallArgumentsDelta + extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.function_call_arguments.delta`. + """) + type: RealtimeServerEventType.response_function_call_arguments_delta; + + /** The ID of the response. */ + response_id: string; + + /** The ID of the function call item. */ + item_id: string; + + /** The index of the output item in the response. */ + output_index: int32; + + /** The ID of the function call. */ + call_id: string; + + /** The arguments delta as a JSON string. */ + delta: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** + * Returned when the model-generated function call arguments are done streaming. + * Also emitted when a Response is interrupted, incomplete, or cancelled. + */ +model RealtimeServerEventResponseFunctionCallArgumentsDone + extends RealtimeServerEvent { + @doc(""" + The event type, must be `response.function_call_arguments.done`. + """) + type: RealtimeServerEventType.response_function_call_arguments_done; + + /** The ID of the response. */ + response_id: string; + + /** The ID of the function call item. */ + item_id: string; + + /** The index of the output item in the response. */ + output_index: int32; + + /** The ID of the function call. */ + call_id: string; + + /** The final arguments as a JSON string. */ + arguments: string; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** + * Emitted at the beginning of a Response to indicate the updated rate limits. + * When a Response is created some tokens will be "reserved" for the output + * tokens, the rate limits shown here reflect that reservation, which is then + * adjusted accordingly once the Response is completed. + */ +model RealtimeServerEventRateLimitsUpdated extends RealtimeServerEvent { + @doc(""" + The event type, must be `rate_limits.updated`. + """) + type: RealtimeServerEventType.rate_limits_updated; + + // Tool customization: use custom type for rate limit items (applying encoded duration) + /** List of rate limit information. */ + rate_limits: RealtimeServerEventRateLimitsUpdatedRateLimitsItem[]; +} + +/** Create a new Realtime response with these parameters */ +model RealtimeResponseCreateParams { + // Tool customization: Apply reusable modality representation + /** + * The set of modalities the model can respond with. To disable audio, + * set this to ["text"]. + */ + modalities?: RealtimeModality[]; + + @doc(""" + The default system instructions (i.e. system message) prepended to model + calls. This field allows the client to guide the model on desired + responses. The model can be instructed on response content and format, + (e.g. "be extremely succinct", "act friendly", "here are examples of good + responses") and on audio behavior (e.g. "talk quickly", "inject emotion + into your voice", "laugh frequently"). The instructions are not guaranteed + to be followed by the model, but they provide guidance to the model on the + desired behavior. + + Note that the server sets default instructions which will be used if this + field is not set and are visible in the `session.created` event at the + start of the session. + """) + instructions?: string; + + @doc(""" + The voice the model uses to respond. Voice cannot be changed during the + session once the model has responded with audio at least once. Current + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, + `onyx`, `nova`, `sage`, `shimmer`, and `verse`. + """) + voice?: VoiceIdsShared; + + // Tool customization: use extracted and reusable audio format definition + @doc(""" + The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + """) + output_audio_format?: RealtimeAudioFormat = RealtimeAudioFormat.pcm16; + + // Tool customization: use enriched tool definition + /** Tools (functions) available to the model. */ + tools?: RealtimeTool[]; + + @doc(""" + How the model chooses tools. Options are `auto`, `none`, `required`, or + specify a function, like `{"type": "function", "function": {"name": "my_function"}}`. + """) + tool_choice?: string; + + /** Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8. */ + temperature?: float32; + + // Tool customization: Address (observed as of 2025-01-31) spec issue with 'max_response_output_tokens' + @doc(""" + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + """) + max_output_tokens?: int32 | "inf"; + + @doc(""" + Controls which conversation the response is added to. Currently supports + `auto` and `none`, with `auto` as the default value. The `auto` value + means that the contents of the response will be added to the default + conversation. Set this to `none` to create an out-of-band response which + will not add items to default conversation. + """) + conversation?: string | "auto" | "none"; + + ...MetadataPropertyForRequest; + + // Tool customization: apply a customized, more specific discriminated type hierarchy + @doc(""" + Input items to include in the prompt for the model. Using this field + creates a new context for this Response instead of using the default + conversation. An empty array `[]` will clear the context for this Response. + Note that this can include references to items from the default conversation. + """) + input?: RealtimeConversationRequestItem[]; +} + +/** Realtime session object configuration. */ +model RealtimeSessionCreateRequest { + // Tool customization: Apply reusable modality representation + /** + * The set of modalities the model can respond with. To disable audio, + * set this to ["text"]. + */ + modalities?: RealtimeModality[]; + + /** The Realtime model used for this session. */ + `model`?: + | "gpt-4o-realtime-preview" + | "gpt-4o-realtime-preview-2024-10-01" + | "gpt-4o-realtime-preview-2024-12-17" + | "gpt-4o-realtime-preview-2025-06-03" + | "gpt-4o-mini-realtime-preview" + | "gpt-4o-mini-realtime-preview-2024-12-17"; + + @doc(""" + The default system instructions (i.e. system message) prepended to model calls. This field allows the client to guide the model on desired responses. The model can be instructed on response content and format, (e.g. "be extremely succinct", "act friendly", "here are examples of good responses") and on audio behavior (e.g. "talk quickly", "inject emotion into your voice", "laugh frequently"). The instructions are not guaranteed to be followed by the model, but they provide guidance to the model on the desired behavior. + + Note that the server sets default instructions which will be used if this field is not set and are visible in the `session.created` event at the start of the session. + """) + instructions?: string; + + @doc(""" + The voice the model uses to respond. Voice cannot be changed during the + session once the model has responded with audio at least once. Current + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, + `onyx`, `nova`, `sage`, `shimmer`, and `verse`. + """) + voice?: VoiceIdsShared; + + // Tool customization: use extracted and reusable audio format definition + @doc(""" + The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + For `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, + single channel (mono), and little-endian byte order. + """) + input_audio_format?: RealtimeAudioFormat = RealtimeAudioFormat.pcm16; + + // Tool customization: use extracted and reusable audio format definition + @doc(""" + The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + For `pcm16`, output audio is sampled at a rate of 24kHz. + """) + output_audio_format?: RealtimeAudioFormat = RealtimeAudioFormat.pcm16; + + @doc(""" + Configuration for input audio transcription, defaults to off and can be set to `null` to turn off once on. Input audio transcription is not native to the model, since the model consumes audio directly. Transcription runs asynchronously through [the /audio/transcriptions endpoint](https://platform.openai.com/docs/api-reference/audio/createTranscription) and should be treated as guidance of input audio content rather than precisely what the model heard. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. + """) + input_audio_transcription?: { + @doc(""" + The model to use for transcription, current options are `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `whisper-1`. + """) + `model`?: string; + + @doc(""" + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + """) + language?: string; + + @doc(""" + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models, the prompt is a free text string, for example "expect words related to technology". + """) + prompt?: string; + }; + + @doc(""" + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + Semantic VAD is more advanced and uses a turn detection model (in conjuction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + """) + turn_detection?: { + /** Type of turn detection. */ + type?: "server_vad" | "semantic_vad" = "server_vad"; + + @doc(""" + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. + """) + eagerness?: "low" | "medium" | "high" | "auto" = "auto"; + + @doc(""" + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + """) + threshold?: float32; + + @doc(""" + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + """) + prefix_padding_ms?: int32; + + @doc(""" + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + """) + silence_duration_ms?: int32; + + /** Whether or not to automatically generate a response when a VAD stop event occurs. */ + create_response?: boolean = true; + + @doc(""" + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. + """) + interrupt_response?: boolean = true; + }; + + @doc(""" + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + """) + input_audio_noise_reduction?: { + @doc(""" + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + """) + type?: "near_field" | "far_field"; + } | null = null; + + /** + * The speed of the model's spoken response. 1.0 is the default speed. 0.25 is + * the minimum speed. 1.5 is the maximum speed. This value can only be changed + * in between model turns, not while a response is in progress. + */ + @minValue(0.25) + @maxValue(1.5) + speed?: float32 = 1; + + @doc(""" + Configuration options for tracing. Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + """) + tracing?: "auto" | { + /** + * The name of the workflow to attach to this trace. This is used to + * name the trace in the traces dashboard. + */ + workflow_name?: string; + + /** + * The group id to attach to this trace to enable filtering and + * grouping in the traces dashboard. + */ + group_id?: string; + + /** + * The arbitrary metadata to attach to this trace to enable + * filtering in the traces dashboard. + */ + metadata?: unknown; + }; + + // Tool customization: use enriched tool definition + /** Tools (functions) available to the model. */ + tools?: RealtimeTool[]; + + @doc(""" + How the model chooses tools. Options are `auto`, `none`, `required`, or + specify a function. + """) + tool_choice?: string = "auto"; + + /** Sampling temperature for the model, limited to [0.6, 1.2]. For audio models a temperature of 0.8 is highly recommended for best performance. */ + temperature?: float32 = 0.8; + + @doc(""" + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + """) + max_response_output_tokens?: int32 | "inf"; + + /** Configuration options for the generated client secret. */ + client_secret?: { + /** Configuration for the ephemeral token expiration. */ + expires_at?: { + @doc(""" + The anchor point for the ephemeral token expiration. Only `created_at` is currently supported. + """) + anchor?: "created_at" = "created_at"; + + @doc(""" + The number of seconds from the anchor point to the expiration. Select a value between `10` and `7200`. + """) + seconds?: int32 = 600; + }; + }; +} + +/** + * A new Realtime session configuration, with an ephermeral key. Default TTL + * for keys is one minute. + */ +model RealtimeSessionCreateResponse { + /** Ephemeral key returned by the API. */ + client_secret: { + /** + * Ephemeral key usable in client environments to authenticate connections + * to the Realtime API. Use this in client-side environments rather than + * a standard API token, which should only be used server-side. + */ + value: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** + * Timestamp for when the token expires. Currently, all tokens expire + * after one minute. + */ + @encode("unixTimestamp", int32) + expires_at: utcDateTime; + }; + + // Tool customization: Apply reusable modality representation + /** + * The set of modalities the model can respond with. To disable audio, + * set this to ["text"]. + */ + modalities?: RealtimeModality[]; + + @doc(""" + The default system instructions (i.e. system message) prepended to model + calls. This field allows the client to guide the model on desired + responses. The model can be instructed on response content and format, + (e.g. "be extremely succinct", "act friendly", "here are examples of good + responses") and on audio behavior (e.g. "talk quickly", "inject emotion + into your voice", "laugh frequently"). The instructions are not guaranteed + to be followed by the model, but they provide guidance to the model on the + desired behavior. + + Note that the server sets default instructions which will be used if this + field is not set and are visible in the `session.created` event at the + start of the session. + """) + instructions?: string; + + @doc(""" + The voice the model uses to respond. Voice cannot be changed during the + session once the model has responded with audio at least once. Current + voice options are `alloy`, `ash`, `ballad`, `coral`, `echo` `sage`, + `shimmer` and `verse`. + """) + voice?: VoiceIdsShared; + + // Tool customization: use extracted and reusable audio format definition + @doc(""" + The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + """) + input_audio_format?: RealtimeAudioFormat; + + // Tool customization: use extracted and reusable audio format definition + @doc(""" + The format of output audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + """) + output_audio_format?: RealtimeAudioFormat; + + @doc(""" + Configuration for input audio transcription, defaults to off and can be + set to `null` to turn off once on. Input audio transcription is not native + to the model, since the model consumes audio directly. Transcription runs + asynchronously through Whisper and should be treated as rough guidance + rather than the representation understood by the model. + """) + input_audio_transcription?: { + @doc(""" + The model to use for transcription, `whisper-1` is the only currently + supported model. + """) + `model`?: string; + }; + + /** + * The speed of the model's spoken response. 1.0 is the default speed. 0.25 is + * the minimum speed. 1.5 is the maximum speed. This value can only be changed + * in between model turns, not while a response is in progress. + */ + @minValue(0.25) + @maxValue(1.5) + speed?: float32 = 1; + + @doc(""" + Configuration options for tracing. Set to null to disable tracing. Once + tracing is enabled for a session, the configuration cannot be modified. + + `auto` will create a trace for the session with default values for the + workflow name, group id, and metadata. + """) + tracing?: "auto" | { + /** + * The name of the workflow to attach to this trace. This is used to + * name the trace in the traces dashboard. + */ + workflow_name?: string; + + /** + * The group id to attach to this trace to enable filtering and + * grouping in the traces dashboard. + */ + group_id?: string; + + /** + * The arbitrary metadata to attach to this trace to enable + * filtering in the traces dashboard. + */ + metadata?: unknown; + }; + + @doc(""" + Configuration for turn detection. Can be set to `null` to turn off. Server + VAD means that the model will detect the start and end of speech based on + audio volume and respond at the end of user speech. + """) + turn_detection?: { + @doc(""" + Type of turn detection, only `server_vad` is currently supported. + """) + type?: string; + + /** + * Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + * higher threshold will require louder audio to activate the model, and + * thus might perform better in noisy environments. + */ + threshold?: float32; + + /** + * Amount of audio to include before the VAD detected speech (in + * milliseconds). Defaults to 300ms. + */ + prefix_padding_ms?: int32; + + /** + * Duration of silence to detect speech stop (in milliseconds). Defaults + * to 500ms. With shorter values the model will respond more quickly, + * but may jump in on short pauses from the user. + */ + silence_duration_ms?: int32; + }; + + // Tool customization: use enriched tool definition + /** Tools (functions) available to the model. */ + tools?: RealtimeTool[]; + + @doc(""" + How the model chooses tools. Options are `auto`, `none`, `required`, or + specify a function. + """) + tool_choice?: string; + + /** Sampling temperature for the model, limited to [0.6, 1.2]. Defaults to 0.8. */ + temperature?: float32; + + @doc(""" + Maximum number of output tokens for a single assistant response, + inclusive of tool calls. Provide an integer between 1 and 4096 to + limit output tokens, or `inf` for the maximum available tokens for a + given model. Defaults to `inf`. + """) + max_response_output_tokens?: int32 | "inf"; +} + +/** The item to add to the conversation. */ +model RealtimeConversationItemWithReference { + @doc(""" + For an item of type (`message` | `function_call` | `function_call_output`) + this field allows the client to assign the unique ID of the item. It is + not required because the server will generate one if not provided. + + For an item of type `item_reference`, this field is required and is a + reference to any item that has previously existed in the conversation. + """) + id?: string; + + @doc(""" + The type of the item (`message`, `function_call`, `function_call_output`, `item_reference`). + """) + type?: "message" | "function_call" | "function_call_output"; + + @doc(""" + Identifier for the API object being returned - always `realtime.item`. + """) + object?: "realtime.item"; + + @doc(""" + The status of the item (`completed`, `incomplete`). These have no effect + on the conversation, but are accepted for consistency with the + `conversation.item.created` event. + """) + status?: "completed" | "incomplete"; + + @doc(""" + The role of the message sender (`user`, `assistant`, `system`), only + applicable for `message` items. + """) + role?: "user" | "assistant" | "system"; + + @doc(""" + The content of the message, applicable for `message` items. + - Message items of role `system` support only `input_text` content + - Message items of role `user` support `input_text` and `input_audio` + content + - Message items of role `assistant` support `text` content. + """) + content?: RealtimeConversationItemWithReferenceContent[]; + + @doc(""" + The ID of the function call (for `function_call` and + `function_call_output` items). If passed on a `function_call_output` + item, the server will check that a `function_call` item with the same + ID exists in the conversation history. + """) + call_id?: string; + + @doc(""" + The name of the function being called (for `function_call` items). + """) + name?: string; + + @doc(""" + The arguments of the function call (for `function_call` items). + """) + arguments?: string; + + @doc(""" + The output of the function call (for `function_call_output` items). + """) + output?: string; +} + +// Tool customization (apply_discriminator): apply discriminated type base +@doc(""" + Send this event when you want to retrieve the server's representation of a specific item in the conversation history. This is useful, for example, to inspect user audio after noise cancellation and VAD. + The server will respond with a `conversation.item.retrieved` event, + unless the item does not exist in the conversation history, in which case the + server will respond with an error. + """) +model RealtimeClientEventConversationItemRetrieve extends RealtimeClientEvent { + @doc(""" + The event type, must be `conversation.item.retrieve`. + """) + type: RealtimeClientEventType.conversation_item_retrieve; + + /** The ID of the item to retrieve. */ + item_id: string; +} + +// Tool customization (apply_discriminator): apply discriminated type base +/** Send this event to update a transcription session. */ +model RealtimeClientEventTranscriptionSessionUpdate + extends RealtimeClientEvent { + @doc(""" + The event type, must be `transcription_session.update`. + """) + type: RealtimeClientEventType.transcription_session_update; + + session: RealtimeTranscriptionSessionCreateRequest; +} + +// Tool customization (apply_discriminator): apply discriminated type +/** Returned when the text value of an input audio transcription content part is updated. */ +model RealtimeServerEventConversationItemInputAudioTranscriptionDelta + extends RealtimeServerEvent { + @doc(""" + The event type, must be `conversation.item.input_audio_transcription.delta`. + """) + type: RealtimeServerEventType.conversation_item_input_audio_transcription_delta; + + /** The ID of the item. */ + item_id: string; + + /** The index of the content part in the item's content array. */ + content_index?: int32; + + /** The text delta. */ + delta?: string; + + /** The log probabilities of the transcription. */ + logprobs?: LogProbProperties[] | null; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when a conversation item is retrieved with `conversation.item.retrieve`. + """) +model RealtimeServerEventConversationItemRetrieved extends RealtimeServerEvent { + @doc(""" + The event type, must be `conversation.item.retrieved`. + """) + type: RealtimeServerEventType.conversation_item_retrieved; + + // Tool customization: apply enriched item definition hierarchy + item: RealtimeConversationResponseItem; +} + +// Tool customization (apply_discriminator): apply discriminated type +@doc(""" + Returned when a transcription session is updated with a `transcription_session.update` event, unless + there is an error. + """) +model RealtimeServerEventTranscriptionSessionUpdated + extends RealtimeServerEvent { + @doc(""" + The event type, must be `transcription_session.updated`. + """) + type: RealtimeServerEventType.transcription_session_updated; + + session: RealtimeTranscriptionSessionCreateResponse; +} + +/** Realtime transcription session object configuration. */ +model RealtimeTranscriptionSessionCreateRequest { + /** + * The set of modalities the model can respond with. To disable audio, + * set this to ["text"]. + */ + modalities?: ("text" | "audio")[]; + + @doc(""" + The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + For `pcm16`, input audio must be 16-bit PCM at a 24kHz sample rate, + single channel (mono), and little-endian byte order. + """) + input_audio_format?: "pcm16" | "g711_ulaw" | "g711_alaw" = "pcm16"; + + /** Configuration for input audio transcription. The client can optionally set the language and prompt for transcription, these offer additional guidance to the transcription service. */ + input_audio_transcription?: { + @doc(""" + The model to use for transcription, current options are `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `whisper-1`. + """) + `model`?: "gpt-4o-transcribe" | "gpt-4o-mini-transcribe" | "whisper-1"; + + @doc(""" + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + """) + language?: string; + + @doc(""" + An optional text to guide the model's style or continue a previous audio + segment. + For `whisper-1`, the [prompt is a list of keywords](/docs/guides/speech-to-text#prompting). + For `gpt-4o-transcribe` models, the prompt is a free text string, for example "expect words related to technology". + """) + prompt?: string; + }; + + @doc(""" + Configuration for turn detection, ether Server VAD or Semantic VAD. This can be set to `null` to turn off, in which case the client must manually trigger model response. + Server VAD means that the model will detect the start and end of speech based on audio volume and respond at the end of user speech. + Semantic VAD is more advanced and uses a turn detection model (in conjuction with VAD) to semantically estimate whether the user has finished speaking, then dynamically sets a timeout based on this probability. For example, if user audio trails off with "uhhm", the model will score a low probability of turn end and wait longer for the user to continue speaking. This can be useful for more natural conversations, but may have a higher latency. + """) + turn_detection?: { + /** Type of turn detection. */ + type?: "server_vad" | "semantic_vad" = "server_vad"; + + @doc(""" + Used only for `semantic_vad` mode. The eagerness of the model to respond. `low` will wait longer for the user to continue speaking, `high` will respond more quickly. `auto` is the default and is equivalent to `medium`. + """) + eagerness?: "low" | "medium" | "high" | "auto" = "auto"; + + @doc(""" + Used only for `server_vad` mode. Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + higher threshold will require louder audio to activate the model, and + thus might perform better in noisy environments. + """) + threshold?: float32; + + @doc(""" + Used only for `server_vad` mode. Amount of audio to include before the VAD detected speech (in + milliseconds). Defaults to 300ms. + """) + prefix_padding_ms?: int32; + + @doc(""" + Used only for `server_vad` mode. Duration of silence to detect speech stop (in milliseconds). Defaults + to 500ms. With shorter values the model will respond more quickly, + but may jump in on short pauses from the user. + """) + silence_duration_ms?: int32; + + /** Whether or not to automatically generate a response when a VAD stop event occurs. Not available for transcription sessions. */ + create_response?: boolean = true; + + @doc(""" + Whether or not to automatically interrupt any ongoing response with output to the default + conversation (i.e. `conversation` of `auto`) when a VAD start event occurs. Not available for transcription sessions. + """) + interrupt_response?: boolean = true; + }; + + @doc(""" + Configuration for input audio noise reduction. This can be set to `null` to turn off. + Noise reduction filters audio added to the input audio buffer before it is sent to VAD and the model. + Filtering the audio can improve VAD and turn detection accuracy (reducing false positives) and model performance by improving perception of the input audio. + """) + input_audio_noise_reduction?: { + @doc(""" + Type of noise reduction. `near_field` is for close-talking microphones such as headphones, `far_field` is for far-field microphones such as laptop or conference room microphones. + """) + type?: "near_field" | "far_field"; + } | null = null; + + @doc(""" + The set of items to include in the transcription. Current available items are: + - `item.input_audio_transcription.logprobs` + """) + include?: string[]; + + /** Configuration options for the generated client secret. */ + client_secret?: { + /** Configuration for the ephemeral token expiration. */ + expires_at?: { + @doc(""" + The anchor point for the ephemeral token expiration. Only `created_at` is currently supported. + """) + anchor?: "created_at" = "created_at"; + + @doc(""" + The number of seconds from the anchor point to the expiration. Select a value between `10` and `7200`. + """) + seconds?: int32 = 600; + }; + }; +} + +/** + * A new Realtime transcription session configuration. + * + * When a session is created on the server via REST API, the session object + * also contains an ephemeral key. Default TTL for keys is 10 minutes. This + * property is not present when a session is updated via the WebSocket API. + */ +model RealtimeTranscriptionSessionCreateResponse { + /** + * Ephemeral key returned by the API. Only present when the session is + * created on the server via REST API. + */ + client_secret: { + /** + * Ephemeral key usable in client environments to authenticate connections + * to the Realtime API. Use this in client-side environments rather than + * a standard API token, which should only be used server-side. + */ + value: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** + * Timestamp for when the token expires. Currently, all tokens expire + * after one minute. + */ + @encode("unixTimestamp", int32) + expires_at: utcDateTime; + }; + + /** + * The set of modalities the model can respond with. To disable audio, + * set this to ["text"]. + */ + modalities?: ("text" | "audio")[]; + + @doc(""" + The format of input audio. Options are `pcm16`, `g711_ulaw`, or `g711_alaw`. + """) + input_audio_format?: string; + + /** Configuration of the transcription model. */ + input_audio_transcription?: { + @doc(""" + The model to use for transcription. Can be `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, or `whisper-1`. + """) + `model`?: "gpt-4o-transcribe" | "gpt-4o-mini-transcribe" | "whisper-1"; + + @doc(""" + The language of the input audio. Supplying the input language in + [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format + will improve accuracy and latency. + """) + language?: string; + + /** + * An optional text to guide the model's style or continue a previous audio + * segment. The [prompt](/docs/guides/speech-to-text#prompting) should match + * the audio language. + */ + prompt?: string; + }; + + @doc(""" + Configuration for turn detection. Can be set to `null` to turn off. Server + VAD means that the model will detect the start and end of speech based on + audio volume and respond at the end of user speech. + """) + turn_detection?: { + @doc(""" + Type of turn detection, only `server_vad` is currently supported. + """) + type?: string; + + /** + * Activation threshold for VAD (0.0 to 1.0), this defaults to 0.5. A + * higher threshold will require louder audio to activate the model, and + * thus might perform better in noisy environments. + */ + threshold?: float32; + + /** + * Amount of audio to include before the VAD detected speech (in + * milliseconds). Defaults to 300ms. + */ + prefix_padding_ms?: int32; + + /** + * Duration of silence to detect speech stop (in milliseconds). Defaults + * to 500ms. With shorter values the model will respond more quickly, + * but may jump in on short pauses from the user. + */ + silence_duration_ms?: int32; + }; +} diff --git a/specification/base/typespec/realtime/operations.tsp b/specification/base/typespec/realtime/operations.tsp new file mode 100644 index 000000000..a747240dc --- /dev/null +++ b/specification/base/typespec/realtime/operations.tsp @@ -0,0 +1,45 @@ +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("realtime") +@tag("Realtime") +interface Realtime { + @summary("Starts a real-time session for conversation or transcription.") + startRealtimeSession( + ...RealtimeBetaHeader, + @body requestMessages: RealtimeClientEvent[], + ): RealtimeServerEvent[]; + + @post + @route("sessions") + @operationId("create-realtime-session") + @summary(""" + Create an ephemeral API token for use in client-side applications with the Realtime API. Can be configured with the same session parameters as the session.update client event. + + It responds with a session object, plus a client_secret key which contains a usable ephemeral API token that can be used to authenticate browser clients for the Realtime API. + """) + createEphemeralToken( + @body request: RealtimeSessionCreateRequest, + ): RealtimeSessionCreateResponse | ErrorResponse; + + @post + @route("transcription_sessions") + @operationId("create-realtime-transcription-session") + @summary(""" + Create an ephemeral API token for use in client-side applications with the Realtime API specifically for realtime transcriptions. Can be configured with the same session parameters as the transcription_session.update client event. + + It responds with a session object, plus a client_secret key which contains a usable ephemeral API token that can be used to authenticate browser clients for the Realtime API. + """) + createEphemeralTranscriptionToken( + @body request: RealtimeTranscriptionSessionCreateRequest, + ): RealtimeTranscriptionSessionCreateResponse | ErrorResponse; +} + +alias RealtimeBetaHeader = { + @header("OpenAI-Beta") openAIBeta: "realtime=v1"; +}; diff --git a/specification/base/typespec/responses/custom.tsp b/specification/base/typespec/responses/custom.tsp new file mode 100644 index 000000000..0d2c5e9c8 --- /dev/null +++ b/specification/base/typespec/responses/custom.tsp @@ -0,0 +1,28 @@ +import "@typespec/openapi"; +import "../../entrypoints/sdk.dotnet/specialized-types.tsp"; +import "../common"; +import "./custom/items.tsp"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@error +model ResponseErrorResponse { + error: ResponseError; +} + +union ReasoningItemSummaryPartType { + string, + summary_text: "summary_text", +} + +@discriminator("type") +model ReasoningItemSummaryPart { + type: ReasoningItemSummaryPartType; +} + +model ReasoningItemSummaryTextPart extends ReasoningItemSummaryPart { + type: ReasoningItemSummaryPartType.summary_text; + text: string; +} diff --git a/specification/base/typespec/responses/custom/items.messages.tsp b/specification/base/typespec/responses/custom/items.messages.tsp new file mode 100644 index 000000000..103366db8 --- /dev/null +++ b/specification/base/typespec/responses/custom/items.messages.tsp @@ -0,0 +1,118 @@ +import "@typespec/openapi"; +import "./items.tsp"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +/** The collection of valid roles for responses message items. */ +union ResponsesMessageRole { + system: "system", + developer: "developer", + user: "user", + assistant: "assistant", +} + +/** A response message item, representing a role and content, as provided as client request parameters. */ +@discriminator("role") +model ResponsesMessageItemParam extends ItemParam { + /** The type of the responses item, which is always 'message'. */ + type: ItemType.message; + + /** The role associated with the message. */ + role: ResponsesMessageRole; +} + +/** A message parameter item with the `user` role. */ +model ResponsesUserMessageItemParam extends ResponsesMessageItemParam { + /** The role of the message, which is always `user`. */ + role: ResponsesMessageRole.user; + + /** The content associated with the message. */ + content: InputContent[]; +} + +/** A message parameter item with the `system` role. */ +model ResponsesSystemMessageItemParam extends ResponsesMessageItemParam { + /** The role of the message, which is always `system`. */ + role: ResponsesMessageRole.system; + + /** The content associated with the message. */ + content: InputContent[]; +} + +/** A message parameter item with the `developer` role. */ +model ResponsesDeveloperMessageItemParam extends ResponsesMessageItemParam { + /** The role of the message, which is always `developer`. */ + role: ResponsesMessageRole.developer; + + /** The content associated with the message. */ + content: InputContent[]; +} + +/** A message parameter item with the `assistant` role. */ +model ResponsesAssistantMessageItemParam extends ResponsesMessageItemParam { + /** The role of the message, which is always `assistant`. */ + role: ResponsesMessageRole.assistant; + + /** The content associated with the message. */ + content: OutputContent[]; +} + +/** A response message resource item, representing a role and content, as provided on service responses. */ +@discriminator("role") +model ResponsesMessageItemResource extends ItemResource { + /** The type of the responses item, which is always 'message'. */ + type: ItemType.message; + + @doc(""" + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + """) + status: "in_progress" | "completed" | "incomplete"; + + /** The role associated with the message. */ + role: ResponsesMessageRole; +} + +/** A message resource item with the `user` role. */ +model ResponsesUserMessageItemResource extends ResponsesMessageItemResource { + /** The role of the message, which is always `user`. */ + role: ResponsesMessageRole.user; + + /** The content associated with the message. */ + content: InputContent[]; +} + +/** A message resource item with the `system` role. */ +model ResponsesSystemMessageItemResource extends ResponsesMessageItemResource { + /** The role of the message, which is always `system`. */ + role: ResponsesMessageRole.system; + + /** The content associated with the message. */ + content: InputContent[]; +} + +/** A message resource item with the `developer` role. */ +model ResponsesDeveloperMessageItemResource + extends ResponsesMessageItemResource { + /** The role of the message, which is always `developer`. */ + role: ResponsesMessageRole.developer; + + /** The content associated with the message. */ + content: InputContent[]; +} + +/** A message resource item with the `assistant` role. */ +model ResponsesAssistantMessageItemResource + extends ResponsesMessageItemResource { + /** The role of the message, which is always `assistant`. */ + role: ResponsesMessageRole.assistant; + + /** The content associated with the message. */ + content: OutputContent[]; +} + +model ImplicitUserMessage { + content: string | ItemContent[]; +} diff --git a/specification/base/typespec/responses/custom/items.tsp b/specification/base/typespec/responses/custom/items.tsp new file mode 100644 index 000000000..ae8862ea0 --- /dev/null +++ b/specification/base/typespec/responses/custom/items.tsp @@ -0,0 +1,239 @@ +import "@typespec/openapi"; +import "../../common"; +import "../models.tsp"; +import "./items.messages.tsp"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union ItemType { + message: "message", + file_search_call: "file_search_call", + function_call: "function_call", + function_call_output: "function_call_output", + computer_call: "computer_call", + computer_call_output: "computer_call_output", + web_search_call: "web_search_call", + reasoning: "reasoning", + item_reference: "item_reference", + image_generation_call: "image_generation_call", + code_interpreter_call: "code_interpreter_call", + local_shell_call: "local_shell_call", + local_shell_call_output: "local_shell_call_output", + mcp_list_tools: "mcp_list_tools", + mcp_approval_request: "mcp_approval_request", + mcp_approval_response: "mcp_approval_response", + mcp_call: "mcp_call", +} + +model FileSearchToolCallItemParam extends ItemParam { + type: ItemType.file_search_call; + ...FileSearchToolCallItemBase; +} + +model FileSearchToolCallItemResource extends ItemResource { + type: ItemType.file_search_call; + + @doc(""" + The status of the file search tool call. One of `in_progress`, + `searching`, `incomplete` or `failed`, + """) + status: "in_progress" | "searching" | "completed" | "incomplete" | "failed"; + + ...FileSearchToolCallItemBase; +} + +model ComputerToolCallItemParam extends ItemParam { + type: ItemType.computer_call; + ...ComputerToolCallItemBase; +} + +model ComputerToolCallItemResource extends ItemResource { + type: ItemType.computer_call; + + @doc(""" + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + """) + status: "in_progress" | "completed" | "incomplete"; + + ...ComputerToolCallItemBase; +} + +model ComputerToolCallOutputItemParam extends ItemParam { + type: ItemType.computer_call_output; + ...ComputerToolCallOutputItemBase; +} + +model ComputerToolCallOutputItemResource extends ItemResource { + type: ItemType.computer_call_output; + + @doc(""" + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + """) + status: "in_progress" | "completed" | "incomplete"; + + ...ComputerToolCallOutputItemBase; +} + +model WebSearchToolCallItemParam extends ItemParam { + type: ItemType.web_search_call; + ...WebSearchToolCallItemBase; +} + +model WebSearchToolCallItemResource extends ItemResource { + type: ItemType.web_search_call; + + /** The status of the web search tool call. */ + status: "in_progress" | "searching" | "completed" | "failed"; + + ...WebSearchToolCallItemBase; +} + +model FunctionToolCallItemParam extends ItemParam { + type: ItemType.function_call; + ...FunctionToolCallItemBase; +} + +model FunctionToolCallItemResource extends ItemResource { + type: ItemType.function_call; + + @doc(""" + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + """) + status: "in_progress" | "completed" | "incomplete"; + + ...FunctionToolCallItemBase; +} + +model FunctionToolCallOutputItemParam extends ItemParam { + type: ItemType.function_call_output; + ...FunctionToolCallOutputItemBase; +} + +model FunctionToolCallOutputItemResource extends ItemResource { + type: ItemType.function_call_output; + + @doc(""" + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + """) + status: "in_progress" | "completed" | "incomplete"; + + ...FunctionToolCallOutputItemBase; +} + +model ReasoningItemParam extends ItemParam { + type: ItemType.reasoning; + ...ReasoningItemBase; +} + +model ReasoningItemResource extends ItemResource { + type: ItemType.reasoning; + + @doc(""" + The status of the item. One of `in_progress`, `completed`, or + `incomplete`. Populated when items are returned via API. + """) + status: "in_progress" | "completed" | "incomplete"; + + ...ReasoningItemBase; +} + +model ItemReferenceItemParam extends ItemParam { + type: ItemType.item_reference; + + /** The service-originated ID of the previously generated response item being referenced. */ + id: string; + + ...ItemReferenceItemBase; +} + +// Note: there's no current "resource" representation of item references (they're instead resolved) + +model ImageGenToolCallItemParam extends ItemParam { + type: ItemType.image_generation_call; + ...ImageGenToolCallItemBase; +} + +model ImageGenToolCallItemResource extends ItemResource { + type: ItemType.image_generation_call; + status: "in_progress" | "completed" | "generating" | "failed"; + ...ImageGenToolCallItemBase; +} + +model CodeInterpreterToolCallItemParam extends ItemParam { + type: ItemType.code_interpreter_call; + ...CodeInterpreterToolCallItemBase; +} + +model CodeInterpreterToolCallItemResource extends ItemResource { + type: ItemType.code_interpreter_call; + status: "in_progress" | "interpreting" | "completed"; + ...CodeInterpreterToolCallItemBase; +} + +model LocalShellToolCallItemParam extends ItemParam { + type: ItemType.local_shell_call; + ...LocalShellToolCallItemBase; +} + +model LocalShellToolCallItemResource extends ItemResource { + type: ItemType.local_shell_call; + status: "in_progress" | "completed" | "incomplete"; + ...LocalShellToolCallItemBase; +} + +model LocalShellToolCallOutputItemParam extends ItemParam { + type: ItemType.local_shell_call_output; + ...LocalShellToolCallOutputItemBase; +} + +model LocalShellToolCallOutputItemResource extends ItemResource { + type: ItemType.local_shell_call_output; + status: "in_progress" | "completed" | "incomplete"; + ...LocalShellToolCallOutputItemBase; +} + +model MCPListToolsItemParam extends ItemParam { + type: ItemType.mcp_list_tools; + ...MCPListToolsItemBase; +} + +model MCPListToolsItemResource extends ItemResource { + type: ItemType.mcp_list_tools; + ...MCPListToolsItemBase; +} + +model MCPApprovalRequestItemParam extends ItemParam { + type: ItemType.mcp_approval_request; + ...MCPApprovalRequestItemBase; +} + +model MCPApprovalRequestItemResource extends ItemResource { + type: ItemType.mcp_approval_request; + ...MCPApprovalRequestItemBase; +} + +model MCPApprovalResponseItemParam extends ItemParam { + type: ItemType.mcp_approval_response; + ...MCPApprovalResponseItemBase; +} + +model MCPApprovalResponseItemResource extends ItemResource { + type: ItemType.mcp_approval_response; + ...MCPApprovalResponseItemBase; +} + +model MCPCallItemParam extends ItemParam { + type: ItemType.mcp_call; + ...MCPCallItemBase; +} + +model MCPCallItemResource extends ItemResource { + type: ItemType.mcp_call; + ...MCPCallItemBase; +} diff --git a/specification/base/typespec/responses/main.tsp b/specification/base/typespec/responses/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/responses/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/responses/models.tsp b/specification/base/typespec/responses/models.tsp new file mode 100644 index 000000000..04bb035be --- /dev/null +++ b/specification/base/typespec/responses/models.tsp @@ -0,0 +1,2630 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../common"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from FileSearchToolCallItemBase.results +alias FileSearchToolCallItemBaseResult = { + /** The unique ID of the file. */ + file_id?: string; + + /** The text that was retrieved from the file. */ + text?: string; + + /** The name of the file. */ + filename?: string; + + attributes?: VectorStoreFileAttributes; + + /** The relevance score of the file - a value between 0 and 1. */ + score?: float32; +}; + +// Tool generated type. Extracts from CodeInterpreterFileOutput.files +alias CodeInterpreterFileOutputFile = { + /** The MIME type of the file. */ + mime_type: string; + + /** The ID of the file. */ + file_id: string; +}; + +model CreateResponse { + ...ModelResponsePropertiesForRequest; + ...ResponseProperties; + + // Tool customization: Apply renamed Item -> ItemParam + /** + * Text, image, or file inputs to the model, used to generate a response. + * + * Learn more: + * - [Text inputs and outputs](/docs/guides/text) + * - [Image inputs](/docs/guides/images) + * - [File inputs](/docs/guides/pdf-files) + * - [Conversation state](/docs/guides/conversation-state) + * - [Function calling](/docs/guides/function-calling) + */ + input: string | (ImplicitUserMessage | ItemParam)[]; + + @doc(""" + Specify additional output data to include in the model response. Currently + supported values are: + - `file_search_call.results`: Include the search results of + the file search tool call. + - `message.input_image.image_url`: Include image urls from the input message. + - `computer_call_output.output.image_url`: Include image urls from the computer call output. + - `reasoning.encrypted_content`: Includes an encrypted version of reasoning + tokens in reasoning item outputs. This enables reasoning items to be used in + multi-turn conversations when using the Responses API statelessly (like + when the `store` parameter is set to `false`, or when an organization is + enrolled in the zero data retention program). + - `code_interpreter_call.outputs`: Includes the outputs of python code execution + in code interpreter tool call items. + """) + include?: Includable[] | null; + + /** Whether to allow the model to run tool calls in parallel. */ + parallel_tool_calls?: boolean | null = true; + + /** + * Whether to store the generated model response for later retrieval via + * API. + */ + store?: boolean | null = true; + + /** + * If set to true, the model response data will be streamed to the client + * as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). + * See the [Streaming section below](/docs/api-reference/responses-streaming) + * for more information. + */ + stream?: boolean | null = false; +} + +model Response { + ...ModelResponsePropertiesForResponse; + ...ResponseProperties; + + /** Unique identifier for this Response. */ + id: string; + + @doc(""" + The object type of this resource - always set to `response`. + """) + object: "response"; + + @doc(""" + The status of the response generation. One of `completed`, `failed`, + `in_progress`, `cancelled`, `queued`, or `incomplete`. + """) + status?: + | "completed" + | "failed" + | "in_progress" + | "cancelled" + | "queued" + | "incomplete"; + + // Tool customization: Fully qualify as an integer-based unix timestamp + /** Unix timestamp (in seconds) of when this Response was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + error: ResponseError | null; + + /** Details about why the response is incomplete. */ + incomplete_details: { + /** The reason why the response is incomplete. */ + reason?: "max_output_tokens" | "content_filter"; + } | null; + + @doc(""" + An array of content items generated by the model. + + - The length and order of items in the `output` array is dependent + on the model's response. + - Rather than accessing the first item in the `output` array and + assuming it's an `assistant` message with the content generated by + the model, you might consider using the `output_text` property where + supported in SDKs. + """) + output: OutputItem[]; + + @doc(""" + SDK-only convenience property that contains the aggregated text output + from all `output_text` items in the `output` array, if any are present. + Supported in the Python and JavaScript SDKs. + """) + output_text?: string | null; + + usage?: ResponseUsage; + + /** Whether to allow the model to run tool calls in parallel. */ + parallel_tool_calls: boolean = true; +} + +model ResponseProperties { + /** + * The unique ID of the previous response to the model. Use this to + * create multi-turn conversations. Learn more about + * [conversation state](/docs/guides/conversation-state). + */ + previous_response_id?: string | null; + + @doc(""" + Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI + offers a wide range of models with different capabilities, performance + characteristics, and price points. Refer to the [model guide](/docs/models) + to browse and compare available models. + """) + `model`?: ModelIdsResponses; + + reasoning?: Reasoning | null; + + /** + * Whether to run the model response in the background. + * [Learn more](/docs/guides/background). + */ + background?: boolean | null = false; + + /** An upper bound for the number of tokens that can be generated for a response, including visible output tokens and [reasoning tokens](/docs/guides/reasoning). */ + max_output_tokens?: int32 | null; + + @doc(""" + Inserts a system (or developer) message as the first item in the model's context. + + When using along with `previous_response_id`, the instructions from a previous + response will not be carried over to the next response. This makes it simple + to swap out system (or developer) messages in new responses. + """) + instructions?: string | null; + + /** + * Configuration options for a text response from the model. Can be plain + * text or structured JSON data. Learn more: + * - [Text inputs and outputs](/docs/guides/text) + * - [Structured Outputs](/docs/guides/structured-outputs) + */ + text?: { + // Tool customization: Employ discriminated type base + format?: ResponseTextFormatConfiguration; + }; + + @doc(""" + An array of tools the model may call while generating a response. You + can specify which tool to use by setting the `tool_choice` parameter. + + The two categories of tools you can provide the model are: + + - **Built-in tools**: Tools that are provided by OpenAI that extend the + model's capabilities, like [web search](/docs/guides/tools-web-search) + or [file search](/docs/guides/tools-file-search). Learn more about + [built-in tools](/docs/guides/tools). + - **Function calls (custom tools)**: Functions that are defined by you, + enabling the model to call your own code. Learn more about + [function calling](/docs/guides/function-calling). + """) + tools?: Tool[]; + + // Tool customization: Employ discriminated type base for tool objects + @doc(""" + How the model should select which tool (or tools) to use when generating + a response. See the `tools` parameter to see how to specify which tools + the model can call. + """) + tool_choice?: ToolChoiceOptions | ToolChoiceObject; + + @doc(""" + The truncation strategy to use for the model response. + - `auto`: If the context of this response and previous ones exceeds + the model's context window size, the model will truncate the + response to fit the context window by dropping input items in the + middle of the conversation. + - `disabled` (default): If a model response will exceed the context window + size for a model, the request will fail with a 400 error. + """) + truncation?: "auto" | "disabled" | null = "disabled"; +} + +// Tool customization: Alias to avoid circular reference +alias ModelIds = ModelIdsResponses; + +union ModelIdsResponses { + ModelIdsShared, + + | "o1-pro" + | "o1-pro-2025-03-19" + | "o3-pro" + | "o3-pro-2025-06-10" + | "computer-use-preview" + | "computer-use-preview-2025-03-11", +} + +// Tool customization: Establish a discriminated type base +/** Content item used to generate a response. */ +@discriminator("type") +model ItemParam { + type: ItemType; +} + +// Tool customization: Rename to supply base for split input/output models +/** + * The results of a file search tool call. See the + * [file search guide](/docs/guides/tools-file-search) for more information. + */ +alias FileSearchToolCallItemBase = { + /** The queries used to search for files. */ + queries: string[]; + + /** The results of the file search tool call. */ + results?: FileSearchToolCallItemBaseResult[] | null; +}; + +@@doc(FileSearchToolCallItemResource, + """ + The results of a file search tool call. See the + [file search guide](/docs/guides/tools-file-search) for more information. + + """ +); +@@doc(FileSearchToolCallItemParam, + """ + The results of a file search tool call. See the + [file search guide](/docs/guides/tools-file-search) for more information. + + """ +); +// Tool customization: Rename to supply base for split input/output models +/** + * A tool call to run a function. See the + * [function calling guide](/docs/guides/function-calling) for more information. + */ +alias FunctionToolCallItemBase = { + /** The unique ID of the function tool call generated by the model. */ + call_id: string; + + /** The name of the function to run. */ + name: string; + + /** A JSON string of the arguments to pass to the function. */ + arguments: string; +}; + +@@doc(FunctionToolCallItemResource, + """ + A tool call to run a function. See the + [function calling guide](/docs/guides/function-calling) for more information. + + """ +); +@@doc(FunctionToolCallItemParam, + """ + A tool call to run a function. See the + [function calling guide](/docs/guides/function-calling) for more information. + + """ +); +// Tool customization: Rename to supply base for split input/output models +/** The output of a function tool call. */ +alias FunctionToolCallOutputItemBase = { + /** The unique ID of the function tool call generated by the model. */ + call_id: string; + + /** A JSON string of the output of the function tool call. */ + output: string; +}; + +@@doc(FunctionToolCallOutputItemResource, + """ + The output of a function tool call. + + """ +); +@@doc(FunctionToolCallOutputItemParam, + """ + The output of a function tool call. + + """ +); +// Tool customization: Rename to supply base for split input/output models +/** + * The results of a web search tool call. See the + * [web search guide](/docs/guides/tools-web-search) for more information. + */ +alias WebSearchToolCallItemBase = {}; + +@@doc(WebSearchToolCallItemResource, + """ + The results of a web search tool call. See the + [web search guide](/docs/guides/tools-web-search) for more information. + + """ +); +@@doc(WebSearchToolCallItemParam, + """ + The results of a web search tool call. See the + [web search guide](/docs/guides/tools-web-search) for more information. + + """ +); +// Tool customization: Rename to supply base for split input/output models +/** + * A tool call to a computer use tool. See the + * [computer use guide](/docs/guides/tools-computer-use) for more information. + */ +alias ComputerToolCallItemBase = { + /** An identifier used when responding to the tool call with output. */ + call_id: string; + + action: ComputerAction; + + /** The pending safety checks for the computer call. */ + pending_safety_checks: ComputerToolCallSafetyCheck[]; +}; + +@@doc(ComputerToolCallItemResource, + """ + A tool call to a computer use tool. See the + [computer use guide](/docs/guides/tools-computer-use) for more information. + + """ +); +@@doc(ComputerToolCallItemParam, + """ + A tool call to a computer use tool. See the + [computer use guide](/docs/guides/tools-computer-use) for more information. + + """ +); +// Tool customization: Rename to supply base for split input/output models +/** The output of a computer tool call. */ +alias ComputerToolCallOutputItemBase = { + /** The ID of the computer tool call that produced the output. */ + call_id: string; + + /** + * The safety checks reported by the API that have been acknowledged by the + * developer. + */ + acknowledged_safety_checks?: ComputerToolCallSafetyCheck[]; + + // Tool customization: Apply discriminated type + output: ComputerToolCallOutputItemOutput; +}; + +@@doc(ComputerToolCallOutputItemResource, + """ + The output of a computer tool call. + + """ +); +@@doc(ComputerToolCallOutputItemParam, + """ + The output of a computer tool call. + + """ +); +// Tool customization: Rename to supply base for split input/output models +alias ReasoningItemBase = { + @doc(""" + The encrypted content of the reasoning item - populated when a response is + generated with `reasoning.encrypted_content` in the `include` parameter. + """) + encrypted_content?: string | null; + + // Tool customization: Use customized discriminated type for summary parts + /** Reasoning text contents. */ + summary: ReasoningItemSummaryPart[]; +}; + +@@doc(ReasoningItemResource, + """ + A description of the chain of thought used by a reasoning model while generating + a response. Be sure to include these items in your `input` to the Responses API + for subsequent turns of a conversation if you are manually + [managing context](/docs/guides/conversation-state). + + """ +); +@@doc(ReasoningItemParam, + """ + A description of the chain of thought used by a reasoning model while generating + a response. Be sure to include these items in your `input` to the Responses API + for subsequent turns of a conversation if you are manually + [managing context](/docs/guides/conversation-state). + + """ +); +// Tool customization: Rename to supply base for split input/output models +/** An internal identifier for an item to reference. */ +alias ItemReferenceItemBase = {}; + +@@doc(ItemReferenceItemParam, + """ + An internal identifier for an item to reference. + """ +); +// Tool customization: Establish a discriminated type base for tools +/** A tool that can be used to generate a response. */ +union ToolType { + string, + file_search: "file_search", + function: "function", + computer_use_preview: "computer_use_preview", + web_search_preview: "web_search_preview", + mcp: "mcp", + code_interpreter: "code_interpreter", + image_generation: "image_generation", + local_shell: "local_shell", +} +@discriminator("type") +model Tool { + type: ToolType; +} + +@doc(""" + Controls which (if any) tool is called by the model. + + `none` means the model will not call any tool and instead generates a message. + + `auto` means the model can pick between generating a message or calling one or + more tools. + + `required` means the model must call one or more tools. + """) +union ToolChoiceOptions { + "none", + "auto", + "required", +} + +// Tool customization: Establish a discriminated type base +/** + * Indicates that the model should use a built-in tool to generate a response. + * [Learn more about built-in tools](/docs/guides/tools). + */ +union ToolChoiceObjectType { + string, + file_search: "file_search", + function: "function", + computer: "computer_use_preview", + web_search: "web_search_preview", + image_generation: "image_generation", + code_interpreter: "code_interpreter", + mcp: "mcp", +} +@discriminator("type") +model ToolChoiceObject { + type: ToolChoiceObjectType; +} +model ToolChoiceObjectFileSearch extends ToolChoiceObject { + type: ToolChoiceObjectType.file_search; +} +model ToolChoiceObjectComputer extends ToolChoiceObject { + type: ToolChoiceObjectType.computer; +} +model ToolChoiceObjectWebSearch extends ToolChoiceObject { + type: ToolChoiceObjectType.web_search; +} +model ToolChoiceObjectImageGen extends ToolChoiceObject { + type: ToolChoiceObjectType.image_generation; +} +model ToolChoiceObjectCodeInterpreter extends ToolChoiceObject { + type: ToolChoiceObjectType.code_interpreter; +} +model ToolChoiceObjectMCP extends ToolChoiceObject { + type: ToolChoiceObjectType.mcp; +} + +// Tool customization (apply_discriminator): Apply discriminated type base +/** Use this option to force the model to call a specific function. */ +model ToolChoiceObjectFunction extends ToolChoiceObject { + @doc(""" + For function calling, the type is always `function`. + """) + type: ToolChoiceObjectType.function; + + /** The name of the function to call. */ + name: string; +} + +// Tool customization (apply_discriminator): Apply discriminated type base for tools +/** Defines a function in your own code the model can choose to call. Learn more about [function calling](https://platform.openai.com/docs/guides/function-calling). */ +model FunctionTool extends Tool { + @doc(""" + The type of the function tool. Always `function`. + """) + type: ToolType.function; + + /** The name of the function to call. */ + name: string; + + /** A description of the function. Used by the model to determine whether or not to call the function. */ + description?: string | null; + + /** A JSON schema object describing the parameters of the function. */ + parameters: unknown | null; + + @doc(""" + Whether to enforce strict parameter validation. Default `true`. + """) + strict: boolean | null; +} + +// Tool customization (apply_discriminator): Apply discriminated type base for tools +/** A tool that searches for relevant content from uploaded files. Learn more about the [file search tool](https://platform.openai.com/docs/guides/tools-file-search). */ +model FileSearchTool extends Tool { + @doc(""" + The type of the file search tool. Always `file_search`. + """) + type: ToolType.file_search; + + /** The IDs of the vector stores to search. */ + vector_store_ids: string[]; + + /** The maximum number of results to return. This number should be between 1 and 50 inclusive. */ + max_num_results?: int32; + + /** Ranking options for search. */ + ranking_options?: RankingOptions; + + /** A filter to apply. */ + filters?: Filters | null; +} + +// Tool customization (apply_discriminator): Apply discriminated type base for tools +/** A tool that controls a virtual computer. Learn more about the [computer tool](https://platform.openai.com/docs/guides/tools-computer-use). */ +model ComputerUsePreviewTool extends Tool { + @doc(""" + The type of the computer use tool. Always `computer_use_preview`. + """) + type: ToolType.computer_use_preview; + + /** The type of computer environment to control. */ + environment: "windows" | "mac" | "linux" | "ubuntu" | "browser"; + + /** The width of the computer display. */ + display_width: int32; + + /** The height of the computer display. */ + display_height: int32; +} + +// Tool customization (apply_discriminator): Apply discriminated type base for tools +/** This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://platform.openai.com/docs/guides/tools-web-search). */ +model WebSearchPreviewTool extends Tool { + @doc(""" + The type of the web search tool. One of `web_search_preview` or `web_search_preview_2025_03_11`. + """) + type: ToolType.web_search_preview; + + // Tool customization: Use a custom discriminated type basis for web search locations + /** The user's location. */ + user_location?: Location | null; + + @doc(""" + High level guidance for the amount of context window space to use for the search. One of `low`, `medium`, or `high`. `medium` is the default. + """) + search_context_size?: "low" | "medium" | "high"; +} + +// Tool customization: Establish a discriminated base for location approximation +union LocationType { + string, + approximate: "approximate", +} +@discriminator("type") +model Location { + type: LocationType; +} +model ApproximateLocation extends Location { + type: LocationType.approximate; + country?: string | null; + region?: string | null; + city?: string | null; + timezone?: string | null; +} + +/** A pending safety check for the computer call. */ +model ComputerCallSafetyCheckParam { + /** The ID of the pending safety check. */ + id: string; + + /** The type of the pending safety check. */ + code?: string | null; + + /** Details about the pending safety check. */ + message?: string | null; +} + +/** A pending safety check for the computer call. */ +model ComputerToolCallSafetyCheck { + /** The ID of the pending safety check. */ + id: string; + + /** The type of the pending safety check. */ + code: string; + + /** Details about the pending safety check. */ + message: string; +} + +// Tool customization (apply_discriminator): Apply base discriminator type for ComputerAction and align naming +/** A click action. */ +model ComputerActionClick extends ComputerAction { + @doc(""" + Specifies the event type. For a click action, this property is + always set to `click`. + """) + type: ComputerActionType.click; + + @doc(""" + Indicates which mouse button was pressed during the click. One of `left`, `right`, `wheel`, `back`, or `forward`. + """) + button: "left" | "right" | "wheel" | "back" | "forward"; + + /** The x-coordinate where the click occurred. */ + x: int32; + + /** The y-coordinate where the click occurred. */ + y: int32; +} + +// Tool customization: Establish discriminated type base +union ComputerActionType { + screenshot: "screenshot", + click: "click", + double_click: "double_click", + scroll: "scroll", + type: "type", + wait: "wait", + keypress: "keypress", + drag: "drag", + move: "move", +} +@discriminator("type") +model ComputerAction { + type: ComputerActionType; +} + +// Tool customization: Establish a discriminated type basis for computer call outputs +/** A computer screenshot image used with the computer use tool. */ +union ComputerToolCallOutputItemOutputType { + string, + screenshot: "computer_screenshot", +} +@discriminator("type") +model ComputerToolCallOutputItemOutput { + type: ComputerToolCallOutputItemOutputType; +} +model ComputerToolCallOutputItemOutputComputerScreenshot + extends ComputerToolCallOutputItemOutput { + type: ComputerToolCallOutputItemOutputType.screenshot; + image_url?: string; + file_id?: string; +} + +// Tool customization (apply_discriminator): Apply base discriminator type for ComputerAction and align naming +/** A double click action. */ +model ComputerActionDoubleClick extends ComputerAction { + @doc(""" + Specifies the event type. For a double click action, this property is + always set to `double_click`. + """) + type: ComputerActionType.double_click; + + /** The x-coordinate where the double click occurred. */ + x: int32; + + /** The y-coordinate where the double click occurred. */ + y: int32; +} + +// Tool customization (apply_discriminator): Apply base discriminator type for ComputerAction and align naming +/** A drag action. */ +model ComputerActionDrag extends ComputerAction { + @doc(""" + Specifies the event type. For a drag action, this property is + always set to `drag`. + """) + type: ComputerActionType.drag; + + @doc(""" + An array of coordinates representing the path of the drag action. Coordinates will appear as an array + of objects, eg + ``` + [ + { x: 100, y: 200 }, + { x: 200, y: 300 } + ] + ``` + """) + path: Coordinate[]; +} + +// Tool customization (apply_discriminator): Apply base discriminator type for ComputerAction and align naming +/** A mouse move action. */ +model ComputerActionMove extends ComputerAction { + @doc(""" + Specifies the event type. For a move action, this property is + always set to `move`. + """) + type: ComputerActionType.move; + + /** The x-coordinate to move to. */ + x: int32; + + /** The y-coordinate to move to. */ + y: int32; +} + +// Tool customization (apply_discriminator): Apply base discriminator type for ComputerAction and align naming +/** A screenshot action. */ +model ComputerActionScreenshot extends ComputerAction { + @doc(""" + Specifies the event type. For a screenshot action, this property is + always set to `screenshot`. + """) + type: ComputerActionType.screenshot; +} + +// Tool customization (apply_discriminator): Apply base discriminator type for ComputerAction and align naming +/** A scroll action. */ +model ComputerActionScroll extends ComputerAction { + @doc(""" + Specifies the event type. For a scroll action, this property is + always set to `scroll`. + """) + type: ComputerActionType.scroll; + + /** The x-coordinate where the scroll occurred. */ + x: int32; + + /** The y-coordinate where the scroll occurred. */ + y: int32; + + /** The horizontal scroll distance. */ + scroll_x: int32; + + /** The vertical scroll distance. */ + scroll_y: int32; +} + +// Tool customization (apply_discriminator): Apply base discriminator type for ComputerAction and align naming +/** An action to type in text. */ +model ComputerActionTypeKeys extends ComputerAction { + @doc(""" + Specifies the event type. For a type action, this property is + always set to `type`. + """) + type: ComputerActionType.type; + + /** The text to type. */ + text: string; +} + +// Tool customization (apply_discriminator): Apply base discriminator type for ComputerAction and align naming +/** A wait action. */ +model ComputerActionWait extends ComputerAction { + @doc(""" + Specifies the event type. For a wait action, this property is + always set to `wait`. + """) + type: ComputerActionType.wait; +} + +// Tool customization (apply_discriminator): Apply base discriminator type for ComputerAction and align naming +/** A collection of keypresses the model would like to perform. */ +model ComputerActionKeyPress extends ComputerAction { + @doc(""" + Specifies the event type. For a keypress action, this property is + always set to `keypress`. + """) + type: ComputerActionType.keypress; + + /** + * The combination of keys the model is requesting to be pressed. This is an + * array of strings, each representing a key. + */ + keys: string[]; +} + +@doc(""" + An x/y coordinate pair, e.g. `{ x: 100, y: 200 }`. + """) +model Coordinate { + /** The x-coordinate. */ + x: int32; + + /** The y-coordinate. */ + y: int32; +} + +/** + * **o-series models only** + * + * Configuration options for + * [reasoning models](https://platform.openai.com/docs/guides/reasoning). + */ +model Reasoning { + effort?: ReasoningEffort | null = "medium"; + + @doc(""" + A summary of the reasoning performed by the model. This can be + useful for debugging and understanding the model's reasoning process. + One of `auto`, `concise`, or `detailed`. + """) + summary?: "auto" | "concise" | "detailed" | null; + + // Tool customization: Correct inapplicable default + #suppress "deprecated" "Warning unnecessary for spec description of deprecation" + #deprecated "This field is marked as deprecated." + @doc(""" + **Deprecated:** use `summary` instead. + + A summary of the reasoning performed by the model. This can be + useful for debugging and understanding the model's reasoning process. + One of `auto`, `concise`, or `detailed`. + """) + generate_summary?: "auto" | "concise" | "detailed" | null = null; +} + +// Tool customization: Establish discriminated type base to increase union precision, rename for clarity +@doc(""" + An object specifying the format that the model must output. + + Configuring `{ "type": "json_schema" }` enables Structured Outputs, + which ensures the model will match your supplied JSON schema. Learn more in the + [Structured Outputs guide](/docs/guides/structured-outputs). + + The default format is `{ "type": "text" }` with no additional options. + + **Not recommended for gpt-4o and newer models:** + + Setting to `{ "type": "json_object" }` enables the older JSON mode, which + ensures the message the model generates is valid JSON. Using `json_schema` + is preferred for models that support it. + """) +union ResponseTextFormatConfigurationType { + string, + text: "text", + json_schema: "json_schema", + json_object: "json_object", +} +@discriminator("type") +model ResponseTextFormatConfiguration { + type: ResponseTextFormatConfigurationType; +} +model ResponseTextFormatConfigurationText + extends ResponseTextFormatConfiguration { + type: ResponseTextFormatConfigurationType.text; +} +model ResponseTextFormatConfigurationJsonObject + extends ResponseTextFormatConfiguration { + type: ResponseTextFormatConfigurationType.json_object; +} + +// Tool customization (apply_discriminator): Apply base type +/** + * JSON Schema response format. Used to generate structured JSON responses. + * Learn more about [Structured Outputs](/docs/guides/structured-outputs). + */ +model ResponseTextFormatConfigurationJsonSchema + extends ResponseTextFormatConfiguration { + @doc(""" + The type of response format being defined. Always `json_schema`. + """) + type: ResponseTextFormatConfigurationType.json_schema; + + /** + * A description of what the response format is for, used by the model to + * determine how to respond in the format. + */ + description?: string; + + /** + * The name of the response format. Must be a-z, A-Z, 0-9, or contain + * underscores and dashes, with a maximum length of 64. + */ + name: string; + + schema: ResponseFormatJsonSchemaSchema; + + @doc(""" + Whether to enable strict schema adherence when generating the output. + If set to true, the model will always follow the exact schema defined + in the `schema` field. Only a subset of JSON Schema is supported when + `strict` is `true`. To learn more, read the [Structured Outputs + guide](/docs/guides/structured-outputs). + """) + strict?: boolean | null = false; +} + +@doc(""" + Specify additional output data to include in the model response. Currently + supported values are: + - `file_search_call.results`: Include the search results of + the file search tool call. + - `message.input_image.image_url`: Include image urls from the input message. + - `computer_call_output.output.image_url`: Include image urls from the computer call output. + - `reasoning.encrypted_content`: Includes an encrypted version of reasoning + tokens in reasoning item outputs. This enables reasoning items to be used in + multi-turn conversations when using the Responses API statelessly (like + when the `store` parameter is set to `false`, or when an organization is + enrolled in the zero data retention program). + - `code_interpreter_call.outputs`: Includes the outputs of python code execution + in code interpreter tool call items. + """) +union Includable { + "file_search_call.results", + "message.input_image.image_url", + "computer_call_output.output.image_url", + "reasoning.encrypted_content", + "code_interpreter_call.outputs", +} + +// Tool customization: Establish discriminated type hierarchy +/** Multi-modal input and output contents. */ +union ItemContentType { + input_text: "input_text", + input_audio: "input_audio", + input_image: "input_image", + input_file: "input_file", + output_text: "output_text", + output_audio: "output_audio", + refusal: "refusal", +} +@discriminator("type") +model ItemContent { + type: ItemContentType; +} + +// Tool customization (apply_discriminator): Apply discriminated type base, rename for clarity +/** An audio input to the model. */ +model ItemContentInputAudio extends ItemContent { + @doc(""" + The type of the input item. Always `input_audio`. + """) + type: ItemContentType.input_audio; + + /** Base64-encoded audio data. */ + data: string; + + @doc(""" + The format of the audio data. Currently supported formats are `mp3` and + `wav`. + """) + format: "mp3" | "wav"; +} + +/** + * A list of one or many input items to the model, containing different content + * types. + */ +model InputMessageContentList is InputContent[]; + +// Tool customization (apply_discriminator): Apply discriminated type base, rename for clarity +/** An audio output from the model. */ +model ItemContentOutputAudio extends ItemContent { + @doc(""" + The type of the output audio. Always `output_audio`. + """) + type: ItemContentType.output_audio; + + /** Base64-encoded audio data from the model. */ + data: string; + + /** The transcript of the audio data from the model. */ + transcript: string; +} + +// Tool customization (apply_discriminator): Apply discriminated type base, rename for clarity +/** A refusal from the model. */ +model ItemContentRefusal extends ItemContent { + @doc(""" + The type of the refusal. Always `refusal`. + """) + type: ItemContentType.refusal; + + /** The refusal explanationfrom the model. */ + refusal: string; +} + +// Tool customization: Establish discriminated type hierarchy +union AnnotationType { + string, + file_citation: "file_citation", + url_citation: "url_citation", + file_path: "file_path", + container_file_citation: "container_file_citation", +} +@discriminator("type") +model Annotation { + type: AnnotationType; +} + +// Tool customization (apply_discriminator): Apply discriminated base type, rename for consistency and clarity +/** A citation to a file. */ +model AnnotationFileCitation extends Annotation { + @doc(""" + The type of the file citation. Always `file_citation`. + """) + type: AnnotationType.file_citation; + + /** The ID of the file. */ + file_id: string; + + /** The index of the file in the list of files. */ + index: int32; +} + +// Tool customization (apply_discriminator): Apply discriminated base type, rename for consistency and clarity +/** A citation for a web resource used to generate a model response. */ +model AnnotationUrlCitation extends Annotation { + @doc(""" + The type of the URL citation. Always `url_citation`. + """) + type: AnnotationType.url_citation; + + // Tool customization: url uses the url type + /** The URL of the web resource. */ + url: url; + + /** The index of the first character of the URL citation in the message. */ + start_index: int32; + + /** The index of the last character of the URL citation in the message. */ + end_index: int32; + + /** The title of the web resource. */ + title: string; +} + +/** A citation for a container file used to generate a model response. */ +model ContainerFileCitationBody { + @doc(""" + The type of the container file citation. Always `container_file_citation`. + """) + type: "container_file_citation" = "container_file_citation"; + + /** The ID of the container file. */ + container_id: string; + + /** The ID of the file. */ + file_id: string; + + /** The index of the first character of the container file citation in the message. */ + start_index: int32; + + /** The index of the last character of the container file citation in the message. */ + end_index: int32; +} + +// Tool customization (apply_discriminator): Apply discriminated base type, rename for consistency and clarity +/** A path to a file. */ +model AnnotationFilePath extends Annotation { + @doc(""" + The type of the file path. Always `file_path`. + """) + type: AnnotationType.file_path; + + /** The ID of the file. */ + file_id: string; + + /** The index of the file in the list of files. */ + index: int32; +} + +// Tool customization (apply_discriminator): Apply discriminated type base, rename for clarity +/** A text input to the model. */ +model ItemContentInputText extends ItemContent { + @doc(""" + The type of the input item. Always `input_text`. + """) + type: ItemContentType.input_text; + + /** The text input to the model. */ + text: string; +} + +// Tool customization (apply_discriminator): Apply discriminated type base, rename for clarity +/** An image input to the model. Learn about [image inputs](/docs/guides/vision). */ +model ItemContentInputImage extends ItemContent { + @doc(""" + The type of the input item. Always `input_image`. + """) + type: ItemContentType.input_image; + + /** The URL of the image to be sent to the model. A fully qualified URL or base64 encoded image in a data URL. */ + image_url?: string | null; + + /** The ID of the file to be sent to the model. */ + file_id?: string | null; + + // Tool customization: Fix optionality, default of property + @doc(""" + The detail level of the image to be sent to the model. One of `high`, `low`, or `auto`. Defaults to `auto`. + """) + detail?: "low" | "high" | "auto" = "auto"; +} + +// Tool customization (apply_discriminator): Apply discriminated type base, rename for clarity +/** A file input to the model. */ +model ItemContentInputFile extends ItemContent { + @doc(""" + The type of the input item. Always `input_file`. + """) + type: ItemContentType.input_file; + + /** The ID of the file to be sent to the model. */ + file_id?: string | null; + + /** The name of the file to be sent to the model. */ + filename?: string; + + /** The content of the file to be sent to the model. */ + file_data?: string; +} + +model RankingOptions { + /** The ranker to use for the file search. */ + ranker?: "auto" | "default-2024-11-15"; + + /** The score threshold for the file search, a number between 0 and 1. Numbers closer to 1 will attempt to return only the most relevant results, but may return fewer results. */ + score_threshold?: float32; +} + +union Filters { + ComparisonFilter, + CompoundFilter, +} + +// Tool customization (apply_discriminator): Apply discriminated type base, rename for clarity +/** A text output from the model. */ +model ItemContentOutputText extends ItemContent { + @doc(""" + The type of the output text. Always `output_text`. + """) + type: ItemContentType.output_text; + + /** The text output from the model. */ + text: string; + + /** The annotations of the text output. */ + annotations: Annotation[]; + + logprobs?: LogProb[]; +} + +/** + * Represents token usage details including input tokens, output tokens, + * a breakdown of output tokens, and the total tokens used. + */ +model ResponseUsage { + /** The number of input tokens. */ + input_tokens: int32; + + /** A detailed breakdown of the input tokens. */ + input_tokens_details: { + /** + * The number of tokens that were retrieved from the cache. + * [More on prompt caching](/docs/guides/prompt-caching). + */ + cached_tokens: int32; + }; + + /** The number of output tokens. */ + output_tokens: int32; + + /** A detailed breakdown of the output tokens. */ + output_tokens_details: { + /** The number of reasoning tokens. */ + reasoning_tokens: int32; + }; + + /** The total number of tokens used. */ + total_tokens: int32; +} + +/** An error object returned when the model fails to generate a Response. */ +model ResponseError { + code: ResponseErrorCode; + + /** A human-readable description of the error. */ + message: string; +} + +/** The error code for the response. */ +union ResponseErrorCode { + "server_error", + "rate_limit_exceeded", + "invalid_prompt", + "vector_store_timeout", + "invalid_image", + "invalid_image_format", + "invalid_base64_image", + "invalid_image_url", + "image_too_large", + "image_too_small", + "image_parse_error", + "image_content_policy_violation", + "invalid_image_mode", + "image_file_too_large", + "unsupported_image_media_type", + "empty_image_file", + "failed_to_download_image", + "image_file_not_found", +} + +/** A list of Response items. */ +model ResponseItemList { + @doc(""" + The type of object returned, must be `list`. + """) + object: "list"; + + /** A list of items used to generate this response. */ + data: ItemResource[]; + + /** Whether there are more items available. */ + has_more: boolean; + + /** The ID of the first item in the list. */ + first_id: string; + + /** The ID of the last item in the list. */ + last_id: string; +} + +// Tool customization: Establish discriminated type base +union ResponseStreamEventType { + string, + response_audio_delta: "response.audio.delta", + response_audio_done: "response.audio.done", + response_audio_transcript_delta: "response.audio_transcript.delta", + response_audio_transcript_done: "response.audio_transcript.done", + response_code_interpreter_call_code_delta: "response.code_interpreter_call_code.delta", + response_code_interpreter_call_code_done: "response.code_interpreter_call_code.done", + response_code_interpreter_call_completed: "response.code_interpreter_call.completed", + response_code_interpreter_call_in_progress: "response.code_interpreter_call.in_progress", + response_code_interpreter_call_interpreting: "response.code_interpreter_call.interpreting", + response_completed: "response.completed", + response_content_part_added: "response.content_part.added", + response_content_part_done: "response.content_part.done", + response_created: "response.created", + error: "error", + response_file_search_call_completed: "response.file_search_call.completed", + response_file_search_call_in_progress: "response.file_search_call.in_progress", + response_file_search_call_searching: "response.file_search_call.searching", + response_function_call_arguments_delta: "response.function_call_arguments.delta", + response_function_call_arguments_done: "response.function_call_arguments.done", + response_in_progress: "response.in_progress", + response_failed: "response.failed", + response_incomplete: "response.incomplete", + response_output_item_added: "response.output_item.added", + response_output_item_done: "response.output_item.done", + response_refusal_delta: "response.refusal.delta", + response_refusal_done: "response.refusal.done", + response_output_text_annotation_added: "response.output_text.annotation.added", + response_output_text_delta: "response.output_text.delta", + response_output_text_done: "response.output_text.done", + response_reasoning_summary_part_added: "response.reasoning_summary_part.added", + response_reasoning_summary_part_done: "response.reasoning_summary_part.done", + response_reasoning_summary_text_delta: "response.reasoning_summary_text.delta", + response_reasoning_summary_text_done: "response.reasoning_summary_text.done", + response_web_search_call_completed: "response.web_search_call.completed", + response_web_search_call_in_progress: "response.web_search_call.in_progress", + response_web_search_call_searching: "response.web_search_call.searching", + response_image_generation_call_completed: "response.image_generation_call.completed", + response_image_generation_call_generating: "response.image_generation_call.generating", + response_image_generation_call_in_progress: "response.image_generation_call.in_progress", + response_image_generation_call_partial_image: "response.image_generation_call.partial_image", + response_mcp_call_arguments_delta: "response.mcp_call.arguments_delta", + response_mcp_call_arguments_done: "response.mcp_call.arguments_done", + response_mcp_call_completed: "response.mcp_call.completed", + response_mcp_call_failed: "response.mcp_call.failed", + response_mcp_call_in_progress: "response.mcp_call.in_progress", + response_mcp_list_tools_completed: "response.mcp_list_tools.completed", + response_mcp_list_tools_failed: "response.mcp_list_tools.failed", + response_mcp_list_tools_in_progress: "response.mcp_list_tools.in_progress", + response_queued: "response.queued", + response_reasoning_delta: "response.reasoning.delta", + response_reasoning_done: "response.reasoning.done", + response_reasoning_summary_delta: "response.reasoning_summary.delta", + response_reasoning_summary_done: "response.reasoning_summary.done", +} +@discriminator("type") +model ResponseStreamEvent { + type: ResponseStreamEventType; + + /** The sequence number for this event. */ + sequence_number: int32; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the model response is complete. */ +model ResponseCompletedEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.completed`. + """) + type: ResponseStreamEventType.response_completed; + + /** Properties of the completed response. */ + response: Response; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a new content part is added. */ +model ResponseContentPartAddedEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.content_part.added`. + """) + type: ResponseStreamEventType.response_content_part_added; + + /** The ID of the output item that the content part was added to. */ + item_id: string; + + /** The index of the output item that the content part was added to. */ + output_index: int32; + + /** The index of the content part that was added. */ + content_index: int32; + + /** The content part that was added. */ + part: OutputContent; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a content part is done. */ +model ResponseContentPartDoneEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.content_part.done`. + """) + type: ResponseStreamEventType.response_content_part_done; + + /** The ID of the output item that the content part was added to. */ + item_id: string; + + /** The index of the output item that the content part was added to. */ + output_index: int32; + + /** The index of the content part that is done. */ + content_index: int32; + + /** The content part that is done. */ + part: OutputContent; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** An event that is emitted when a response is created. */ +model ResponseCreatedEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.created`. + """) + type: ResponseStreamEventType.response_created; + + /** The response that was created. */ + response: Response; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when an error occurs. */ +model ResponseErrorEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `error`. + """) + type: ResponseStreamEventType.error; + + /** The error code. */ + code: string | null; + + /** The error message. */ + message: string; + + /** The error parameter. */ + param: string | null; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a file search call is completed (results found). */ +model ResponseFileSearchCallCompletedEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.file_search_call.completed`. + """) + type: ResponseStreamEventType.response_file_search_call_completed; + + /** The index of the output item that the file search call is initiated. */ + output_index: int32; + + /** The ID of the output item that the file search call is initiated. */ + item_id: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a file search call is initiated. */ +model ResponseFileSearchCallInProgressEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.file_search_call.in_progress`. + """) + type: ResponseStreamEventType.response_file_search_call_in_progress; + + /** The index of the output item that the file search call is initiated. */ + output_index: int32; + + /** The ID of the output item that the file search call is initiated. */ + item_id: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a file search is currently searching. */ +model ResponseFileSearchCallSearchingEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.file_search_call.searching`. + """) + type: ResponseStreamEventType.response_file_search_call_searching; + + /** The index of the output item that the file search call is searching. */ + output_index: int32; + + /** The ID of the output item that the file search call is initiated. */ + item_id: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when there is a partial function-call arguments delta. */ +model ResponseFunctionCallArgumentsDeltaEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.function_call_arguments.delta`. + """) + type: ResponseStreamEventType.response_function_call_arguments_delta; + + /** The ID of the output item that the function-call arguments delta is added to. */ + item_id: string; + + /** The index of the output item that the function-call arguments delta is added to. */ + output_index: int32; + + /** The function-call arguments delta that is added. */ + delta: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when function-call arguments are finalized. */ +model ResponseFunctionCallArgumentsDoneEvent extends ResponseStreamEvent { + type: ResponseStreamEventType.response_function_call_arguments_done; + + /** The ID of the item. */ + item_id: string; + + /** The index of the output item. */ + output_index: int32; + + /** The function-call arguments. */ + arguments: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the response is in progress. */ +model ResponseInProgressEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.in_progress`. + """) + type: ResponseStreamEventType.response_in_progress; + + /** The response that is in progress. */ + response: Response; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** An event that is emitted when a response fails. */ +model ResponseFailedEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.failed`. + """) + type: ResponseStreamEventType.response_failed; + + /** The response that failed. */ + response: Response; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** An event that is emitted when a response finishes as incomplete. */ +model ResponseIncompleteEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.incomplete`. + """) + type: ResponseStreamEventType.response_incomplete; + + /** The response that was incomplete. */ + response: Response; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a new output item is added. */ +model ResponseOutputItemAddedEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.output_item.added`. + """) + type: ResponseStreamEventType.response_output_item_added; + + /** The index of the output item that was added. */ + output_index: int32; + + /** The output item that was added. */ + item: OutputItem; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when an output item is marked done. */ +model ResponseOutputItemDoneEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.output_item.done`. + """) + type: ResponseStreamEventType.response_output_item_done; + + /** The index of the output item that was marked done. */ + output_index: int32; + + /** The output item that was marked done. */ + item: OutputItem; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when there is a partial refusal text. */ +model ResponseRefusalDeltaEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.refusal.delta`. + """) + type: ResponseStreamEventType.response_refusal_delta; + + /** The ID of the output item that the refusal text is added to. */ + item_id: string; + + /** The index of the output item that the refusal text is added to. */ + output_index: int32; + + /** The index of the content part that the refusal text is added to. */ + content_index: int32; + + /** The refusal text that is added. */ + delta: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when refusal text is finalized. */ +model ResponseRefusalDoneEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.refusal.done`. + """) + type: ResponseStreamEventType.response_refusal_done; + + /** The ID of the output item that the refusal text is finalized. */ + item_id: string; + + /** The index of the output item that the refusal text is finalized. */ + output_index: int32; + + /** The index of the content part that the refusal text is finalized. */ + content_index: int32; + + /** The refusal text that is finalized. */ + refusal: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when there is an additional text delta. */ +model ResponseTextDeltaEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.output_text.delta`. + """) + type: ResponseStreamEventType.response_output_text_delta; + + /** The ID of the output item that the text delta was added to. */ + item_id: string; + + /** The index of the output item that the text delta was added to. */ + output_index: int32; + + /** The index of the content part that the text delta was added to. */ + content_index: int32; + + /** The text delta that was added. */ + delta: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when text content is finalized. */ +model ResponseTextDoneEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.output_text.done`. + """) + type: ResponseStreamEventType.response_output_text_done; + + /** The ID of the output item that the text content is finalized. */ + item_id: string; + + /** The index of the output item that the text content is finalized. */ + output_index: int32; + + /** The index of the content part that the text content is finalized. */ + content_index: int32; + + /** The text content that is finalized. */ + text: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a new reasoning summary part is added. */ +model ResponseReasoningSummaryPartAddedEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.reasoning_summary_part.added`. + """) + type: ResponseStreamEventType.response_reasoning_summary_part_added; + + /** The ID of the item this summary part is associated with. */ + item_id: string; + + /** The index of the output item this summary part is associated with. */ + output_index: int32; + + /** The index of the summary part within the reasoning summary. */ + summary_index: int32; + + // Tool customization: Use customized discriminated type for summary parts + /** The summary part that was added. */ + part: ReasoningItemSummaryPart; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a reasoning summary part is completed. */ +model ResponseReasoningSummaryPartDoneEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.reasoning_summary_part.done`. + """) + type: ResponseStreamEventType.response_reasoning_summary_part_done; + + /** The ID of the item this summary part is associated with. */ + item_id: string; + + /** The index of the output item this summary part is associated with. */ + output_index: int32; + + /** The index of the summary part within the reasoning summary. */ + summary_index: int32; + + // Tool customization: Use customized discriminated type for summary parts + /** The completed summary part. */ + part: ReasoningItemSummaryPart; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a delta is added to a reasoning summary text. */ +model ResponseReasoningSummaryTextDeltaEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.reasoning_summary_text.delta`. + """) + type: ResponseStreamEventType.response_reasoning_summary_text_delta; + + /** The ID of the item this summary text delta is associated with. */ + item_id: string; + + /** The index of the output item this summary text delta is associated with. */ + output_index: int32; + + /** The index of the summary part within the reasoning summary. */ + summary_index: int32; + + /** The text delta that was added to the summary. */ + delta: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a reasoning summary text is completed. */ +model ResponseReasoningSummaryTextDoneEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.reasoning_summary_text.done`. + """) + type: ResponseStreamEventType.response_reasoning_summary_text_done; + + /** The ID of the item this summary text is associated with. */ + item_id: string; + + /** The index of the output item this summary text is associated with. */ + output_index: int32; + + /** The index of the summary part within the reasoning summary. */ + summary_index: int32; + + /** The full text of the completed reasoning summary. */ + text: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a web search call is completed. */ +model ResponseWebSearchCallCompletedEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.web_search_call.completed`. + """) + type: ResponseStreamEventType.response_web_search_call_completed; + + /** The index of the output item that the web search call is associated with. */ + output_index: int32; + + /** Unique ID for the output item associated with the web search call. */ + item_id: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a web search call is initiated. */ +model ResponseWebSearchCallInProgressEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.web_search_call.in_progress`. + """) + type: ResponseStreamEventType.response_web_search_call_in_progress; + + /** The index of the output item that the web search call is associated with. */ + output_index: int32; + + /** Unique ID for the output item associated with the web search call. */ + item_id: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a web search call is executing. */ +model ResponseWebSearchCallSearchingEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.web_search_call.searching`. + """) + type: ResponseStreamEventType.response_web_search_call_searching; + + /** The index of the output item that the web search call is associated with. */ + output_index: int32; + + /** Unique ID for the output item associated with the web search call. */ + item_id: string; +} + +// Tool customization: Establish a discriminated type base +/** Content item used to generate a response. */ +@discriminator("type") +model ItemResource { + type: ItemType; + id: string; +} + +// Tool customization: Stub/remove deeply customized type +alias InputItem = ItemParam; + +// Tool customization: Stub/remove deeply customized type +alias InputContent = ItemContent; + +// Tool customization: Stub/remove deeply customized type +alias OutputContent = ItemContent; + +// Tool customization: Stub/remove deeply customized type +alias OutputItem = ItemResource; + +// Tool customization: Stub/remove deeply customized type +alias OutputMessage = ResponsesMessageItemResource; + +// Tool customization: Stub/remove deeply customized type +alias InputMessage = ResponsesMessageItemResource; + +// Tool customization: Stub/remove deeply customized type +alias InputMessageResource = ResponsesMessageItemParam; + +// Tool customization: Stub/remove deeply customized type +alias EasyInputMessage = unknown; + +// Tool customization: Stub/remove deeply customized type +alias ComputerCallOutputItemParam = ItemParam; + +// Tool customization: Stub/remove deeply customized type +alias ComputerToolCallOutputResource = ComputerToolCallOutputItemResource; + +// Tool customization: Stub/remove deeply customized type +alias FunctionToolCallResource = FunctionToolCallItemResource; + +// Tool customization: Stub/remove deeply customized type +alias FunctionToolCallOutputResource = FunctionToolCallOutputItemResource; + +// Tool customization: Stub/remove deeply customized type +alias FunctionCallOutputItemParam = FunctionToolCallOutputItemParam; + +// Tool customization (apply_discriminator): Apply discriminated type base for tools +/** A tool that runs Python code to help generate a response to a prompt. */ +model CodeInterpreterTool extends Tool { + @doc(""" + The type of the code interpreter tool. Always `code_interpreter`. + """) + type: ToolType.code_interpreter; + + /** + * The code interpreter container. Can be a container ID or an object that + * specifies uploaded file IDs to make available to your code. + */ + container: string | CodeInterpreterToolAuto; +} + +/** + * Configuration for a code interpreter container. Optionally specify the IDs + * of the files to run the code on. + */ +model CodeInterpreterToolAuto { + @doc(""" + Always `auto`. + """) + type: "auto"; + + /** An optional list of uploaded files to make available to your code. */ + file_ids?: string[]; +} + +// Tool customization (apply_discriminator): Apply discriminated type base for tools +@doc(""" + A tool that generates images using a model like `gpt-image-1`. + """) +model ImageGenTool extends Tool { + @doc(""" + The type of the image generation tool. Always `image_generation`. + """) + type: ToolType.image_generation; + + @doc(""" + The image generation model to use. Default: `gpt-image-1`. + """) + `model`?: "gpt-image-1" = "gpt-image-1"; + + @doc(""" + The quality of the generated image. One of `low`, `medium`, `high`, + or `auto`. Default: `auto`. + """) + quality?: "low" | "medium" | "high" | "auto" = "auto"; + + @doc(""" + The size of the generated image. One of `1024x1024`, `1024x1536`, + `1536x1024`, or `auto`. Default: `auto`. + """) + size?: "1024x1024" | "1024x1536" | "1536x1024" | "auto" = "auto"; + + @doc(""" + The output format of the generated image. One of `png`, `webp`, or + `jpeg`. Default: `png`. + """) + output_format?: "png" | "webp" | "jpeg" = "png"; + + /** Compression level for the output image. Default: 100. */ + @minValue(0) + @maxValue(100) + output_compression?: int32 = 100; + + @doc(""" + Moderation level for the generated image. Default: `auto`. + """) + moderation?: "auto" | "low" = "auto"; + + @doc(""" + Background type for the generated image. One of `transparent`, + `opaque`, or `auto`. Default: `auto`. + """) + background?: "transparent" | "opaque" | "auto" = "auto"; + + @doc(""" + Optional mask for inpainting. Contains `image_url` + (string, optional) and `file_id` (string, optional). + """) + input_image_mask?: { + /** Base64-encoded mask image. */ + image_url?: string; + + /** File ID for the mask image. */ + file_id?: string; + }; + + /** Number of partial images to generate in streaming mode, from 0 (default value) to 3. */ + @minValue(0) + @maxValue(3) + partial_images?: int32 = 0; +} + +// Tool customization: Rename to supply base for split input/output models +/** An image generation request made by the model. */ +alias ImageGenToolCallItemBase = { + /** The generated image encoded in base64. */ + result: string | null; +}; + +@@doc(ImageGenToolCallItemResource, + """ + An image generation request made by the model. + + """ +); +@@doc(ImageGenToolCallItemParam, + """ + An image generation request made by the model. + + """ +); +/** Execute a shell command on the server. */ +model LocalShellExecAction { + @doc(""" + The type of the local shell action. Always `exec`. + """) + type: "exec"; + + /** The command to run. */ + command: string[]; + + /** Optional timeout in milliseconds for the command. */ + timeout_ms?: int32 | null; + + /** Optional working directory to run the command in. */ + working_directory?: string | null; + + /** Environment variables to set for the command. */ + env: Record; + + /** Optional user to run the command as. */ + user?: string | null; +} + +// Tool customization (apply_discriminator): Apply discriminated type base for tools +/** A tool that allows the model to execute shell commands in a local environment. */ +model LocalShellTool extends Tool { + @doc(""" + The type of the local shell tool. Always `local_shell`. + """) + type: ToolType.local_shell; +} + +// Tool customization: Rename to supply base for split input/output models +/** A tool call to run a command on the local shell. */ +alias LocalShellToolCallItemBase = { + /** The unique ID of the local shell tool call generated by the model. */ + call_id: string; + + action: LocalShellExecAction; +}; + +@@doc(LocalShellToolCallItemResource, + """ + A tool call to run a command on the local shell. + + """ +); +@@doc(LocalShellToolCallItemParam, + """ + A tool call to run a command on the local shell. + + """ +); +// Tool customization: Rename to supply base for split input/output models +/** The output of a local shell tool call. */ +alias LocalShellToolCallOutputItemBase = { + /** A JSON string of the output of the local shell tool call. */ + output: string; +}; + +@@doc(LocalShellToolCallOutputItemResource, + """ + The output of a local shell tool call. + + """ +); +@@doc(LocalShellToolCallOutputItemParam, + """ + The output of a local shell tool call. + + """ +); +// Tool customization: Rename to supply base for split input/output models +/** A request for human approval of a tool invocation. */ +alias MCPApprovalRequestItemBase = { + /** The label of the MCP server making the request. */ + server_label: string; + + /** The name of the tool to run. */ + name: string; + + /** A JSON string of arguments for the tool. */ + arguments: string; +}; + +@@doc(MCPApprovalRequestItemResource, + """ + A request for human approval of a tool invocation. + + """ +); +@@doc(MCPApprovalRequestItemParam, + """ + A request for human approval of a tool invocation. + + """ +); +// Tool customization: Rename to supply base for split input/output models +/** A response to an MCP approval request. */ +alias MCPApprovalResponseItemBase = { + /** The ID of the approval request being answered. */ + approval_request_id: string; + + /** Whether the request was approved. */ + approve: boolean; + + /** Optional reason for the decision. */ + reason?: string | null; +}; + +@@doc(MCPApprovalResponseItemResource, + """ + A response to an MCP approval request. + + """ +); +@@doc(MCPApprovalResponseItemParam, + """ + A response to an MCP approval request. + + """ +); +// Tool customization: Stub for already-split type +alias MCPApprovalResponseResource = MCPApprovalResponseItemResource; + +// Tool customization: Rename to supply base for split input/output models +/** A list of tools available on an MCP server. */ +alias MCPListToolsItemBase = { + /** The label of the MCP server. */ + server_label: string; + + /** The tools available on the server. */ + tools: MCPListToolsTool[]; + + /** Error message if the server could not list tools. */ + error?: string | null; +}; + +@@doc(MCPListToolsItemResource, + """ + A list of tools available on an MCP server. + + """ +); +@@doc(MCPListToolsItemParam, + """ + A list of tools available on an MCP server. + + """ +); +/** A tool available on an MCP server. */ +model MCPListToolsTool { + /** The name of the tool. */ + name: string; + + /** The description of the tool. */ + description?: string | null; + + /** The JSON schema describing the tool's input. */ + input_schema: unknown; + + /** Additional annotations about the tool. */ + annotations?: unknown | null; +} + +// Tool customization (apply_discriminator): Apply discriminated type base for tools +/** + * Give the model access to additional tools via remote Model Context Protocol + * (MCP) servers. [Learn more about MCP](/docs/guides/tools-remote-mcp). + */ +model MCPTool extends Tool { + @doc(""" + The type of the MCP tool. Always `mcp`. + """) + type: ToolType.mcp; + + /** A label for this MCP server, used to identify it in tool calls. */ + server_label: string; + + /** The URL for the MCP server. */ + server_url: string; + + /** + * Optional HTTP headers to send to the MCP server. Use for authentication + * or other purposes. + */ + headers?: Record | null; + + /** List of allowed tool names or a filter object. */ + allowed_tools?: string[] | { + /** List of allowed tool names. */ + tool_names?: string[]; + } | null; + + /** Specify which of the MCP server's tools require approval. */ + require_approval?: + | { + /** A list of tools that always require approval. */ + always?: { + /** List of tools that require approval. */ + tool_names?: string[]; + }; + + /** A list of tools that never require approval. */ + `never`?: { + /** List of tools that do not require approval. */ + tool_names?: string[]; + }; + } + | "always" + | "never" + | null = "always"; +} + +// Tool customization: Rename to supply base for split input/output models +/** An invocation of a tool on an MCP server. */ +alias MCPCallItemBase = { + /** The label of the MCP server running the tool. */ + server_label: string; + + /** The name of the tool that was run. */ + name: string; + + /** A JSON string of the arguments passed to the tool. */ + arguments: string; + + /** The output from the tool call. */ + output?: string | null; + + /** The error from the tool call, if any. */ + error?: string | null; +}; + +@@doc(MCPCallItemResource, + """ + An invocation of a tool on an MCP server. + + """ +); +@@doc(MCPCallItemParam, + """ + An invocation of a tool on an MCP server. + + """ +); +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when an image generation tool call has completed and the final image is available. */ +model ResponseImageGenCallCompletedEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.image_generation_call.completed'. */ + type: ResponseStreamEventType.response_image_generation_call_completed; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The unique identifier of the image generation item being processed. */ + item_id: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when an image generation tool call is actively generating an image (intermediate state). */ +model ResponseImageGenCallGeneratingEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.image_generation_call.generating'. */ + type: ResponseStreamEventType.response_image_generation_call_generating; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The unique identifier of the image generation item being processed. */ + item_id: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when an image generation tool call is in progress. */ +model ResponseImageGenCallInProgressEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.image_generation_call.in_progress'. */ + type: ResponseStreamEventType.response_image_generation_call_in_progress; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The unique identifier of the image generation item being processed. */ + item_id: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a partial image is available during image generation streaming. */ +model ResponseImageGenCallPartialImageEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.image_generation_call.partial_image'. */ + type: ResponseStreamEventType.response_image_generation_call_partial_image; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The unique identifier of the image generation item being processed. */ + item_id: string; + + /** 0-based index for the partial image (backend is 1-based, but this is 0-based for the user). */ + partial_image_index: int32; + + /** Base64-encoded partial image data, suitable for rendering as an image. */ + partial_image_b64: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when there is a delta (partial update) to the arguments of an MCP tool call. */ +model ResponseMCPCallArgumentsDeltaEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.mcp_call.arguments_delta'. */ + type: ResponseStreamEventType.response_mcp_call_arguments_delta; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The unique identifier of the MCP tool call item being processed. */ + item_id: string; + + /** The partial update to the arguments for the MCP tool call. */ + delta: unknown; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the arguments for an MCP tool call are finalized. */ +model ResponseMCPCallArgumentsDoneEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.mcp_call.arguments_done'. */ + type: ResponseStreamEventType.response_mcp_call_arguments_done; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The unique identifier of the MCP tool call item being processed. */ + item_id: string; + + /** The finalized arguments for the MCP tool call. */ + arguments: unknown; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when an MCP tool call has completed successfully. */ +model ResponseMCPCallCompletedEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.mcp_call.completed'. */ + type: ResponseStreamEventType.response_mcp_call_completed; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when an MCP tool call has failed. */ +model ResponseMCPCallFailedEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.mcp_call.failed'. */ + type: ResponseStreamEventType.response_mcp_call_failed; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when an MCP tool call is in progress. */ +model ResponseMCPCallInProgressEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.mcp_call.in_progress'. */ + type: ResponseStreamEventType.response_mcp_call_in_progress; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The unique identifier of the MCP tool call item being processed. */ + item_id: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the list of available MCP tools has been successfully retrieved. */ +model ResponseMCPListToolsCompletedEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.mcp_list_tools.completed'. */ + type: ResponseStreamEventType.response_mcp_list_tools_completed; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the attempt to list available MCP tools has failed. */ +model ResponseMCPListToolsFailedEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.mcp_list_tools.failed'. */ + type: ResponseStreamEventType.response_mcp_list_tools_failed; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the system is in the process of retrieving the list of available MCP tools. */ +model ResponseMCPListToolsInProgressEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.mcp_list_tools.in_progress'. */ + type: ResponseStreamEventType.response_mcp_list_tools_in_progress; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when an annotation is added to output text content. */ +model ResponseOutputTextAnnotationAddedEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.output_text_annotation.added'. */ + type: ResponseStreamEventType.response_output_text_annotation_added; + + /** The unique identifier of the item to which the annotation is being added. */ + item_id: string; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The index of the content part within the output item. */ + content_index: int32; + + /** The index of the annotation within the content part. */ + annotation_index: int32; + + /** The annotation object being added. (See annotation schema for details.) */ + annotation: unknown; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a response is queued and waiting to be processed. */ +model ResponseQueuedEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.queued'. */ + type: ResponseStreamEventType.response_queued; + + /** The full response object that is queued. */ + response: Response; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when there is a delta (partial update) to the reasoning content. */ +model ResponseReasoningDeltaEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.reasoning.delta'. */ + type: ResponseStreamEventType.response_reasoning_delta; + + /** The unique identifier of the item for which reasoning is being updated. */ + item_id: string; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The index of the reasoning content part within the output item. */ + content_index: int32; + + /** The partial update to the reasoning content. */ + delta: unknown; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the reasoning content is finalized for an item. */ +model ResponseReasoningDoneEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.reasoning.done'. */ + type: ResponseStreamEventType.response_reasoning_done; + + /** The unique identifier of the item for which reasoning is finalized. */ + item_id: string; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The index of the reasoning content part within the output item. */ + content_index: int32; + + /** The finalized reasoning text. */ + text: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when there is a delta (partial update) to the reasoning summary content. */ +model ResponseReasoningSummaryDeltaEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.reasoning_summary.delta'. */ + type: ResponseStreamEventType.response_reasoning_summary_delta; + + /** The unique identifier of the item for which the reasoning summary is being updated. */ + item_id: string; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The index of the summary part within the output item. */ + summary_index: int32; + + /** The partial update to the reasoning summary content. */ + delta: unknown; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the reasoning summary content is finalized for an item. */ +model ResponseReasoningSummaryDoneEvent extends ResponseStreamEvent { + /** The type of the event. Always 'response.reasoning_summary.done'. */ + type: ResponseStreamEventType.response_reasoning_summary_done; + + /** The unique identifier of the item for which the reasoning summary is finalized. */ + item_id: string; + + /** The index of the output item in the response's output array. */ + output_index: int32; + + /** The index of the summary part within the output item. */ + summary_index: int32; + + /** The finalized reasoning summary text. */ + text: string; +} + +/** The output of a code interpreter tool call that is a file. */ +model CodeInterpreterFileOutput { + @doc(""" + The type of the code interpreter file output. Always `files`. + """) + type: "files"; + + files: CodeInterpreterFileOutputFile[]; +} + +/** The output of a code interpreter tool call that is text. */ +model CodeInterpreterTextOutput { + @doc(""" + The type of the code interpreter text output. Always `logs`. + """) + type: "logs"; + + /** The logs of the code interpreter tool call. */ + logs: string; +} + +// Tool customization: Rename to supply base for split input/output models +/** A tool call to run code. */ +alias CodeInterpreterToolCallItemBase = { + /** The ID of the container used to run the code. */ + container_id?: string; + + /** The code to run. */ + code: string; + + /** The results of the code interpreter tool call. */ + results: CodeInterpreterToolOutput[]; +}; + +@@doc(CodeInterpreterToolCallItemResource, + """ + A tool call to run code. + + """ +); +@@doc(CodeInterpreterToolCallItemParam, + """ + A tool call to run code. + + """ +); +/** The output of a code interpreter tool. */ +union CodeInterpreterToolOutput { + CodeInterpreterTextOutput, + CodeInterpreterFileOutput, +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when there is a partial audio response. */ +model ResponseAudioDeltaEvent { + @doc(""" + The type of the event. Always `response.audio.delta`. + """) + type: "response.audio.delta"; + + /** A chunk of Base64 encoded response audio bytes. */ + delta: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the audio response is complete. */ +model ResponseAudioDoneEvent { + @doc(""" + The type of the event. Always `response.audio.done`. + """) + type: "response.audio.done"; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when there is a partial transcript of audio. */ +model ResponseAudioTranscriptDeltaEvent { + @doc(""" + The type of the event. Always `response.audio.transcript.delta`. + """) + type: "response.audio.transcript.delta"; + + /** The partial transcript of the audio response. */ + delta: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the full audio transcript is completed. */ +model ResponseAudioTranscriptDoneEvent { + @doc(""" + The type of the event. Always `response.audio.transcript.done`. + """) + type: "response.audio.transcript.done"; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a partial code snippet is added by the code interpreter. */ +model ResponseCodeInterpreterCallCodeDeltaEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.code_interpreter_call_code.delta`. + """) + type: ResponseStreamEventType.response_code_interpreter_call_code_delta; + + /** The index of the output item that the code interpreter call is in progress. */ + output_index: int32; + + /** The partial code snippet added by the code interpreter. */ + delta: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when code snippet output is finalized by the code interpreter. */ +model ResponseCodeInterpreterCallCodeDoneEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.code_interpreter_call_code.done`. + """) + type: ResponseStreamEventType.response_code_interpreter_call_code_done; + + /** The index of the output item that the code interpreter call is in progress. */ + output_index: int32; + + /** The final code snippet output by the code interpreter. */ + code: string; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the code interpreter call is completed. */ +model ResponseCodeInterpreterCallCompletedEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.code_interpreter_call.completed`. + """) + type: ResponseStreamEventType.response_code_interpreter_call_completed; + + /** The index of the output item that the code interpreter call is in progress. */ + output_index: int32; + + // Tool customization: Use split resource type + code_interpreter_call: CodeInterpreterToolCallItemResource; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when a code interpreter call is in progress. */ +model ResponseCodeInterpreterCallInProgressEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.code_interpreter_call.in_progress`. + """) + type: ResponseStreamEventType.response_code_interpreter_call_in_progress; + + /** The index of the output item that the code interpreter call is in progress. */ + output_index: int32; + + // Tool customization: Use split resource type + code_interpreter_call: CodeInterpreterToolCallItemResource; +} + +// Tool customization: Remove shared sequence_number property that was moved to the common parent +/** Emitted when the code interpreter is actively interpreting the code snippet. */ +model ResponseCodeInterpreterCallInterpretingEvent extends ResponseStreamEvent { + @doc(""" + The type of the event. Always `response.code_interpreter_call.interpreting`. + """) + type: ResponseStreamEventType.response_code_interpreter_call_interpreting; + + /** The index of the output item that the code interpreter call is in progress. */ + output_index: int32; + + // Tool customization: Use split resource type + code_interpreter_call: CodeInterpreterToolCallItemResource; +} + +/** The top log probability of a token. */ +model TopLogProb { + token: string; + logprob: float32; + bytes: int32[]; +} + +/** The log probability of a token. */ +model LogProb { + token: string; + logprob: float32; + bytes: int32[]; + top_logprobs: TopLogProb[]; +} diff --git a/specification/base/typespec/responses/operations.tsp b/specification/base/typespec/responses/operations.tsp new file mode 100644 index 000000000..f7fc0e3ae --- /dev/null +++ b/specification/base/typespec/responses/operations.tsp @@ -0,0 +1,92 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common/custom.tsp"; +import "./custom.tsp"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("responses") +@tag("Responses") +interface Responses { + /** + * Creates a model response. + */ + @operationId("createResponse") + @post + createResponse( + ...AcceptJsonOrEventStreamHeader, + @body requestBody: CreateResponse, + ): Response | SseResponseOf | ResponseErrorResponse; + + /** + * Retrieves a model response with the given ID. + * + * @param response_id The ID of the response to retrieve. + * @param include Specifies additional output data to include in the model response. + * @param stream If set to true, model response data will be streamed to the client as it is generated using server-sent events. + * @param starting_after The sequence number of the event after which to start streaming. + */ + @operationId("getResponse") + @get + @route("{response_id}") + getResponse( + @path + @example("resp_677efb5139a88190b512bc3fef8e535d") + response_id: string, + + @query(#{ name: "include[]", explode: true }) + includables?: Includable[] = #[], + + @query stream?: boolean = false, + @query starting_after?: int32, + ): Response | SseResponseOf | ResponseErrorResponse; + + @delete + @route("{response_id}") + @operationId("deleteResponse") + deleteResponse( + /** + * The ID of the response to delete. + */ + @path + @example("resp_677efb5139a88190b512bc3fef8e535d") + response_id: string, + ): { + id: string; + object: "response"; + deleted: true; + } | ResponseErrorResponse; + + @post + @route("{response_id}/cancel") + @operationId("cancelResponse") + cancelResponse( + /** + * The ID of the response to cancel. + */ + @path + @example("resp_677efb5139a88190b512bc3fef8e535d") + response_id: string, + ): Response | ResponseErrorResponse; + + /** + * Returns a list of input items for a given response. + * + * @param response_id The ID of the response to retrieve. + */ + @operationId("listInputItems") + @get + @route("{response_id}/input_items") + listInputItems( + @path + @example("resp_677efb5139a88190b512bc3fef8e535d") + response_id: string, + + ...CommonPageQueryParameters, + ): ResponseItemList | ResponseErrorResponse; +} diff --git a/specification/base/typespec/runs/custom.tsp b/specification/base/typespec/runs/custom.tsp new file mode 100644 index 000000000..85967c6c4 --- /dev/null +++ b/specification/base/typespec/runs/custom.tsp @@ -0,0 +1,92 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../assistants"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union RunStepDetailsType { + string, + message_creation: "message_creation", + tool_calls: "tool_calls", +} + +/** + * Abstractly represents a run step details object. + */ +@discriminator("type") +model RunStepObjectStepDetails { + /** The discriminated type identifier for the details object. */ + type: RunStepDetailsType; +} + +union RunStepDetailsToolCallType { + string, + code_interpreter: "code_interpreter", + file_search: "file_search", + function: "function", +} + +/** + * Abstractly represents a run step tool call details inner object. + */ +@discriminator("type") +model RunStepDetailsToolCallsObjectToolCallsObject { + /** The discriminated type identifier for the details object. */ + type: RunStepDetailsToolCallType; + + /** The ID of the tool call object. */ + id: string; +} + +union RunStepDetailsCodeInterpreterOutputType { + string, + logs: "logs", + image: "image", +} + +/** + * Abstractly represents a run step tool call details code interpreter output. + */ +@discriminator("type") +model RunStepDetailsToolCallsCodeObjectCodeInterpreterOutputsObject { + /** The discriminated type identifier for the details object. */ + type: RunStepDetailsCodeInterpreterOutputType; +} + +@discriminator("type") +model RunStepDeltaStepDetails { + /** The discriminated type identifier for the details object. */ + type: RunStepDetailsType; +} + +/** + * Abstractly represents a run step tool call details inner object. + */ +@discriminator("type") +model RunStepDeltaStepDetailsToolCallsObjectToolCallsObject { + /** The discriminated type identifier for the details object. */ + type: RunStepDetailsToolCallType; +} + +/** + * Abstractly represents a run step tool call details code interpreter output. + */ +@discriminator("type") +model RunStepDeltaStepDetailsToolCallsCodeObjectCodeInterpreterOutputsObject { + /** The discriminated type identifier for the details object. */ + type: RunStepDetailsCodeInterpreterOutputType; +} + +union IncludedRunStepProperty { + string, + file_search_result_content: "step_details.tool_calls[*].file_search.results[*].content", +} + +enum RunStepDetailsToolCallsFileSearchResultObjectContentType { + text, +} diff --git a/specification/base/typespec/runs/main.tsp b/specification/base/typespec/runs/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/runs/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/runs/models.tsp b/specification/base/typespec/runs/models.tsp new file mode 100644 index 000000000..cae3f8473 --- /dev/null +++ b/specification/base/typespec/runs/models.tsp @@ -0,0 +1,812 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../assistants"; +import "../common"; +import "../messages"; +import "../threads"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from SubmitToolOutputsRunRequest.tool_outputs +alias SubmitToolOutputsRunRequestToolOutput = { + @doc(""" + The ID of the tool call in the `required_action` object within the run object the output is being submitted for. + """) + tool_call_id?: string; + + /** The output of the tool call to be submitted to continue the run. */ + output?: string; +}; + +// Tool generated type. Extracts from RunStepDetailsToolCallsFileSearchResultObject.content +alias RunStepDetailsToolCallsFileSearchResultObjectContent = { + // Tool customization: Address source spec inaccuracy of optionality & use enum instead of string constants to maintain backwards compatibility + /** The type of the content. */ + type: RunStepDetailsToolCallsFileSearchResultObjectContentType.text; + + // Tool customization: address source spec inaccuracy of optionality + /** The text content of the file. */ + text: string; +}; + +model CreateRunRequest { + /** The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. */ + assistant_id: string; + + /** The ID of the [Model](/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. */ + @extension("x-oaiTypeLabel", "string") + `model`?: AssistantSupportedModels | null; + + reasoning_effort?: ReasoningEffort | null = "medium"; + + /** Overrides the [instructions](/docs/api-reference/assistants/createAssistant) of the assistant. This is useful for modifying the behavior on a per-run basis. */ + instructions?: string | null; + + /** Appends additional instructions at the end of the instructions for the run. This is useful for modifying the behavior on a per-run basis without overriding other instructions. */ + additional_instructions?: string | null; + + /** Adds additional messages to the thread before creating the run. */ + additional_messages?: CreateMessageRequest[] | null; + + // Tool customization: use common model base for tool definitions + /** Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. */ + // Tool note: can't automatically apply to nullable: @maxItems(20) + tools?: AssistantToolDefinition[] | null; + + ...MetadataPropertyForRequest; + + /** What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. */ + @minValue(0) + @maxValue(2) + temperature?: float32 | null = 1; + + /** + * An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + * + * We generally recommend altering this or temperature but not both. + */ + @minValue(0) + @maxValue(1) + top_p?: float32 | null = 1; + + @doc(""" + If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. + """) + stream?: boolean | null; + + @doc(""" + The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. + """) + @minValue(256) + max_prompt_tokens?: int32 | null; + + @doc(""" + The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. + """) + @minValue(256) + max_completion_tokens?: int32 | null; + + truncation_strategy?: TruncationObject | null; + tool_choice?: AssistantsApiToolChoiceOption | null; + parallel_tool_calls?: ParallelToolCalls = true; + response_format?: AssistantsApiResponseFormatOption | null; +} + +model ModifyRunRequest { + ...MetadataPropertyForRequest; +} + +model CreateThreadAndRunRequest { + /** The ID of the [assistant](/docs/api-reference/assistants) to use to execute this run. */ + assistant_id: string; + + thread?: CreateThreadRequest; + + /** The ID of the [Model](/docs/api-reference/models) to be used to execute this run. If a value is provided here, it will override the model associated with the assistant. If not, the model associated with the assistant will be used. */ + @extension("x-oaiTypeLabel", "string") + `model`?: + | string + | "gpt-4.1" + | "gpt-4.1-mini" + | "gpt-4.1-nano" + | "gpt-4.1-2025-04-14" + | "gpt-4.1-mini-2025-04-14" + | "gpt-4.1-nano-2025-04-14" + | "gpt-4o" + | "gpt-4o-2024-11-20" + | "gpt-4o-2024-08-06" + | "gpt-4o-2024-05-13" + | "gpt-4o-mini" + | "gpt-4o-mini-2024-07-18" + | "gpt-4.5-preview" + | "gpt-4.5-preview-2025-02-27" + | "gpt-4-turbo" + | "gpt-4-turbo-2024-04-09" + | "gpt-4-0125-preview" + | "gpt-4-turbo-preview" + | "gpt-4-1106-preview" + | "gpt-4-vision-preview" + | "gpt-4" + | "gpt-4-0314" + | "gpt-4-0613" + | "gpt-4-32k" + | "gpt-4-32k-0314" + | "gpt-4-32k-0613" + | "gpt-3.5-turbo" + | "gpt-3.5-turbo-16k" + | "gpt-3.5-turbo-0613" + | "gpt-3.5-turbo-1106" + | "gpt-3.5-turbo-0125" + | "gpt-3.5-turbo-16k-0613" + | null; + + /** Override the default system message of the assistant. This is useful for modifying the behavior on a per-run basis. */ + instructions?: string | null; + + // Tool customization: use common model base for tool definitions + /** Override the tools the assistant can use for this run. This is useful for modifying the behavior on a per-run basis. */ + // Tool note: can't automatically apply to nullable: @maxItems(20) + tools?: AssistantToolDefinition[] | null; + + @doc(""" + A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + """) + tool_resources?: { + code_interpreter?: { + @doc(""" + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + """) + @maxItems(20) + file_ids?: string[] = #[]; + }; + + // Tool customization: use custom type for sophisticated union + file_search?: ToolResourcesFileSearchIdsOnly; + } | null; + + ...MetadataPropertyForRequest; + + /** What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. */ + @minValue(0) + @maxValue(2) + temperature?: float32 | null = 1; + + /** + * An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. + * + * We generally recommend altering this or temperature but not both. + */ + @minValue(0) + @maxValue(1) + top_p?: float32 | null = 1; + + @doc(""" + If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. + """) + stream?: boolean | null; + + @doc(""" + The maximum number of prompt tokens that may be used over the course of the run. The run will make a best effort to use only the number of prompt tokens specified, across multiple turns of the run. If the run exceeds the number of prompt tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. + """) + @minValue(256) + max_prompt_tokens?: int32 | null; + + @doc(""" + The maximum number of completion tokens that may be used over the course of the run. The run will make a best effort to use only the number of completion tokens specified, across multiple turns of the run. If the run exceeds the number of completion tokens specified, the run will end with status `incomplete`. See `incomplete_details` for more info. + """) + @minValue(256) + max_completion_tokens?: int32 | null; + + truncation_strategy?: TruncationObject | null; + tool_choice?: AssistantsApiToolChoiceOption | null; + parallel_tool_calls?: ParallelToolCalls = true; + response_format?: AssistantsApiResponseFormatOption | null; +} + +model SubmitToolOutputsRunRequest { + /** A list of tools for which the outputs are being submitted. */ + tool_outputs: SubmitToolOutputsRunRequestToolOutput[]; + + @doc(""" + If `true`, returns a stream of events that happen during the Run as server-sent events, terminating when the Run enters a terminal state with a `data: [DONE]` message. + """) + stream?: boolean | null; +} + +model ListRunsResponse { + // Tool customization: add a clear enum enforcement of constrained 'object' label + object: "list"; + + data: RunObject[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model ListRunStepsResponse { + // Tool customization: add a clear enum enforcement of constrained 'object' label + object: "list"; + + data: RunStepObject[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** Details of the message creation by the run step. */ +model RunStepDetailsMessageCreationObject extends RunStepObjectStepDetails { + @doc(""" + Always `message_creation`. + """) + type: RunStepDetailsType.message_creation; + + message_creation: { + /** The ID of the message that was created by this run step. */ + message_id: string; + }; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** Details of the tool call. */ +model RunStepDetailsToolCallsObject extends RunStepObjectStepDetails { + @doc(""" + Always `tool_calls`. + """) + type: RunStepDetailsType.tool_calls; + + // Tool customization: replace unioned types with a custom, common base + @doc(""" + An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `file_search`, or `function`. + """) + tool_calls: RunStepDetailsToolCallsObjectToolCallsObject[]; +} + +// Tool customization: Remove parent-relocated 'id' from discriminated type instance +/** Details of the Code Interpreter tool call the run step was involved in. */ +model RunStepDetailsToolCallsCodeObject + extends RunStepDetailsToolCallsObjectToolCallsObject { + @doc(""" + The type of tool call. This is always going to be `code_interpreter` for this type of tool call. + """) + type: RunStepDetailsToolCallType.code_interpreter; + + /** The Code Interpreter tool call definition. */ + code_interpreter: { + /** The input to the Code Interpreter tool call. */ + input: string; + + // Tool customization: Apply read-only visibility via annotation + @doc(""" + The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type. + """) + @visibility(Lifecycle.Read) + outputs: RunStepDetailsToolCallsCodeObjectCodeInterpreterOutputsObject[]; + }; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** Text output from the Code Interpreter tool call as part of a run step. */ +model RunStepDetailsToolCallsCodeOutputLogsObject + extends RunStepDetailsToolCallsCodeObjectCodeInterpreterOutputsObject { + @doc(""" + Always `logs`. + """) + type: RunStepDetailsCodeInterpreterOutputType.logs; + + /** The text output from the Code Interpreter tool call. */ + logs: string; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +model RunStepDetailsToolCallsCodeOutputImageObject + extends RunStepDetailsToolCallsCodeObjectCodeInterpreterOutputsObject { + @doc(""" + Always `image`. + """) + type: RunStepDetailsCodeInterpreterOutputType.image; + + image: { + /** The [file](/docs/api-reference/files) ID of the image. */ + file_id: string; + }; +} + +// Tool customization: Remove parent-relocated 'id' from discriminated type instance +model RunStepDetailsToolCallsFileSearchObject + extends RunStepDetailsToolCallsObjectToolCallsObject { + @doc(""" + The type of tool call. This is always going to be `file_search` for this type of tool call. + """) + type: RunStepDetailsToolCallType.file_search; + + /** For now, this is always going to be an empty object. */ + @extension("x-oaiTypeLabel", "map") + file_search: { + ranking_options?: RunStepDetailsToolCallsFileSearchRankingOptionsObject; + + // Tool customization: Apply read-only visibility via annotation + /** The results of the file search. */ + @visibility(Lifecycle.Read) + results?: RunStepDetailsToolCallsFileSearchResultObject[]; + }; +} + +/** The ranking options for the file search. */ +model RunStepDetailsToolCallsFileSearchRankingOptionsObject { + ranker: FileSearchRanker; + + /** The score threshold for the file search. All values must be a floating point number between 0 and 1. */ + @minValue(0) + @maxValue(1) + score_threshold: float32; +} + +/** A result instance of the file search. */ +@extension("x-oaiTypeLabel", "map") +model RunStepDetailsToolCallsFileSearchResultObject { + /** The ID of the file that result was found in. */ + file_id: string; + + /** The name of the file that result was found in. */ + file_name: string; + + /** The score of the result. All values must be a floating point number between 0 and 1. */ + @minValue(0) + @maxValue(1) + score: float32; + + /** The content of the result that was found. The content is only included if requested via the include query parameter. */ + content?: RunStepDetailsToolCallsFileSearchResultObjectContent[]; +} + +// Tool customization: Remove parent-relocated 'id' from discriminated type instance +model RunStepDetailsToolCallsFunctionObject + extends RunStepDetailsToolCallsObjectToolCallsObject { + @doc(""" + The type of tool call. This is always going to be `function` for this type of tool call. + """) + type: RunStepDetailsToolCallType.function; + + /** The definition of the function that was called. */ + function: { + /** The name of the function. */ + name: string; + + /** The arguments passed to the function. */ + arguments: string; + + @doc(""" + The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. + """) + output: string | null; + }; +} + +@doc(""" + Usage statistics related to the run. This value will be `null` if the run is not in a terminal state (i.e. `in_progress`, `queued`, etc.). + """) +model RunCompletionUsage { + /** Number of completion tokens used over the course of the run. */ + completion_tokens: int32; + + /** Number of prompt tokens used over the course of the run. */ + prompt_tokens: int32; + + /** Total number of tokens used (prompt + completion). */ + total_tokens: int32; +} + +@doc(""" + Usage statistics related to the run step. This value will be `null` while the run step's status is `in_progress`. + """) +model RunStepCompletionUsage { + /** Number of completion tokens used over the course of the run step. */ + completion_tokens: int32; + + /** Number of prompt tokens used over the course of the run step. */ + prompt_tokens: int32; + + /** Total number of tokens used (prompt + completion). */ + total_tokens: int32; +} + +/** Represents an execution run on a [thread](/docs/api-reference/threads). */ +model RunObject { + /** The identifier, which can be referenced in API endpoints. */ + id: string; + + @doc(""" + The object type, which is always `thread.run`. + """) + object: "thread.run"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The ID of the [thread](/docs/api-reference/threads) that was executed on as a part of this run. */ + thread_id: string; + + /** The ID of the [assistant](/docs/api-reference/assistants) used for execution of this run. */ + assistant_id: string; + + @doc(""" + The status of the run, which can be either `queued`, `in_progress`, `requires_action`, `cancelling`, `cancelled`, `failed`, `completed`, `incomplete`, or `expired`. + """) + status: + | "queued" + | "in_progress" + | "requires_action" + | "cancelling" + | "cancelled" + | "failed" + | "completed" + | "incomplete" + | "expired"; + + @doc(""" + Details on the action required to continue the run. Will be `null` if no action is required. + """) + required_action: { + @doc(""" + For now, this is always `submit_tool_outputs`. + """) + type: "submit_tool_outputs"; + + /** Details on the tool outputs needed for this run to continue. */ + submit_tool_outputs: { + // Tool customization: Apply read-only visibility via annotation + /** A list of the relevant tool calls. */ + @visibility(Lifecycle.Read) + tool_calls: RunToolCallObject[]; + }; + } | null; + + @doc(""" + The last error associated with this run. Will be `null` if there are no errors. + """) + last_error: { + @doc(""" + One of `server_error`, `rate_limit_exceeded`, or `invalid_prompt`. + """) + code: "server_error" | "rate_limit_exceeded" | "invalid_prompt"; + + /** A human-readable description of the error. */ + message: string; + } | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run will expire. */ + @encode("unixTimestamp", int32) + expires_at: utcDateTime | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run was started. */ + @encode("unixTimestamp", int32) + started_at: utcDateTime | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run was cancelled. */ + @encode("unixTimestamp", int32) + cancelled_at: utcDateTime | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run failed. */ + @encode("unixTimestamp", int32) + failed_at: utcDateTime | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run was completed. */ + @encode("unixTimestamp", int32) + completed_at: utcDateTime | null; + + @doc(""" + Details on why the run is incomplete. Will be `null` if the run is not incomplete. + """) + incomplete_details: { + /** The reason why the run is incomplete. This will point to which specific token limit was reached over the course of the run. */ + reason?: "max_completion_tokens" | "max_prompt_tokens"; + } | null; + + /** The model that the [assistant](/docs/api-reference/assistants) used for this run. */ + `model`: string; + + /** The instructions that the [assistant](/docs/api-reference/assistants) used for this run. */ + instructions: string; + + // Tool customization: use common model base for tool definitions + /** The list of tools that the [assistant](/docs/api-reference/assistants) used for this run. */ + @maxItems(20) + tools: AssistantToolDefinition[] = #[]; + + ...MetadataPropertyForResponse; + usage: RunCompletionUsage | null; + + /** The sampling temperature used for this run. If not set, defaults to 1. */ + temperature?: float32 | null; + + /** The nucleus sampling value used for this run. If not set, defaults to 1. */ + top_p?: float32 | null; + + /** The maximum number of prompt tokens specified to have been used over the course of the run. */ + @minValue(256) + max_prompt_tokens: int32 | null; + + /** The maximum number of completion tokens specified to have been used over the course of the run. */ + @minValue(256) + max_completion_tokens: int32 | null; + + truncation_strategy: TruncationObject | null; + tool_choice: AssistantsApiToolChoiceOption | null; + parallel_tool_calls: ParallelToolCalls = true; + response_format: AssistantsApiResponseFormatOption | null; +} + +/** Represents a step in execution of a run. */ +model RunStepObject { + /** The identifier of the run step, which can be referenced in API endpoints. */ + id: string; + + @doc(""" + The object type, which is always `thread.run.step`. + """) + object: "thread.run.step"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run step was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The ID of the [assistant](/docs/api-reference/assistants) associated with the run step. */ + assistant_id: string; + + /** The ID of the [thread](/docs/api-reference/threads) that was run. */ + thread_id: string; + + /** The ID of the [run](/docs/api-reference/runs) that this run step is a part of. */ + run_id: string; + + @doc(""" + The type of run step, which can be either `message_creation` or `tool_calls`. + """) + type: "message_creation" | "tool_calls"; + + @doc(""" + The status of the run step, which can be either `in_progress`, `cancelled`, `failed`, `completed`, or `expired`. + """) + status: "in_progress" | "cancelled" | "failed" | "completed" | "expired"; + + // Tool customization: replace unioned types with a custom, common base + /** The details of the run step. */ + step_details: RunStepObjectStepDetails; + + @doc(""" + The last error associated with this run step. Will be `null` if there are no errors. + """) + last_error: { + @doc(""" + One of `server_error` or `rate_limit_exceeded`. + """) + code: "server_error" | "rate_limit_exceeded"; + + /** A human-readable description of the error. */ + message: string; + } | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run step expired. A step is considered expired if the parent run is expired. */ + @encode("unixTimestamp", int32) + expired_at: utcDateTime | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run step was cancelled. */ + @encode("unixTimestamp", int32) + cancelled_at: utcDateTime | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run step failed. */ + @encode("unixTimestamp", int32) + failed_at: utcDateTime | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the run step completed. */ + @encode("unixTimestamp", int32) + completed_at: utcDateTime | null; + + ...MetadataPropertyForResponse; + usage: RunStepCompletionUsage | null; +} + +/** Tool call objects */ +model RunToolCallObject { + /** The ID of the tool call. This ID must be referenced when you submit the tool outputs in using the [Submit tool outputs to run](/docs/api-reference/runs/submitToolOutputs) endpoint. */ + id: string; + + @doc(""" + The type of tool call the output is required for. For now, this is always `function`. + """) + type: "function"; + + /** The function definition. */ + function: { + /** The name of the function. */ + name: string; + + /** The arguments that the model expects you to pass to the function. */ + arguments: string; + }; +} + +/** Represents a run step delta i.e. any changed fields on a run step during streaming. */ +model RunStepDeltaObject { + /** The identifier of the run step, which can be referenced in API endpoints. */ + id: string; + + @doc(""" + The object type, which is always `thread.run.step.delta`. + """) + object: "thread.run.step.delta"; + + /** The delta containing the fields that have changed on the run step. */ + delta: { + // Tool customization: replace unioned types with a custom, common base + /** The details of the run step. */ + step_details?: RunStepDeltaStepDetails; + }; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** Details of the message creation by the run step. */ +model RunStepDeltaStepDetailsMessageCreationObject + extends RunStepDeltaStepDetails { + @doc(""" + Always `message_creation`. + """) + type: "message_creation"; + + message_creation?: { + /** The ID of the message that was created by this run step. */ + message_id?: string; + }; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** Details of the tool call. */ +model RunStepDeltaStepDetailsToolCallsObject extends RunStepDeltaStepDetails { + @doc(""" + Always `tool_calls`. + """) + type: "tool_calls"; + + // Tool customization: replace unioned types with a custom, common base + @doc(""" + An array of tool calls the run step was involved in. These can be associated with one of three types of tools: `code_interpreter`, `file_search`, or `function`. + """) + tool_calls?: RunStepDeltaStepDetailsToolCallsObjectToolCallsObject[]; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** Details of the Code Interpreter tool call the run step was involved in. */ +model RunStepDeltaStepDetailsToolCallsCodeObject + extends RunStepDeltaStepDetailsToolCallsObjectToolCallsObject { + /** The index of the tool call in the tool calls array. */ + index: int32; + + /** The ID of the tool call. */ + id?: string; + + @doc(""" + The type of tool call. This is always going to be `code_interpreter` for this type of tool call. + """) + type: RunStepDetailsToolCallType.code_interpreter; + + /** The Code Interpreter tool call definition. */ + code_interpreter?: { + /** The input to the Code Interpreter tool call. */ + input?: string; + + // Tool customization: Apply read-only visibility via annotation + @doc(""" + The outputs from the Code Interpreter tool call. Code Interpreter can output one or more items, including text (`logs`) or images (`image`). Each of these are represented by a different object type. + """) + @visibility(Lifecycle.Read) + outputs?: RunStepDeltaStepDetailsToolCallsCodeObjectCodeInterpreterOutputsObject[]; + }; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +/** Text output from the Code Interpreter tool call as part of a run step. */ +model RunStepDeltaStepDetailsToolCallsCodeOutputLogsObject + extends RunStepDeltaStepDetailsToolCallsCodeObjectCodeInterpreterOutputsObject { + /** The index of the output in the outputs array. */ + index: int32; + + @doc(""" + Always `logs`. + """) + type: RunStepDetailsCodeInterpreterOutputType.logs; + + /** The text output from the Code Interpreter tool call. */ + logs?: string; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +model RunStepDeltaStepDetailsToolCallsCodeOutputImageObject + extends RunStepDeltaStepDetailsToolCallsCodeObjectCodeInterpreterOutputsObject { + /** The index of the output in the outputs array. */ + index: int32; + + @doc(""" + Always `image`. + """) + type: RunStepDetailsCodeInterpreterOutputType.image; + + image?: { + /** The [file](/docs/api-reference/files) ID of the image. */ + file_id?: string; + }; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +model RunStepDeltaStepDetailsToolCallsFileSearchObject + extends RunStepDeltaStepDetailsToolCallsObjectToolCallsObject { + /** The index of the tool call in the tool calls array. */ + index: int32; + + /** The ID of the tool call object. */ + id?: string; + + @doc(""" + The type of tool call. This is always going to be `file_search` for this type of tool call. + """) + type: RunStepDetailsToolCallType.file_search; + + // Tool customization: add missing and shared file_search definition for streaming + /** For now, this is always going to be an empty object. */ + @extension("x-oaiTypeLabel", "map") + file_search: { + ranking_options?: RunStepDetailsToolCallsFileSearchRankingOptionsObject; + + /** The results of the file search. */ + @visibility(Lifecycle.Read) + results?: RunStepDetailsToolCallsFileSearchResultObject[]; + }; +} + +// Tool customization (apply_discriminator): apply custom, common base type to union items +model RunStepDeltaStepDetailsToolCallsFunctionObject + extends RunStepDeltaStepDetailsToolCallsObjectToolCallsObject { + /** The index of the tool call in the tool calls array. */ + index: int32; + + /** The ID of the tool call object. */ + id?: string; + + @doc(""" + The type of tool call. This is always going to be `function` for this type of tool call. + """) + type: RunStepDetailsToolCallType.function; + + /** The definition of the function that was called. */ + function?: { + /** The name of the function. */ + name?: string; + + /** The arguments passed to the function. */ + arguments?: string; + + @doc(""" + The output of the function. This will be `null` if the outputs have not been [submitted](/docs/api-reference/runs/submitToolOutputs) yet. + """) + output?: string | null; + }; +} diff --git a/specification/base/typespec/runs/operations.tsp b/specification/base/typespec/runs/operations.tsp new file mode 100644 index 000000000..b29381379 --- /dev/null +++ b/specification/base/typespec/runs/operations.tsp @@ -0,0 +1,180 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/threads") +interface Runs { + @route("runs") + @post + @operationId("createThreadAndRun") + @tag("Assistants") + @summary("Create a thread and run it in one request.") + createThreadAndRun( + ...AcceptJsonOrEventStreamHeader, + ...AssistantsBetaHeader, + @body requestBody: CreateThreadAndRunRequest, + ): RunObject | ErrorResponse; + + @route("{thread_id}/runs") + @post + @operationId("createRun") + @tag("Assistants") + @summary("Create a run.") + createRun( + ...AcceptJsonOrEventStreamHeader, + ...AssistantsBetaHeader, + + /** The ID of the thread to run. */ + @path thread_id: string, + + ...IncludedRunStepPropertyParameter, + @body requestBody: CreateRunRequest, + ): RunObject | ErrorResponse; + + @route("{thread_id}/runs") + @get + @operationId("listRuns") + @tag("Assistants") + @summary("Returns a list of runs belonging to a thread.") + listRuns( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the thread the run belongs to. */ + @path thread_id: string, + + ...CommonPageQueryParameters, + ): ListRunsResponse | ErrorResponse; + + @route("{thread_id}/runs/{run_id}") + @get + @operationId("getRun") + @tag("Assistants") + @summary("Retrieves a run.") + getRun( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the [thread](/docs/api-reference/threads) that was run. */ + @path thread_id: string, + + /** The ID of the run to retrieve. */ + @path run_id: string, + ): RunObject | ErrorResponse; + + @route("{thread_id}/runs/{run_id}") + @post + @operationId("modifyRun") + @tag("Assistants") + @summary("Modifies a run.") + modifyRun( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the [thread](/docs/api-reference/threads) that was run. */ + @path thread_id: string, + + /** The ID of the run to modify. */ + @path run_id: string, + + @body requestBody: ModifyRunRequest, + ): RunObject | ErrorResponse; + + @route("{thread_id}/runs/{run_id}/cancel") + @post + @operationId("cancelRun") + @tag("Assistants") + @summary("Cancels a run that is `in_progress`.") + cancelRun( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the thread to which this run belongs. */ + @path thread_id: string, + + /** The ID of the run to cancel. */ + @path run_id: string, + ): RunObject | ErrorResponse; + + @route("{thread_id}/runs/{run_id}/submit_tool_outputs") + @post + @operationId("submitToolOutputsToRun") + @tag("Assistants") + @summary(""" + When a run has the `status: "requires_action"` and `required_action.type` is + `submit_tool_outputs`, this endpoint can be used to submit the outputs from the tool calls once + they're all completed. All outputs must be submitted in a single request. + """) + submitToolOutputsToRun( + ...AcceptJsonOrEventStreamHeader, + ...AssistantsBetaHeader, + + /** The ID of the [thread](/docs/api-reference/threads) to which this run belongs. */ + @path thread_id: string, + + /** The ID of the run that requires the tool output submission. */ + @path run_id: string, + + @body requestBody: SubmitToolOutputsRunRequest, + ): RunObject | ErrorResponse; + + @route("{thread_id}/runs/{run_id}/steps") + @get + @operationId("listRunSteps") + @tag("Assistants") + @summary("Returns a list of run steps belonging to a run.") + listRunSteps( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the thread the run and run steps belong to. */ + @path thread_id: string, + + /** The ID of the run the run steps belong to. */ + @path run_id: string, + + ...CommonPageQueryParameters, + ...IncludedRunStepPropertyParameter, + ): ListRunStepsResponse | ErrorResponse; + + @route("{thread_id}/runs/{run_id}/steps/{step_id}") + @get + @operationId("getRunStep") + @tag("Assistants") + @summary("Retrieves a run step.") + getRunStep( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the thread to which the run and run step belongs. */ + @path thread_id: string, + + /** The ID of the run to which the run step belongs. */ + @path run_id: string, + + /** The ID of the run step to retrieve. */ + @path step_id: string, + + ...IncludedRunStepPropertyParameter, + ): RunStepObject | ErrorResponse; +} + +alias IncludedRunStepPropertyParameter = { + /** + * A list of additional fields to include in the response. Currently the only supported value is + * `step_details.tool_calls[*].file_search.results[*].content` to fetch the file search result + * content. + * + * See the + * [file search tool documentation](/docs/assistants/tools/file-search/customizing-file-search-settings) + * for more information. + */ + @query `include[]`?: IncludedRunStepProperty[]; +}; diff --git a/specification/base/typespec/servers/rest.tsp b/specification/base/typespec/servers/rest.tsp new file mode 100644 index 000000000..faafb6df9 --- /dev/null +++ b/specification/base/typespec/servers/rest.tsp @@ -0,0 +1,18 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +using TypeSpec.Http; + +/** The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details. */ +@OpenAPI.info(#{ + termsOfService: "https://openai.com/policies/terms-of-use", + contact: #{ name: "OpenAI Support", url: "https://help.openai.com" }, + license: #{ + name: "MIT", + url: "https://github.com/openai/openai-openapi/blob/master/LICENSE", + }, +}) +@service(#{ title: "OpenAI API" }) +@server("https://api.openai.com/v1", "OpenAI Endpoint") +@useAuth(BearerAuth) +namespace OpenAI; diff --git a/specification/base/typespec/servers/websocket.tsp b/specification/base/typespec/servers/websocket.tsp new file mode 100644 index 000000000..cf5abc61a --- /dev/null +++ b/specification/base/typespec/servers/websocket.tsp @@ -0,0 +1,19 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +using TypeSpec.Http; + +/** The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details. */ +@OpenAPI.info(#{ + termsOfService: "https://openai.com/policies/terms-of-use", + contact: #{ name: "OpenAI Support", url: "https://help.openai.com" }, + license: #{ + name: "MIT", + url: "https://github.com/openai/openai-openapi/blob/master/LICENSE", + }, +}) + +@service(#{ title: "OpenAI API" }) +@server("wss://api.openai.com/v1", "OpenAI Endpoint") +@useAuth(BearerAuth) +namespace OpenAI; diff --git a/specification/base/typespec/specialized-types/custom.tsp b/specification/base/typespec/specialized-types/custom.tsp new file mode 100644 index 000000000..1589d157f --- /dev/null +++ b/specification/base/typespec/specialized-types/custom.tsp @@ -0,0 +1,3 @@ +import "@typespec/http"; + +namespace OpenAI; diff --git a/specification/base/typespec/specialized-types/main.tsp b/specification/base/typespec/specialized-types/main.tsp new file mode 100644 index 000000000..5ad1d3a2b --- /dev/null +++ b/specification/base/typespec/specialized-types/main.tsp @@ -0,0 +1 @@ +import "./models.tsp"; diff --git a/specification/base/typespec/specialized-types/models.tsp b/specification/base/typespec/specialized-types/models.tsp new file mode 100644 index 000000000..d3bae4a78 --- /dev/null +++ b/specification/base/typespec/specialized-types/models.tsp @@ -0,0 +1,57 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +/** A filter used to compare a specified attribute key to a given value using a defined comparison operation. */ +model ComparisonFilter { + @doc(""" + Specifies the comparison operator: `eq`, `ne`, `gt`, `gte`, `lt`, `lte`. + - `eq`: equals + - `ne`: not equal + - `gt`: greater than + - `gte`: greater than or equal + - `lt`: less than + - `lte`: less than or equal + """) + type: "eq" | "ne" | "gt" | "gte" | "lt" | "lte" = "eq"; + + /** The key to compare against the value. */ + key: string; + + /** The value to compare against the attribute key; supports string, number, or boolean types. */ + value: string | float32 | boolean; +} + +@doc(""" + Combine multiple filters using `and` or `or`. + """) +model CompoundFilter { + @doc(""" + Type of operation: `and` or `or`. + """) + type: "and" | "or"; + + @doc(""" + Array of filters to combine. Items can be `ComparisonFilter` or `CompoundFilter`. + """) + filters: (ComparisonFilter | CompoundFilter)[]; +} + +// Tool customization: Replace with more detailed representation +/** + * Set of 16 key-value pairs that can be attached to an object. This can be + * useful for storing additional information about the object in a structured + * format, and querying for objects via API or the dashboard. Keys are strings + * with a maximum length of 64 characters. Values are strings with a maximum + * length of 512 characters, booleans, or numbers. + */ +@extension("x-oaiTypeLabel", "map") +model VectorStoreFileAttributes is Record; diff --git a/specification/base/typespec/streaming/models.tsp b/specification/base/typespec/streaming/models.tsp new file mode 100644 index 000000000..9af9b78a6 --- /dev/null +++ b/specification/base/typespec/streaming/models.tsp @@ -0,0 +1,163 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../common"; +import "../messages"; +import "../runs"; +import "../threads"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@doc(""" + Represents an event emitted when streaming a Run. + + Each event in a server-sent events stream has an `event` and `data` property: + + ``` + event: thread.created + data: {"id": "thread_123", "object": "thread", ...} + ``` + + We emit events whenever a new object is created, transitions to a new state, or is being + streamed in parts (deltas). For example, we emit `thread.run.created` when a new run + is created, `thread.run.completed` when a run completes, and so on. When an Assistant chooses + to create a message during a run, we emit a `thread.message.created event`, a + `thread.message.in_progress` event, many `thread.message.delta` events, and finally a + `thread.message.completed` event. + + We may add additional events over time, so we recommend handling unknown events gracefully + in your code. See the [Assistants API quickstart](/docs/assistants/overview) to learn how to + integrate the Assistants API with streaming. + """) +union AssistantStreamEvent { + ThreadStreamEvent, + RunStreamEvent, + RunStepStreamEvent, + MessageStreamEvent, + ErrorEvent, + DoneEvent, +} + +union ThreadStreamEvent { + { + /** Whether to enable input audio transcription. */ + enabled?: boolean, + + event: "thread.created", + data: ThreadObject, + }, +} + +union RunStreamEvent { + { + event: "thread.run.created", + data: RunObject, + }, + { + event: "thread.run.queued", + data: RunObject, + }, + { + event: "thread.run.in_progress", + data: RunObject, + }, + { + event: "thread.run.requires_action", + data: RunObject, + }, + { + event: "thread.run.completed", + data: RunObject, + }, + { + event: "thread.run.incomplete", + data: RunObject, + }, + { + event: "thread.run.failed", + data: RunObject, + }, + { + event: "thread.run.cancelling", + data: RunObject, + }, + { + event: "thread.run.cancelled", + data: RunObject, + }, + { + event: "thread.run.expired", + data: RunObject, + }, +} + +union RunStepStreamEvent { + { + event: "thread.run.step.created", + data: RunStepObject, + }, + { + event: "thread.run.step.in_progress", + data: RunStepObject, + }, + { + event: "thread.run.step.delta", + data: RunStepDeltaObject, + }, + { + event: "thread.run.step.completed", + data: RunStepObject, + }, + { + event: "thread.run.step.failed", + data: RunStepObject, + }, + { + event: "thread.run.step.cancelled", + data: RunStepObject, + }, + { + event: "thread.run.step.expired", + data: RunStepObject, + }, +} + +union MessageStreamEvent { + { + event: "thread.message.created", + data: MessageObject, + }, + { + event: "thread.message.in_progress", + data: MessageObject, + }, + { + event: "thread.message.delta", + data: MessageDeltaObject, + }, + { + event: "thread.message.completed", + data: MessageObject, + }, + { + event: "thread.message.incomplete", + data: MessageObject, + }, +} + +/** Occurs when an [error](/docs/guides/error-codes#api-errors) occurs. This can happen due to an internal server error or a timeout. */ +model ErrorEvent { + event: "error"; + data: Error; +} + +/** Occurs when a stream ends. */ +model DoneEvent { + event: "done"; + data: "[DONE]"; +} diff --git a/specification/base/typespec/threads/custom.tsp b/specification/base/typespec/threads/custom.tsp new file mode 100644 index 000000000..1862f827e --- /dev/null +++ b/specification/base/typespec/threads/custom.tsp @@ -0,0 +1,46 @@ +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// This customization allows us to concretely specify that the file_search object must provide +// either ID references --or-- in-line creation helpers, but not both. + +alias CreateThreadRequestToolResourcesFileSearch = CreateThreadRequestToolResourcesFileSearchVectorStoreIdReferences | CreateThreadRequestToolResourcesFileSearchVectorStoreCreationHelpers; + +model CreateThreadRequestToolResourcesFileSearchVectorStoreIdReferences { + ...CreateThreadRequestToolResourcesFileSearchBase; + + /** + * The [vector store](/docs/api-reference/vector-stores/object) attached to this thread. + * There can be a maximum of 1 vector store attached to the thread. + */ + @maxItems(1) + vector_store_ids?: string[]; +} + +model CreateThreadRequestToolResourcesFileSearchVectorStoreCreationHelpers { + ...CreateThreadRequestToolResourcesFileSearchBase; + + /** + * A helper to create a [vector store](/docs/api-reference/vector-stores/object) with + * file_ids and attach it to this thread. There can be a maximum of 1 vector store attached + * to the thread. + */ + @maxItems(1) + vector_stores?: CreateThreadRequestToolResourcesFileSearchVectorStoreCreationHelper[]; +} + +model CreateThreadRequestToolResourcesFileSearchBase { + // Common fields (currently none) +} + +alias CreateThreadRequestToolResourcesFileSearchVectorStoreCreationHelper = { + /** + * A list of [file](/docs/api-reference/files) IDs to add to the vector store. There can be + * a maximum of 10000 files in a vector store. + */ + @maxItems(10000) + file_ids?: string[]; + + ...MetadataPropertyForRequest; +}; diff --git a/specification/base/typespec/threads/main.tsp b/specification/base/typespec/threads/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/threads/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/threads/models.tsp b/specification/base/typespec/threads/models.tsp new file mode 100644 index 000000000..04fc23aae --- /dev/null +++ b/specification/base/typespec/threads/models.tsp @@ -0,0 +1,102 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../common"; +import "../messages"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +/** + * Options to create a new thread. If no thread is provided when running a + * request, an empty thread will be created. + */ +model CreateThreadRequest { + /** A list of [messages](/docs/api-reference/messages) to start the thread with. */ + messages?: CreateMessageRequest[]; + + @doc(""" + A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + """) + tool_resources?: { + code_interpreter?: { + @doc(""" + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + """) + @maxItems(20) + file_ids?: string[] = #[]; + }; + + // Tool customization: use custom type for sophisticated union + file_search?: ToolResourcesFileSearch; + } | null; + + ...MetadataPropertyForRequest; +} + +model ModifyThreadRequest { + @doc(""" + A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + """) + tool_resources?: { + code_interpreter?: { + @doc(""" + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + """) + @maxItems(20) + file_ids?: string[] = #[]; + }; + + // Tool customization: use custom type for sophisticated union + file_search?: ToolResourcesFileSearchIdsOnly; + } | null; + + ...MetadataPropertyForRequest; +} + +model DeleteThreadResponse { + id: string; + deleted: boolean; + object: "thread.deleted"; +} + +/** Represents a thread that contains [messages](/docs/api-reference/messages). */ +model ThreadObject { + /** The identifier, which can be referenced in API endpoints. */ + id: string; + + @doc(""" + The object type, which is always `thread`. + """) + object: "thread"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the thread was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + @doc(""" + A set of resources that are made available to the assistant's tools in this thread. The resources are specific to the type of tool. For example, the `code_interpreter` tool requires a list of file IDs, while the `file_search` tool requires a list of vector store IDs. + """) + tool_resources: { + code_interpreter?: { + @doc(""" + A list of [file](/docs/api-reference/files) IDs made available to the `code_interpreter` tool. There can be a maximum of 20 files associated with the tool. + """) + @maxItems(20) + file_ids?: string[] = #[]; + }; + file_search?: { + /** The [vector store](/docs/api-reference/vector-stores/object) attached to this thread. There can be a maximum of 1 vector store attached to the thread. */ + @maxItems(1) + vector_store_ids?: string[]; + }; + } | null; + + ...MetadataPropertyForResponse; +} diff --git a/specification/base/typespec/threads/operations.tsp b/specification/base/typespec/threads/operations.tsp new file mode 100644 index 000000000..1fc8e2254 --- /dev/null +++ b/specification/base/typespec/threads/operations.tsp @@ -0,0 +1,64 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/threads") +interface Threads { + @post + @operationId("createThread") + @tag("Assistants") + @summary("Create a thread.") + createThread( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + @body requestBody: CreateThreadRequest, + ): ThreadObject | ErrorResponse; + + @route("{thread_id}") + @get + @operationId("getThread") + @tag("Assistants") + @summary("Retrieves a thread.") + getThread( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the thread to retrieve. */ + @path thread_id: string, + ): ThreadObject | ErrorResponse; + + @route("{thread_id}") + @post + @operationId("modifyThread") + @tag("Assistants") + @summary("Modifies a thread.") + modifyThread( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the thread to modify. Only the `metadata` can be modified. */ + @path thread_id: string, + + @body requestBody: ModifyThreadRequest, + ): ThreadObject | ErrorResponse; + + @route("{thread_id}") + @delete + @operationId("deleteThread") + @tag("Assistants") + @summary("Delete a thread.") + deleteThread( + ...AcceptJsonHeader, + ...AssistantsBetaHeader, + + /** The ID of the thread to delete. */ + @path thread_id: string, + ): DeleteThreadResponse | ErrorResponse; +} diff --git a/specification/base/typespec/unsorted/custom.tsp b/specification/base/typespec/unsorted/custom.tsp new file mode 100644 index 000000000..1589d157f --- /dev/null +++ b/specification/base/typespec/unsorted/custom.tsp @@ -0,0 +1,3 @@ +import "@typespec/http"; + +namespace OpenAI; diff --git a/specification/base/typespec/unsorted/models.tsp b/specification/base/typespec/unsorted/models.tsp new file mode 100644 index 000000000..e8fb3a510 --- /dev/null +++ b/specification/base/typespec/unsorted/models.tsp @@ -0,0 +1,49 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +/** Emitted when there is a partial audio response. */ +model ResponseAudioDeltaEvent { + @doc(""" + The type of the event. Always `response.audio.delta`. + """) + type: "response.audio.delta"; + + /** A chunk of Base64 encoded response audio bytes. */ + delta: string; +} + +/** Emitted when the audio response is complete. */ +model ResponseAudioDoneEvent { + @doc(""" + The type of the event. Always `response.audio.done`. + """) + type: "response.audio.done"; +} + +/** Emitted when there is a partial transcript of audio. */ +model ResponseAudioTranscriptDeltaEvent { + @doc(""" + The type of the event. Always `response.audio.transcript.delta`. + """) + type: "response.audio.transcript.delta"; + + /** The partial transcript of the audio response. */ + delta: string; +} + +/** Emitted when the full audio transcript is completed. */ +model ResponseAudioTranscriptDoneEvent { + @doc(""" + The type of the event. Always `response.audio.transcript.done`. + """) + type: "response.audio.transcript.done"; +} diff --git a/specification/base/typespec/uploads/main.tsp b/specification/base/typespec/uploads/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/uploads/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/uploads/models.tsp b/specification/base/typespec/uploads/models.tsp new file mode 100644 index 000000000..f32318dd8 --- /dev/null +++ b/specification/base/typespec/uploads/models.tsp @@ -0,0 +1,99 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../files"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +model CreateUploadRequest { + /** The name of the file to upload. */ + filename: string; + + /** + * The intended purpose of the uploaded file. + * + * See the [documentation on File purposes](/docs/api-reference/files/create#files-create-purpose). + */ + purpose: "assistants" | "batch" | "fine-tune" | "vision"; + + /** The number of bytes in the file you are uploading. */ + bytes: int32; + + /** + * The MIME type of the file. + * + * This must fall within the supported MIME types for your file purpose. See the supported MIME types for assistants and vision. + */ + mime_type: string; +} + +model AddUploadPartRequest { + // Tool customization: Apply HttpPart for property in multipart request model + /** The chunk of bytes for this Part. */ + data: HttpPart; +} + +model CompleteUploadRequest { + /** The ordered list of Part IDs. */ + part_ids: string[]; + + /** The optional md5 checksum for the file contents to verify if the bytes uploaded matches what you expect. */ + md5?: string; +} + +/** The Upload object can accept byte chunks in the form of Parts. */ +model Upload { + /** The Upload unique identifier, which can be referenced in API endpoints. */ + id: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the Upload was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The name of the file to be uploaded. */ + filename: string; + + /** The intended number of bytes to be uploaded. */ + bytes: int32; + + /** The intended purpose of the file. [Please refer here](/docs/api-reference/files/object#files/object-purpose) for acceptable values. */ + purpose: string; + + /** The status of the Upload. */ + status: "pending" | "completed" | "cancelled" | "expired"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the Upload will expire. */ + @encode("unixTimestamp", int32) + expires_at: utcDateTime; + + /** The object type, which is always "upload". */ + object?: "upload"; + + file?: OpenAIFile | null; +} + +/** The upload Part represents a chunk of bytes we can add to an Upload object. */ +model UploadPart { + /** The upload Part unique identifier, which can be referenced in API endpoints. */ + id: string; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the Part was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The ID of the Upload object that this Part was added to. */ + upload_id: string; + + @doc(""" + The object type, which is always `upload.part`. + """) + object: "upload.part"; +} diff --git a/specification/base/typespec/uploads/operations.tsp b/specification/base/typespec/uploads/operations.tsp new file mode 100644 index 000000000..3ea06e6ad --- /dev/null +++ b/specification/base/typespec/uploads/operations.tsp @@ -0,0 +1,78 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("/uploads") +interface Uploads { + @post + @operationId("createUpload") + @tag("Uploads") + @summary(""" + Creates an intermediate [Upload](/docs/api-reference/uploads/object) object that you can add [Parts](/docs/api-reference/uploads/part-object) to. Currently, an Upload can accept at most 8 GB in total and expires after an hour after you create it. + + Once you complete the Upload, we will create a [File](/docs/api-reference/files/object) object that contains all the parts you uploaded. This File is usable in the rest of our platform as a regular File object. + + For certain `purpose`s, the correct `mime_type` must be specified. Please refer to documentation for the supported MIME types for your use case: + - [Assistants](/docs/assistants/tools/file-search/supported-files) + + For guidance on the proper filename extensions for each purpose, please follow the documentation on [creating a File](/docs/api-reference/files/create). + """) + createUpload( + @header accept: "application/json", + @body requestBody: CreateUploadRequest, + ): Upload | ErrorResponse; + + @route("{upload_id}/parts") + @post + @operationId("addUploadPart") + @tag("Uploads") + @summary(""" + Adds a [Part](/docs/api-reference/uploads/part-object) to an [Upload](/docs/api-reference/uploads/object) object. A Part represents a chunk of bytes from the file you are trying to upload. + + Each Part can be at most 64 MB, and you can add Parts until you hit the Upload maximum of 8 GB. + + It is possible to add multiple Parts in parallel. You can decide the intended order of the Parts when you [complete the Upload](/docs/api-reference/uploads/complete). + """) + addUploadPart( + @header accept: "application/json", + @header contentType: "multipart/form-data", + @path upload_id: string, + @multipartBody requestBody: AddUploadPartRequest, + ): UploadPart | ErrorResponse; + + @route("{upload_id}/complete") + @post + @operationId("completeUpload") + @tag("Uploads") + @summary(""" + Completes the [Upload](/docs/api-reference/uploads/object). + + Within the returned Upload object, there is a nested [File](/docs/api-reference/files/object) object that is ready to use in the rest of the platform. + + You can specify the order of the Parts by passing in an ordered list of the Part IDs. + + The number of bytes uploaded upon completion must match the number of bytes initially specified when creating the Upload object. No Parts may be added after an Upload is completed. + """) + completeUpload( + @header accept: "application/json", + @path upload_id: string, + @body requestBody: CompleteUploadRequest, + ): Upload | ErrorResponse; + + @route("{upload_id}/cancel") + @post + @operationId("cancelUpload") + @tag("Uploads") + @summary("Cancels the Upload. No Parts may be added after an Upload is cancelled.") + cancelUpload( + @header accept: "application/json", + @path upload_id: string, + ): Upload | ErrorResponse; +} diff --git a/specification/base/typespec/vector-stores/custom.tsp b/specification/base/typespec/vector-stores/custom.tsp new file mode 100644 index 000000000..0b3adf637 --- /dev/null +++ b/specification/base/typespec/vector-stores/custom.tsp @@ -0,0 +1,22 @@ +import "../../entrypoints/sdk.dotnet/specialized-types.tsp"; + +using TypeSpec.OpenAPI; + +namespace OpenAI; + +union ListVectorStoreFilesFilter { + string, + "in_progress", + "completed", + "failed", + "cancelled", +} + +@discriminator("type") +model ChunkingStrategyResponseParam { + type: "static" | "other"; +} + +enum VectorStoreExpirationAnchor { + last_active_at, +} diff --git a/specification/base/typespec/vector-stores/main.tsp b/specification/base/typespec/vector-stores/main.tsp new file mode 100644 index 000000000..144c4aeaf --- /dev/null +++ b/specification/base/typespec/vector-stores/main.tsp @@ -0,0 +1 @@ +import "./operations.tsp"; diff --git a/specification/base/typespec/vector-stores/models.tsp b/specification/base/typespec/vector-stores/models.tsp new file mode 100644 index 000000000..8e5c6db28 --- /dev/null +++ b/specification/base/typespec/vector-stores/models.tsp @@ -0,0 +1,426 @@ +/* + * This file was automatically generated from an OpenAPI .yaml file. + * Edits made directly to this file will be lost. + */ + +import "../common"; +import "./custom.tsp"; + +using Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +// Tool generated type. Extracts from VectorStoreFileContentResponse.data +alias VectorStoreFileContentResponseData = { + @doc(""" + The content type (currently only `"text"`) + """) + type?: string; + + /** The text content */ + text?: string; +}; + +/** The expiration policy for a vector store. */ +model VectorStoreExpirationAfter { + // Tool customization: Use enum instead of string constants to maintain backwards compatibility + @doc(""" + Anchor timestamp after which the expiration policy applies. Supported anchors: `last_active_at`. + """) + anchor: VectorStoreExpirationAnchor.last_active_at; + + /** The number of days after the anchor time that the vector store will expire. */ + @minValue(1) + @maxValue(365) + days: int32; +} + +@doc(""" + A vector store is a collection of processed files can be used by the `file_search` tool. + """) +model VectorStoreObject { + /** The identifier, which can be referenced in API endpoints. */ + id: string; + + @doc(""" + The object type, which is always `vector_store`. + """) + object: "vector_store"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the vector store was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The name of the vector store. */ + name: string; + + /** The total number of bytes used by the files in the vector store. */ + usage_bytes: int32; + + file_counts: { + /** The number of files that are currently being processed. */ + in_progress: int32; + + /** The number of files that have been successfully processed. */ + completed: int32; + + /** The number of files that have failed to process. */ + failed: int32; + + /** The number of files that were cancelled. */ + cancelled: int32; + + /** The total number of files. */ + total: int32; + }; + + @doc(""" + The status of the vector store, which can be either `expired`, `in_progress`, or `completed`. A status of `completed` indicates that the vector store is ready for use. + """) + status: "expired" | "in_progress" | "completed"; + + expires_after?: VectorStoreExpirationAfter; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the vector store will expire. */ + @encode("unixTimestamp", int32) + expires_at?: utcDateTime | null; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the vector store was last active. */ + @encode("unixTimestamp", int32) + last_active_at: utcDateTime | null; + + ...MetadataPropertyForResponse; +} + +model CreateVectorStoreRequest { + @doc(""" + A list of [File](/docs/api-reference/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files. + """) + @maxItems(500) + file_ids?: string[]; + + /** The name of the vector store. */ + name?: string; + + expires_after?: VectorStoreExpirationAfter; + + @doc(""" + The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. Only applicable if `file_ids` is non-empty. + """) + chunking_strategy?: AutoChunkingStrategyRequestParam | StaticChunkingStrategyRequestParam; + + ...MetadataPropertyForRequest; +} + +model UpdateVectorStoreRequest { + /** The name of the vector store. */ + name?: string | null; + + expires_after?: VectorStoreExpirationAfter | null; + ...MetadataPropertyForRequest; +} + +model ListVectorStoresResponse { + // Tool customization: add a clear enum enforcement of constrained 'object' label + object: "list"; + + data: VectorStoreObject[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model DeleteVectorStoreResponse { + id: string; + deleted: boolean; + object: "vector_store.deleted"; +} + +/** A list of files attached to a vector store. */ +model VectorStoreFileObject { + /** The identifier, which can be referenced in API endpoints. */ + id: string; + + @doc(""" + The object type, which is always `vector_store.file`. + """) + object: "vector_store.file"; + + /** The total vector store usage in bytes. Note that this may be different from the original file size. */ + usage_bytes: int32; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the vector store file was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The ID of the [vector store](/docs/api-reference/vector-stores/object) that the [File](/docs/api-reference/files) is attached to. */ + vector_store_id: string; + + @doc(""" + The status of the vector store file, which can be either `in_progress`, `completed`, `cancelled`, or `failed`. The status `completed` indicates that the vector store file is ready for use. + """) + status: "in_progress" | "completed" | "cancelled" | "failed"; + + @doc(""" + The last error associated with this vector store file. Will be `null` if there are no errors. + """) + last_error: { + @doc(""" + One of `server_error` or `rate_limit_exceeded`. + """) + code: "server_error" | "unsupported_file" | "invalid_file"; + + /** A human-readable description of the error. */ + message: string; + } | null; + + // Tool customization: Use customized common base for chunking strategy response + /** The strategy used to chunk the file. */ + chunking_strategy?: ChunkingStrategyResponseParam; + + attributes?: VectorStoreFileAttributes | null; +} + +model CreateVectorStoreFileRequest { + @doc(""" + A [File](/docs/api-reference/files) ID that the vector store should use. Useful for tools like `file_search` that can access files. + """) + file_id: string; + + chunking_strategy?: ChunkingStrategyRequestParam; + attributes?: VectorStoreFileAttributes | null; +} + +model ListVectorStoreFilesResponse { + // Tool customization: add a clear enum enforcement of constrained 'object' label + object: "list"; + + data: VectorStoreFileObject[]; + first_id: string; + last_id: string; + has_more: boolean; +} + +model DeleteVectorStoreFileResponse { + id: string; + deleted: boolean; + object: "vector_store.file.deleted"; +} + +/** A batch of files attached to a vector store. */ +model VectorStoreFileBatchObject { + /** The identifier, which can be referenced in API endpoints. */ + id: string; + + @doc(""" + The object type, which is always `vector_store.file_batch`. + """) + object: "vector_store.files_batch"; + + // Tool customization: 'created' and fields ending in '_at' are Unix encoded utcDateTime + /** The Unix timestamp (in seconds) for when the vector store files batch was created. */ + @encode("unixTimestamp", int32) + created_at: utcDateTime; + + /** The ID of the [vector store](/docs/api-reference/vector-stores/object) that the [File](/docs/api-reference/files) is attached to. */ + vector_store_id: string; + + @doc(""" + The status of the vector store files batch, which can be either `in_progress`, `completed`, `cancelled` or `failed`. + """) + status: "in_progress" | "completed" | "cancelled" | "failed"; + + file_counts: { + /** The number of files that are currently being processed. */ + in_progress: int32; + + /** The number of files that have been processed. */ + completed: int32; + + /** The number of files that have failed to process. */ + failed: int32; + + /** The number of files that where cancelled. */ + cancelled: int32; + + /** The total number of files. */ + total: int32; + }; +} + +model CreateVectorStoreFileBatchRequest { + @doc(""" + A list of [File](/docs/api-reference/files) IDs that the vector store should use. Useful for tools like `file_search` that can access files. + """) + @minItems(1) + @maxItems(500) + file_ids: string[]; + + chunking_strategy?: ChunkingStrategyRequestParam; + attributes?: VectorStoreFileAttributes | null; +} + +// Tool customization (apply_discriminator): Apply customized common base for chunking strategy response +@doc(""" + This is returned when the chunking strategy is unknown. Typically, this is because the file was indexed before the `chunking_strategy` concept was introduced in the API. + """) +model OtherChunkingStrategyResponseParam extends ChunkingStrategyResponseParam { + @doc(""" + Always `other`. + """) + type: "other"; +} + +// Tool customization (apply_discriminator): Apply customized common base for chunking strategy response +model StaticChunkingStrategyResponseParam + extends ChunkingStrategyResponseParam { + @doc(""" + Always `static`. + """) + type: "static"; + + static: StaticChunkingStrategy; +} + +model StaticChunkingStrategy { + @doc(""" + The maximum number of tokens in each chunk. The default value is `800`. The minimum value is `100` and the maximum value is `4096`. + """) + @minValue(100) + @maxValue(4096) + max_chunk_size_tokens: int32; + + @doc(""" + The number of tokens that overlap between chunks. The default value is `400`. + + Note that the overlap must not exceed half of `max_chunk_size_tokens`. + """) + chunk_overlap_tokens: int32; +} + +// Tool customization: Qualify union as discriminated base +@doc(""" + The chunking strategy used to chunk the file(s). If not set, will use the `auto` strategy. + """) +@discriminator("type") +model ChunkingStrategyRequestParam { + /** The type of chunking strategy. */ + type: "auto" | "static"; +} + +// Tool customization (apply_discriminator): apply custom common base +@doc(""" + The default strategy. This strategy currently uses a `max_chunk_size_tokens` of `800` and `chunk_overlap_tokens` of `400`. + """) +model AutoChunkingStrategyRequestParam extends ChunkingStrategyRequestParam { + @doc(""" + Always `auto`. + """) + type: "auto"; +} + +// Tool customization (apply_discriminator): apply custom common base +/** Customize your own chunking strategy by setting chunk size and chunk overlap. */ +model StaticChunkingStrategyRequestParam extends ChunkingStrategyRequestParam { + @doc(""" + Always `static`. + """) + type: "static"; + + static: StaticChunkingStrategy; +} + +model UpdateVectorStoreFileAttributesRequest { + attributes: VectorStoreFileAttributes | null; +} + +/** Represents the parsed content of a vector store file. */ +model VectorStoreFileContentResponse { + @doc(""" + The object type, which is always `vector_store.file_content.page` + """) + object: "vector_store.file_content.page"; + + /** Parsed content of the file. */ + data: VectorStoreFileContentResponseData[]; + + /** Indicates if there are more content pages to fetch. */ + has_more: boolean; + + /** The token for the next page, if any. */ + next_page: string | null; +} + +model VectorStoreSearchRequest { + /** A query string for a search */ + query: string | string[]; + + /** Whether to rewrite the natural language query for vector search. */ + rewrite_query?: boolean = false; + + /** The maximum number of results to return. This number should be between 1 and 50 inclusive. */ + @minValue(1) + @maxValue(50) + max_num_results?: int32 = 10; + + /** A filter to apply based on file attributes. */ + filters?: ComparisonFilter | CompoundFilter; + + /** Ranking options for search. */ + ranking_options?: { + ranker?: "auto" | "default-2024-11-15" = "auto"; + + @minValue(0) + @maxValue(1) + score_threshold?: float32 = 0; + }; +} + +model VectorStoreSearchResultContentObject { + /** The type of content. */ + type: "text"; + + /** The text content returned from search. */ + text: string; +} + +model VectorStoreSearchResultItem { + /** The ID of the vector store file. */ + file_id: string; + + /** The name of the vector store file. */ + filename: string; + + /** The similarity score for the result. */ + @minValue(0) + @maxValue(1) + score: float32; + + attributes: VectorStoreFileAttributes | null; + + /** Content chunks from the file. */ + content: VectorStoreSearchResultContentObject[]; +} + +model VectorStoreSearchResultsPage { + @doc(""" + The object type, which is always `vector_store.search_results.page` + """) + object: "vector_store.search_results.page"; + + search_query: string[]; + + /** The list of search result items. */ + data: VectorStoreSearchResultItem[]; + + /** Indicates if there are more results to fetch. */ + has_more: boolean; + + /** The token for the next page, if any. */ + next_page: string | null; +} diff --git a/specification/base/typespec/vector-stores/operations.tsp b/specification/base/typespec/vector-stores/operations.tsp new file mode 100644 index 000000000..ac707f51d --- /dev/null +++ b/specification/base/typespec/vector-stores/operations.tsp @@ -0,0 +1,226 @@ +import "@typespec/http"; +import "@typespec/openapi"; + +import "../common"; +import "./custom.tsp"; +import "./models.tsp"; + +using TypeSpec.Http; +using TypeSpec.OpenAPI; + +namespace OpenAI; + +@route("vector_stores") +@tag("Vector Stores") +interface VectorStores { + @get + @operationId("listVectorStores") + @summary("Returns a list of vector stores.") + listVectorStores( + ...AcceptJsonHeader, + ...CommonPageQueryParameters, + ): ListVectorStoresResponse | ErrorResponse; + + @post + @operationId("createVectorStore") + @summary("Creates a vector store.") + createVectorStore( + ...AcceptJsonHeader, + @body requestBody: CreateVectorStoreRequest, + ): VectorStoreObject | ErrorResponse; + + @route("{vector_store_id}") + @get + @operationId("getVectorStore") + @summary("Retrieves a vector store.") + getVectorStore( + ...AcceptJsonHeader, + + /** The ID of the vector store to retrieve. */ + @path vector_store_id: string, + ): VectorStoreObject | ErrorResponse; + + @route("{vector_store_id}") + @post + @operationId("modifyVectorStore") + @summary("Modifies a vector store.") + modifyVectorStore( + ...AcceptJsonHeader, + + /** The ID of the vector store to modify. */ + @path vector_store_id: string, + + @body requestBody: UpdateVectorStoreRequest, + ): VectorStoreObject | ErrorResponse; + + @route("{vector_store_id}") + @delete + @operationId("deleteVectorStore") + @summary("Delete a vector store.") + deleteVectorStore( + ...AcceptJsonHeader, + + /** The ID of the vector store to delete. */ + @path vector_store_id: string, + ): DeleteVectorStoreResponse | ErrorResponse; + + @route("{vector_store_id}/file_batches") + @post + @operationId("createVectorStoreFileBatch") + @summary("Create a vector store file batch.") + createVectorStoreFileBatch( + ...AcceptJsonHeader, + + /** The ID of the vector store for which to create a file batch. */ + @path vector_store_id: string, + + @body requestBody: CreateVectorStoreFileBatchRequest, + ): VectorStoreFileBatchObject | ErrorResponse; + + @route("{vector_store_id}/file_batches/{batch_id}") + @get + @operationId("getVectorStoreFileBatch") + @summary("Retrieves a vector store file batch.") + getVectorStoreFileBatch( + ...AcceptJsonHeader, + + /** The ID of the vector store that the file batch belongs to. */ + @path vector_store_id: string, + + /** The ID of the file batch being retrieved. */ + @path batch_id: string, + ): VectorStoreFileBatchObject | ErrorResponse; + + @route("{vector_store_id}/file_batches/{batch_id}/cancel") + @post + @operationId("cancelVectorStoreFileBatch") + @summary("Cancel a vector store file batch. This attempts to cancel the processing of files in this batch as soon as possible.") + cancelVectorStoreFileBatch( + ...AcceptJsonHeader, + + /** The ID of the vector store that the file batch belongs to. */ + @path vector_store_id: string, + + /** The ID of the file batch to cancel. */ + @path batch_id: string, + ): VectorStoreFileBatchObject | ErrorResponse; + + @route("{vector_store_id}/file_batches/{batch_id}/files") + @get + @operationId("listFilesInVectorStoreBatch") + @summary("Returns a list of vector store files in a batch.") + listFilesInVectorStoreBatch( + ...AcceptJsonHeader, + + /** The ID of the vector store that the file batch belongs to. */ + @path vector_store_id: string, + + /** The ID of the file batch that the files belong to. */ + @path batch_id: string, + + ...VectorStoreFilesPageQueryParameters, + ): ListVectorStoreFilesResponse | ErrorResponse; + + @route("{vector_store_id}/files") + @get + @operationId("listVectorStoreFiles") + @summary("Returns a list of vector store files.") + listVectorStoreFiles( + ...AcceptJsonHeader, + + /** The ID of the vector store that the files belong to. */ + @path vector_store_id: string, + + ...VectorStoreFilesPageQueryParameters, + ): ListVectorStoreFilesResponse | ErrorResponse; + + @route("{vector_store_id}/files") + @post + @operationId("createVectorStoreFile") + @summary("Create a vector store file by attaching a [File](/docs/api-reference/files) to a [vector store](/docs/api-reference/vector-stores/object).") + createVectorStoreFile( + ...AcceptJsonHeader, + + /** The ID of the vector store for which to create a File. */ + @path vector_store_id: string, + + @body requestBody: CreateVectorStoreFileRequest, + ): VectorStoreFileObject | ErrorResponse; + + @route("{vector_store_id}/files/{file_id}") + @get + @operationId("getVectorStoreFile") + @summary("Retrieves a vector store file.") + getVectorStoreFile( + ...AcceptJsonHeader, + + /** The ID of the vector store that the file belongs to. */ + @path vector_store_id: string, + + /** The ID of the file being retrieved. */ + @path file_id: string, + ): VectorStoreFileObject | ErrorResponse; + + @route("{vector_store_id}/files/{file_id}") + @delete + @operationId("deleteVectorStoreFile") + @summary("Delete a vector store file. This will remove the file from the vector store but the file itself will not be deleted. To delete the file, use the [delete file](/docs/api-reference/files/delete) endpoint.") + deleteVectorStoreFile( + ...AcceptJsonHeader, + + /** The ID of the vector store that the file belongs to. */ + @path vector_store_id: string, + + /** The ID of the file to delete. */ + @path file_id: string, + ): DeleteVectorStoreFileResponse | ErrorResponse; + + @post + @route("{vector_store_id}/files/{file_id}") + @operationId("updateVectorStoreFileAttributes") + @summary("Update the attributes of a vector store file.") + updateVectorStoreFileAttributes( + /** The ID of the vector store the file being updated belongs to. */ + @path vector_store_id: string, + + /** The ID of the file to update attributes for. */ + @path file_id: string, + + ...UpdateVectorStoreFileAttributesRequest, + ): VectorStoreFileObject | ErrorResponse; + + @get + @route("{vector_store_id}/files/{file_id}/content") + @operationId("retrieveVectorStoreFileContent") + @summary("Retrieves the content of a vector store file.") + retrieveVectorStoreFileContent( + /** The ID of the vector store that the file belongs to. */ + @path vector_store_id: string, + + /** The ID of the file with content being retrieved. */ + @path file_id: string, + ): VectorStoreFileContentResponse | ErrorResponse; + + @post + @route("{vector_store_id}/search") + @operationId("searchVectorStore") + @summary("Searches a vector store for relevant chunks based on a query and file attributes filter.") + searchVectorStore( + /** The ID of the vector store to search. */ + @path vector_store_id: string, + + ...VectorStoreSearchRequest, + ): VectorStoreSearchResultsPage | ErrorResponse; +} + +alias VectorStoreFilesPageQueryParameters = { + ...PageLimitQueryParameter; + ...PageOrderQueryParameter; + ...PageAfterQueryParameter; + ...PageBeforeQueryParameter; + + /** + * Filter by file status. One of `in_progress`, `completed`, `failed`, `cancelled`. + */ + @query filter?: ListVectorStoreFilesFilter; +};