From 94f1c0f5ce25b5cfa3017410a7fb6f5758fe98c7 Mon Sep 17 00:00:00 2001 From: Quentin Pradet Date: Mon, 7 Apr 2025 17:24:27 +0400 Subject: [PATCH] Remove EIS APIs (#4212) (cherry picked from commit c542836a5f1966c8f70f9018779f9934a81d2118) # Conflicts: # output/schema/schema-serverless.json # output/schema/schema.json # specification/inference/post_eis_chat_completion/PostEisChatCompletionResponse.ts # specification/inference/put_eis/PutEisResponse.ts --- output/openapi/elasticsearch-openapi.json | 141 -------- .../elasticsearch-serverless-openapi.json | 141 -------- output/schema/schema-serverless.json | 304 ------------------ output/schema/schema.json | 266 +-------------- output/typescript/types.ts | 27 -- .../PostEisChatCompletionRequest.ts | 48 --- .../PostEisChatCompletionResponse.ts | 24 -- .../PostEisChatCompletionRequestExample.yaml | 17 - .../inference/put_eis/PutEisRequest.ts | 66 ---- .../inference/put_eis/PutEisResponse.ts | 24 -- .../example/request/PutEisRequestExample.yaml | 11 - 11 files changed, 9 insertions(+), 1060 deletions(-) delete mode 100644 specification/inference/post_eis_chat_completion/PostEisChatCompletionRequest.ts delete mode 100644 specification/inference/post_eis_chat_completion/PostEisChatCompletionResponse.ts delete mode 100644 specification/inference/post_eis_chat_completion/examples/PostEisChatCompletionRequestExample.yaml delete mode 100644 specification/inference/put_eis/PutEisRequest.ts delete mode 100644 specification/inference/put_eis/PutEisResponse.ts delete mode 100644 specification/inference/put_eis/example/request/PutEisRequestExample.yaml diff --git a/output/openapi/elasticsearch-openapi.json b/output/openapi/elasticsearch-openapi.json index b1ab67fe65..5e2391d759 100644 --- a/output/openapi/elasticsearch-openapi.json +++ b/output/openapi/elasticsearch-openapi.json @@ -17797,52 +17797,6 @@ "x-state": "Added in 8.11.0" } }, - "/_inference/chat_completion/{eis_inference_id}/_stream": { - "post": { - "tags": [ - "inference" - ], - "summary": "Perform a chat completion task through the Elastic Inference Service (EIS)", - "description": "Perform a chat completion inference task with the `elastic` service.", - "operationId": "inference-post-eis-chat-completion", - "parameters": [ - { - "in": "path", - "name": "eis_inference_id", - "description": "The unique identifier of the inference endpoint.", - "required": true, - "deprecated": false, - "schema": { - "$ref": "#/components/schemas/_types:Id" - }, - "style": "simple" - } - ], - "requestBody": { - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/inference._types:RequestChatCompletion" - } - } - }, - "required": true - }, - "responses": { - "200": { - "description": "", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/_types:StreamResult" - } - } - } - } - }, - "x-state": "Added in 9.0.0" - } - }, "/_inference/{task_type}/{alibabacloud_inference_id}": { "put": { "tags": [ @@ -18363,74 +18317,6 @@ "x-state": "Added in 8.13.0" } }, - "/_inference/{task_type}/{eis_inference_id}": { - "put": { - "tags": [ - "inference" - ], - "summary": "Create an Elastic Inference Service (EIS) inference endpoint", - "description": "Create an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).", - "operationId": "inference-put-eis", - "parameters": [ - { - "in": "path", - "name": "task_type", - "description": "The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.", - "required": true, - "deprecated": false, - "schema": { - "$ref": "#/components/schemas/inference._types:EisTaskType" - }, - "style": "simple" - }, - { - "in": "path", - "name": "eis_inference_id", - "description": "The unique identifier of the inference endpoint.", - "required": true, - "deprecated": false, - "schema": { - "$ref": "#/components/schemas/_types:Id" - }, - "style": "simple" - } - ], - "requestBody": { - "content": { - "application/json": { - "schema": { - "type": "object", - "properties": { - "service": { - "$ref": "#/components/schemas/inference._types:EisServiceType" - }, - "service_settings": { - "$ref": "#/components/schemas/inference._types:EisServiceSettings" - } - }, - "required": [ - "service", - "service_settings" - ] - } - } - } - }, - "responses": { - "200": { - "description": "", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/inference._types:InferenceEndpointInfo" - } - } - } - } - }, - "x-state": "Added in 8.12.0" - } - }, "/_inference/{task_type}/{elasticsearch_inference_id}": { "put": { "tags": [ @@ -78807,33 +78693,6 @@ "START" ] }, - "inference._types:EisTaskType": { - "type": "string", - "enum": [ - "chat_completion" - ] - }, - "inference._types:EisServiceType": { - "type": "string", - "enum": [ - "elastic" - ] - }, - "inference._types:EisServiceSettings": { - "type": "object", - "properties": { - "model_id": { - "description": "The name of the model to use for the inference task.", - "type": "string" - }, - "rate_limit": { - "$ref": "#/components/schemas/inference._types:RateLimitSetting" - } - }, - "required": [ - "model_id" - ] - }, "inference._types:ElasticsearchTaskType": { "type": "string", "enum": [ diff --git a/output/openapi/elasticsearch-serverless-openapi.json b/output/openapi/elasticsearch-serverless-openapi.json index 36034a85f5..5b2fd94cfa 100644 --- a/output/openapi/elasticsearch-serverless-openapi.json +++ b/output/openapi/elasticsearch-serverless-openapi.json @@ -9763,52 +9763,6 @@ "x-state": "Added in 8.11.0" } }, - "/_inference/chat_completion/{eis_inference_id}/_stream": { - "post": { - "tags": [ - "inference" - ], - "summary": "Perform a chat completion task through the Elastic Inference Service (EIS)", - "description": "Perform a chat completion inference task with the `elastic` service.", - "operationId": "inference-post-eis-chat-completion", - "parameters": [ - { - "in": "path", - "name": "eis_inference_id", - "description": "The unique identifier of the inference endpoint.", - "required": true, - "deprecated": false, - "schema": { - "$ref": "#/components/schemas/_types:Id" - }, - "style": "simple" - } - ], - "requestBody": { - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/inference._types:RequestChatCompletion" - } - } - }, - "required": true - }, - "responses": { - "200": { - "description": "", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/_types:StreamResult" - } - } - } - } - }, - "x-state": "Added in 9.0.0" - } - }, "/_inference/{task_type}/{alibabacloud_inference_id}": { "put": { "tags": [ @@ -10329,74 +10283,6 @@ "x-state": "Added in 8.13.0" } }, - "/_inference/{task_type}/{eis_inference_id}": { - "put": { - "tags": [ - "inference" - ], - "summary": "Create an Elastic Inference Service (EIS) inference endpoint", - "description": "Create an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).", - "operationId": "inference-put-eis", - "parameters": [ - { - "in": "path", - "name": "task_type", - "description": "The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.", - "required": true, - "deprecated": false, - "schema": { - "$ref": "#/components/schemas/inference._types:EisTaskType" - }, - "style": "simple" - }, - { - "in": "path", - "name": "eis_inference_id", - "description": "The unique identifier of the inference endpoint.", - "required": true, - "deprecated": false, - "schema": { - "$ref": "#/components/schemas/_types:Id" - }, - "style": "simple" - } - ], - "requestBody": { - "content": { - "application/json": { - "schema": { - "type": "object", - "properties": { - "service": { - "$ref": "#/components/schemas/inference._types:EisServiceType" - }, - "service_settings": { - "$ref": "#/components/schemas/inference._types:EisServiceSettings" - } - }, - "required": [ - "service", - "service_settings" - ] - } - } - } - }, - "responses": { - "200": { - "description": "", - "content": { - "application/json": { - "schema": { - "$ref": "#/components/schemas/inference._types:InferenceEndpointInfo" - } - } - } - } - }, - "x-state": "Added in 8.12.0" - } - }, "/_inference/{task_type}/{elasticsearch_inference_id}": { "put": { "tags": [ @@ -50120,33 +50006,6 @@ "START" ] }, - "inference._types:EisTaskType": { - "type": "string", - "enum": [ - "chat_completion" - ] - }, - "inference._types:EisServiceType": { - "type": "string", - "enum": [ - "elastic" - ] - }, - "inference._types:EisServiceSettings": { - "type": "object", - "properties": { - "model_id": { - "description": "The name of the model to use for the inference task.", - "type": "string" - }, - "rate_limit": { - "$ref": "#/components/schemas/inference._types:RateLimitSetting" - } - }, - "required": [ - "model_id" - ] - }, "inference._types:ElasticsearchTaskType": { "type": "string", "enum": [ diff --git a/output/schema/schema-serverless.json b/output/schema/schema-serverless.json index a7b106c1da..682aaf3750 100644 --- a/output/schema/schema-serverless.json +++ b/output/schema/schema-serverless.json @@ -4662,51 +4662,6 @@ } ] }, - { - "availability": { - "serverless": { - "stability": "stable", - "visibility": "public" - }, - "stack": { - "since": "9.0.0", - "stability": "stable", - "visibility": "public" - } - }, - "description": "Perform a chat completion task through the Elastic Inference Service (EIS).\n\nPerform a chat completion inference task with the `elastic` service.", - "docId": "inference-api-post-eis-chat-completion", - "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/post-inference-api.html", - "name": "inference.post_eis_chat_completion", - "privileges": { - "cluster": [ - "manage_inference" - ] - }, - "request": { - "name": "Request", - "namespace": "inference.post_eis_chat_completion" - }, - "requestBodyRequired": true, - "requestMediaType": [ - "application/json" - ], - "response": { - "name": "Response", - "namespace": "inference.post_eis_chat_completion" - }, - "responseMediaType": [ - "application/json" - ], - "urls": [ - { - "methods": [ - "POST" - ], - "path": "/_inference/chat_completion/{eis_inference_id}/_stream" - } - ] - }, { "availability": { "serverless": { @@ -5028,51 +4983,6 @@ } ] }, - { - "availability": { - "serverless": { - "stability": "stable", - "visibility": "public" - }, - "stack": { - "since": "8.12.0", - "stability": "stable", - "visibility": "public" - } - }, - "description": "Create an Elastic Inference Service (EIS) inference endpoint.\n\nCreate an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).", - "docId": "inference-api-put-eis", - "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-elastic.html", - "name": "inference.put_eis", - "privileges": { - "cluster": [ - "manage_inference" - ] - }, - "request": { - "name": "Request", - "namespace": "inference.put_eis" - }, - "requestBodyRequired": false, - "requestMediaType": [ - "application/json" - ], - "response": { - "name": "Response", - "namespace": "inference.put_eis" - }, - "responseMediaType": [ - "application/json" - ], - "urls": [ - { - "methods": [ - "PUT" - ], - "path": "/_inference/{task_type}/{eis_inference_id}" - } - ] - }, { "availability": { "serverless": { @@ -27958,68 +27868,6 @@ }, "specLocation": "inference/get/GetResponse.ts#L22-L26" }, - { - "attachedBehaviors": [ - "CommonQueryParameters" - ], - "body": { - "codegenName": "chat_completion_request", - "kind": "value", - "value": { - "kind": "instance_of", - "type": { - "name": "RequestChatCompletion", - "namespace": "inference._types" - } - } - }, - "description": "Perform a chat completion task through the Elastic Inference Service (EIS).\n\nPerform a chat completion inference task with the `elastic` service.", - "inherits": { - "type": { - "name": "RequestBase", - "namespace": "_types" - } - }, - "kind": "request", - "name": { - "name": "Request", - "namespace": "inference.post_eis_chat_completion" - }, - "path": [ - { - "description": "The unique identifier of the inference endpoint.", - "name": "eis_inference_id", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "Id", - "namespace": "_types" - } - } - } - ], - "query": [], - "specLocation": "inference/post_eis_chat_completion/PostEisChatCompletionRequest.ts#L23-L48" - }, - { - "body": { - "kind": "value", - "value": { - "kind": "instance_of", - "type": { - "name": "StreamResult", - "namespace": "_types" - } - } - }, - "kind": "response", - "name": { - "name": "Response", - "namespace": "inference.post_eis_chat_completion" - }, - "specLocation": "inference/post_eis_chat_completion/PostEisChatCompletionResponse.ts#L22-L24" - }, { "attachedBehaviors": [ "CommonQueryParameters" @@ -28878,98 +28726,6 @@ }, "specLocation": "inference/put_cohere/PutCohereResponse.ts#L22-L24" }, - { - "attachedBehaviors": [ - "CommonQueryParameters" - ], - "body": { - "kind": "properties", - "properties": [ - { - "description": "The type of service supported for the specified task type. In this case, `elastic`.", - "name": "service", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "EisServiceType", - "namespace": "inference._types" - } - } - }, - { - "description": "Settings used to install the inference model. These settings are specific to the `elastic` service.", - "name": "service_settings", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "EisServiceSettings", - "namespace": "inference._types" - } - } - } - ] - }, - "description": "Create an Elastic Inference Service (EIS) inference endpoint.\n\nCreate an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).", - "inherits": { - "type": { - "name": "RequestBase", - "namespace": "_types" - } - }, - "kind": "request", - "name": { - "name": "Request", - "namespace": "inference.put_eis" - }, - "path": [ - { - "description": "The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.", - "name": "task_type", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "EisTaskType", - "namespace": "inference._types" - } - } - }, - { - "description": "The unique identifier of the inference endpoint.", - "name": "eis_inference_id", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "Id", - "namespace": "_types" - } - } - } - ], - "query": [], - "specLocation": "inference/put_eis/PutEisRequest.ts#L28-L66" - }, - { - "body": { - "kind": "value", - "value": { - "kind": "instance_of", - "type": { - "name": "InferenceEndpointInfo", - "namespace": "inference._types" - } - } - }, - "kind": "response", - "name": { - "name": "Response", - "namespace": "inference.put_eis" - }, - "specLocation": "inference/put_eis/PutEisResponse.ts#L22-L24" - }, { "attachedBehaviors": [ "CommonQueryParameters" @@ -102892,32 +102648,6 @@ } } }, - { - "kind": "enum", - "members": [ - { - "name": "elastic" - } - ], - "name": { - "name": "EisServiceType", - "namespace": "inference._types" - }, - "specLocation": "inference/_types/CommonTypes.ts#L700-L702" - }, - { - "kind": "enum", - "members": [ - { - "name": "chat_completion" - } - ], - "name": { - "name": "EisTaskType", - "namespace": "inference._types" - }, - "specLocation": "inference/_types/CommonTypes.ts#L696-L698" - }, { "kind": "enum", "members": [ @@ -124647,40 +124377,6 @@ ], "specLocation": "inference/_types/CommonTypes.ts#L650-L682" }, - { - "kind": "interface", - "name": { - "name": "EisServiceSettings", - "namespace": "inference._types" - }, - "properties": [ - { - "description": "The name of the model to use for the inference task.", - "name": "model_id", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } - } - }, - { - "description": "This setting helps to minimize the number of rate limit errors returned.\nBy default, the `elastic` service sets the number of requests allowed per minute to `240` in case of `chat_completion`.", - "name": "rate_limit", - "required": false, - "type": { - "kind": "instance_of", - "type": { - "name": "RateLimitSetting", - "namespace": "inference._types" - } - } - } - ], - "specLocation": "inference/_types/CommonTypes.ts#L684-L694" - }, { "kind": "interface", "name": { diff --git a/output/schema/schema.json b/output/schema/schema.json index 8d8c05d9da..e12aad7d7e 100644 --- a/output/schema/schema.json +++ b/output/schema/schema.json @@ -9257,37 +9257,20 @@ }, { "availability": { - "serverless": { - "stability": "stable", - "visibility": "public" - }, "stack": { - "since": "9.0.0", "stability": "stable", "visibility": "public" } }, - "description": "Perform a chat completion task through the Elastic Inference Service (EIS).\n\nPerform a chat completion inference task with the `elastic` service.", - "docId": "inference-api-post-eis-chat-completion", - "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/post-inference-api.html", + "description": "Perform a chat completion task via the Elastic Inference Service (EIS)", + "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/inference-apis.html", "name": "inference.post_eis_chat_completion", - "privileges": { - "cluster": [ - "manage_inference" - ] - }, - "request": { - "name": "Request", - "namespace": "inference.post_eis_chat_completion" - }, - "requestBodyRequired": true, + "request": null, + "requestBodyRequired": false, "requestMediaType": [ "application/json" ], - "response": { - "name": "Response", - "namespace": "inference.post_eis_chat_completion" - }, + "response": null, "responseMediaType": [ "application/json" ], @@ -9623,37 +9606,20 @@ }, { "availability": { - "serverless": { - "stability": "stable", - "visibility": "public" - }, "stack": { - "since": "8.12.0", "stability": "stable", "visibility": "public" } }, - "description": "Create an Elastic Inference Service (EIS) inference endpoint.\n\nCreate an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).", - "docId": "inference-api-put-eis", - "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/{branch}/infer-service-elastic.html", + "description": "Configure an inference endpoint that uses the Elastic Inference Service (EIS)", + "docUrl": "https://www.elastic.co/guide/en/elasticsearch/reference/current/infer-service-elastic.html", "name": "inference.put_eis", - "privileges": { - "cluster": [ - "manage_inference" - ] - }, - "request": { - "name": "Request", - "namespace": "inference.put_eis" - }, + "request": null, "requestBodyRequired": false, "requestMediaType": [ "application/json" ], - "response": { - "name": "Response", - "namespace": "inference.put_eis" - }, + "response": null, "responseMediaType": [ "application/json" ], @@ -150915,66 +150881,6 @@ } } }, - { - "kind": "interface", - "name": { - "name": "EisServiceSettings", - "namespace": "inference._types" - }, - "properties": [ - { - "description": "The name of the model to use for the inference task.", - "name": "model_id", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "string", - "namespace": "_builtins" - } - } - }, - { - "description": "This setting helps to minimize the number of rate limit errors returned.\nBy default, the `elastic` service sets the number of requests allowed per minute to `240` in case of `chat_completion`.", - "name": "rate_limit", - "required": false, - "type": { - "kind": "instance_of", - "type": { - "name": "RateLimitSetting", - "namespace": "inference._types" - } - } - } - ], - "specLocation": "inference/_types/CommonTypes.ts#L684-L694" - }, - { - "kind": "enum", - "members": [ - { - "name": "elastic" - } - ], - "name": { - "name": "EisServiceType", - "namespace": "inference._types" - }, - "specLocation": "inference/_types/CommonTypes.ts#L700-L702" - }, - { - "kind": "enum", - "members": [ - { - "name": "chat_completion" - } - ], - "name": { - "name": "EisTaskType", - "namespace": "inference._types" - }, - "specLocation": "inference/_types/CommonTypes.ts#L696-L698" - }, { "kind": "interface", "name": { @@ -153253,68 +153159,6 @@ }, "specLocation": "inference/get/GetResponse.ts#L22-L26" }, - { - "kind": "request", - "attachedBehaviors": [ - "CommonQueryParameters" - ], - "body": { - "kind": "value", - "codegenName": "chat_completion_request", - "value": { - "kind": "instance_of", - "type": { - "name": "RequestChatCompletion", - "namespace": "inference._types" - } - } - }, - "description": "Perform a chat completion task through the Elastic Inference Service (EIS).\n\nPerform a chat completion inference task with the `elastic` service.", - "inherits": { - "type": { - "name": "RequestBase", - "namespace": "_types" - } - }, - "name": { - "name": "Request", - "namespace": "inference.post_eis_chat_completion" - }, - "path": [ - { - "description": "The unique identifier of the inference endpoint.", - "name": "eis_inference_id", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "Id", - "namespace": "_types" - } - } - } - ], - "query": [], - "specLocation": "inference/post_eis_chat_completion/PostEisChatCompletionRequest.ts#L23-L48" - }, - { - "kind": "response", - "body": { - "kind": "value", - "value": { - "kind": "instance_of", - "type": { - "name": "StreamResult", - "namespace": "_types" - } - } - }, - "name": { - "name": "Response", - "namespace": "inference.post_eis_chat_completion" - }, - "specLocation": "inference/post_eis_chat_completion/PostEisChatCompletionResponse.ts#L22-L24" - }, { "kind": "request", "attachedBehaviors": [ @@ -154173,98 +154017,6 @@ }, "specLocation": "inference/put_cohere/PutCohereResponse.ts#L22-L24" }, - { - "kind": "request", - "attachedBehaviors": [ - "CommonQueryParameters" - ], - "body": { - "kind": "properties", - "properties": [ - { - "description": "The type of service supported for the specified task type. In this case, `elastic`.", - "name": "service", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "EisServiceType", - "namespace": "inference._types" - } - } - }, - { - "description": "Settings used to install the inference model. These settings are specific to the `elastic` service.", - "name": "service_settings", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "EisServiceSettings", - "namespace": "inference._types" - } - } - } - ] - }, - "description": "Create an Elastic Inference Service (EIS) inference endpoint.\n\nCreate an inference endpoint to perform an inference task through the Elastic Inference Service (EIS).", - "inherits": { - "type": { - "name": "RequestBase", - "namespace": "_types" - } - }, - "name": { - "name": "Request", - "namespace": "inference.put_eis" - }, - "path": [ - { - "description": "The type of the inference task that the model will perform.\nNOTE: The `chat_completion` task type only supports streaming and only through the _stream API.", - "name": "task_type", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "EisTaskType", - "namespace": "inference._types" - } - } - }, - { - "description": "The unique identifier of the inference endpoint.", - "name": "eis_inference_id", - "required": true, - "type": { - "kind": "instance_of", - "type": { - "name": "Id", - "namespace": "_types" - } - } - } - ], - "query": [], - "specLocation": "inference/put_eis/PutEisRequest.ts#L28-L66" - }, - { - "kind": "response", - "body": { - "kind": "value", - "value": { - "kind": "instance_of", - "type": { - "name": "InferenceEndpointInfo", - "namespace": "inference._types" - } - } - }, - "name": { - "name": "Response", - "namespace": "inference.put_eis" - }, - "specLocation": "inference/put_eis/PutEisResponse.ts#L22-L24" - }, { "kind": "request", "attachedBehaviors": [ diff --git a/output/typescript/types.ts b/output/typescript/types.ts index e1a4986585..897823ab29 100644 --- a/output/typescript/types.ts +++ b/output/typescript/types.ts @@ -13239,15 +13239,6 @@ export type InferenceDenseByteVector = byte[] export type InferenceDenseVector = float[] -export interface InferenceEisServiceSettings { - model_id: string - rate_limit?: InferenceRateLimitSetting -} - -export type InferenceEisServiceType = 'elastic' - -export type InferenceEisTaskType = 'chat_completion' - export interface InferenceElasticsearchServiceSettings { adaptive_allocations?: InferenceAdaptiveAllocations deployment_id?: string @@ -13521,13 +13512,6 @@ export interface InferenceGetResponse { endpoints: InferenceInferenceEndpointInfo[] } -export interface InferencePostEisChatCompletionRequest extends RequestBase { - eis_inference_id: Id - body?: InferenceRequestChatCompletion -} - -export type InferencePostEisChatCompletionResponse = StreamResult - export interface InferencePutRequest extends RequestBase { task_type?: InferenceTaskType inference_id: Id @@ -13614,17 +13598,6 @@ export interface InferencePutCohereRequest extends RequestBase { export type InferencePutCohereResponse = InferenceInferenceEndpointInfo -export interface InferencePutEisRequest extends RequestBase { - task_type: InferenceEisTaskType - eis_inference_id: Id - body?: { - service: InferenceEisServiceType - service_settings: InferenceEisServiceSettings - } -} - -export type InferencePutEisResponse = InferenceInferenceEndpointInfo - export interface InferencePutElasticsearchRequest extends RequestBase { task_type: InferenceElasticsearchTaskType elasticsearch_inference_id: Id diff --git a/specification/inference/post_eis_chat_completion/PostEisChatCompletionRequest.ts b/specification/inference/post_eis_chat_completion/PostEisChatCompletionRequest.ts deleted file mode 100644 index 5141e37051..0000000000 --- a/specification/inference/post_eis_chat_completion/PostEisChatCompletionRequest.ts +++ /dev/null @@ -1,48 +0,0 @@ -/* - * Licensed to Elasticsearch B.V. under one or more contributor - * license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright - * ownership. Elasticsearch B.V. licenses this file to you under - * the Apache License, Version 2.0 (the "License"); you may - * not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, - * software distributed under the License is distributed on an - * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY - * KIND, either express or implied. See the License for the - * specific language governing permissions and limitations - * under the License. - */ - -import { RequestChatCompletion } from '@inference/_types/CommonTypes' -import { RequestBase } from '@_types/Base' -import { Id } from '@_types/common' -/** - * Perform a chat completion task through the Elastic Inference Service (EIS). - * - * Perform a chat completion inference task with the `elastic` service. - * @rest_spec_name inference.post_eis_chat_completion - * @availability stack since=9.0.0 stability=stable visibility=public - * @availability serverless stability=stable visibility=public - * @cluster_privileges manage_inference - * @doc_id inference-api-post-eis-chat-completion - */ -export interface Request extends RequestBase { - urls: [ - { - path: '/_inference/chat_completion/{eis_inference_id}/_stream' - methods: ['POST'] - } - ] - path_parts: { - /** - * The unique identifier of the inference endpoint. - */ - eis_inference_id: Id - } - /** @codegen_name chat_completion_request */ - body: RequestChatCompletion -} diff --git a/specification/inference/post_eis_chat_completion/PostEisChatCompletionResponse.ts b/specification/inference/post_eis_chat_completion/PostEisChatCompletionResponse.ts deleted file mode 100644 index 74b823bf40..0000000000 --- a/specification/inference/post_eis_chat_completion/PostEisChatCompletionResponse.ts +++ /dev/null @@ -1,24 +0,0 @@ -/* - * Licensed to Elasticsearch B.V. under one or more contributor - * license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright - * ownership. Elasticsearch B.V. licenses this file to you under - * the Apache License, Version 2.0 (the "License"); you may - * not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, - * software distributed under the License is distributed on an - * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY - * KIND, either express or implied. See the License for the - * specific language governing permissions and limitations - * under the License. - */ - -import { StreamResult } from '@_types/Binary' - -export class Response { - body: StreamResult -} diff --git a/specification/inference/post_eis_chat_completion/examples/PostEisChatCompletionRequestExample.yaml b/specification/inference/post_eis_chat_completion/examples/PostEisChatCompletionRequestExample.yaml deleted file mode 100644 index 575da1bfa6..0000000000 --- a/specification/inference/post_eis_chat_completion/examples/PostEisChatCompletionRequestExample.yaml +++ /dev/null @@ -1,17 +0,0 @@ -summary: A chat completion task -description: Run `POST /_inference/chat_completion//_stream` to perform a streaming chat completion task type. -# method_request: "POST /_inference/chat_completion/.rainbow-sprinkles-elastic/_stream" -# type: "request" -value: |- - { - "parameters": - "messages": [ - { - "role": "user", - "content": "Say yes if it works." - } - ], - "temperature": 0.7, - "max_completion_tokens": 300 - } - } diff --git a/specification/inference/put_eis/PutEisRequest.ts b/specification/inference/put_eis/PutEisRequest.ts deleted file mode 100644 index 40c898a6d0..0000000000 --- a/specification/inference/put_eis/PutEisRequest.ts +++ /dev/null @@ -1,66 +0,0 @@ -/* - * Licensed to Elasticsearch B.V. under one or more contributor - * license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright - * ownership. Elasticsearch B.V. licenses this file to you under - * the Apache License, Version 2.0 (the "License"); you may - * not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, - * software distributed under the License is distributed on an - * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY - * KIND, either express or implied. See the License for the - * specific language governing permissions and limitations - * under the License. - */ - -import { - EisServiceSettings, - EisServiceType, - EisTaskType -} from '@inference/_types/CommonTypes' -import { RequestBase } from '@_types/Base' -import { Id } from '@_types/common' - -/** - * Create an Elastic Inference Service (EIS) inference endpoint. - * - * Create an inference endpoint to perform an inference task through the Elastic Inference Service (EIS). - * @rest_spec_name inference.put_eis - * @availability stack since=8.12.0 stability=stable visibility=public - * @availability serverless stability=stable visibility=public - * @cluster_privileges manage_inference - * @doc_id inference-api-put-eis - */ -export interface Request extends RequestBase { - urls: [ - { - path: '/_inference/{task_type}/{eis_inference_id}' - methods: ['PUT'] - } - ] - path_parts: { - /** - * The type of the inference task that the model will perform. - * NOTE: The `chat_completion` task type only supports streaming and only through the _stream API. - */ - task_type: EisTaskType - /** - * The unique identifier of the inference endpoint. - */ - eis_inference_id: Id - } - body: { - /** - * The type of service supported for the specified task type. In this case, `elastic`. - */ - service: EisServiceType - /** - * Settings used to install the inference model. These settings are specific to the `elastic` service. - */ - service_settings: EisServiceSettings - } -} diff --git a/specification/inference/put_eis/PutEisResponse.ts b/specification/inference/put_eis/PutEisResponse.ts deleted file mode 100644 index d40639b031..0000000000 --- a/specification/inference/put_eis/PutEisResponse.ts +++ /dev/null @@ -1,24 +0,0 @@ -/* - * Licensed to Elasticsearch B.V. under one or more contributor - * license agreements. See the NOTICE file distributed with - * this work for additional information regarding copyright - * ownership. Elasticsearch B.V. licenses this file to you under - * the Apache License, Version 2.0 (the "License"); you may - * not use this file except in compliance with the License. - * You may obtain a copy of the License at - * - * http://www.apache.org/licenses/LICENSE-2.0 - * - * Unless required by applicable law or agreed to in writing, - * software distributed under the License is distributed on an - * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY - * KIND, either express or implied. See the License for the - * specific language governing permissions and limitations - * under the License. - */ - -import { InferenceEndpointInfo } from '@inference/_types/Services' - -export class Response { - body: InferenceEndpointInfo -} diff --git a/specification/inference/put_eis/example/request/PutEisRequestExample.yaml b/specification/inference/put_eis/example/request/PutEisRequestExample.yaml deleted file mode 100644 index 573bc66d22..0000000000 --- a/specification/inference/put_eis/example/request/PutEisRequestExample.yaml +++ /dev/null @@ -1,11 +0,0 @@ -summary: A chat completion task -description: Run `PUT _inference/chat_completion/chat-completion-endpoint` to create an inference endpoint to perform a chat completion task type. -# method_request: "PUT _inference/chat_completion/chat-completion-endpoint" -# type: "request" -value: |- - { - "service": "elastic", - "service_settings": { - "model_id": "rainbow-sprinkles" - } - }