Skip to content

Commit cbd089d

Browse files
authored
Merge branch 'main' into trimming
2 parents e869710 + 6203354 commit cbd089d

File tree

1,181 files changed

+35136
-29181
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

1,181 files changed

+35136
-29181
lines changed

.gitignore

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -177,3 +177,7 @@ artifacts
177177

178178
# Temporary typespec folders for typespec generation
179179
TempTypeSpecFiles/
180+
181+
# Artifacts from the generator
182+
tspCodeModel.json
183+
Configuration.json

CHANGELOG.md

Lines changed: 48 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -1,24 +1,58 @@
11
# Release History
22

3+
## 2.1.0 (2024-12-04)
4+
5+
### Features added
6+
7+
- OpenAI.Assistants:
8+
- Added a `Content` property to `RunStepFileSearchResult` ([`step_details.tool_calls.file_search.results.content` in the REST API](https://platform.openai.com/docs/api-reference/run-steps/step-object)). ([bf3f0ed](https://github.com/openai/openai-dotnet/commit/bf3f0eddeda1957a998491e36d7fb551e99be916))
9+
- When using an Assistant with the File Search tool, you can use this property to retrieve the contents of the File Search results that were used by the model.
10+
- Added `FileSearchRankingOptions` and `FileSearchResults` properties to `RunStepDetailsUpdate`. ([bf3f0ed](https://github.com/openai/openai-dotnet/commit/bf3f0eddeda1957a998491e36d7fb551e99be916))
11+
12+
### Breaking Changes in Preview APIs
13+
14+
- OpenAI.RealtimeConversation:
15+
- Renamed the `From*()` factory methods on `ConversationContentPart` to `Create*Part()` for consistency. ([bf3f0ed](https://github.com/openai/openai-dotnet/commit/bf3f0eddeda1957a998491e36d7fb551e99be916))
16+
- Removed an extraneous `toolCallId` parameter from `ConversationItem.CreateSystemMessage()`. ([bf3f0ed](https://github.com/openai/openai-dotnet/commit/bf3f0eddeda1957a998491e36d7fb551e99be916))
17+
- OpenAI.Assistants:
18+
- Renamed `RunStepType` to `RunStepKind`. ([bf3f0ed](https://github.com/openai/openai-dotnet/commit/bf3f0eddeda1957a998491e36d7fb551e99be916))
19+
- Changed `RunStepKind` from an "extensible enum" to a regular enum. ([bf3f0ed](https://github.com/openai/openai-dotnet/commit/bf3f0eddeda1957a998491e36d7fb551e99be916))
20+
- Renamed the `ToolCallId` property of `RunStepToolCall` to `Id`. ([bf3f0ed](https://github.com/openai/openai-dotnet/commit/bf3f0eddeda1957a998491e36d7fb551e99be916))
21+
- Renamed the `ToolKind` property of `RunStepToolCall` to `Kind`. ([bf3f0ed](https://github.com/openai/openai-dotnet/commit/bf3f0eddeda1957a998491e36d7fb551e99be916))
22+
- Replaced the `FileSearchRanker` and `FileSearchScoreThreshold` properties of `RunStepToolCall` with a new `FileSearchRankingOptions` property that contains both values to make it clearer how they are related. ([bf3f0ed](https://github.com/openai/openai-dotnet/commit/bf3f0eddeda1957a998491e36d7fb551e99be916))
23+
24+
### Bugs fixed
25+
26+
- OpenAI.RealtimeConversation:
27+
- Fixed serialization issues with `ConversationItem` creation of system and assistant messages. ([bf3f0ed](https://github.com/openai/openai-dotnet/commit/bf3f0eddeda1957a998491e36d7fb551e99be916))
28+
- Fixed an issue causing a deadlock when calling the `RealtimeConversationSession`'s `SendInputAudio` method overload that takes a `BinaryData` parameter. ([f491c2d](https://github.com/openai/openai-dotnet/commit/f491c2d5a3894953e0bc112431ea3844a64496da))
29+
330
## 2.1.0-beta.2 (2024-11-04)
431

532
### Features added
633

7-
- Added a `StoredOutputEnabled` property to `ChatCompletionOptions` ([`store` in the REST API](https://platform.openai.com/docs/api-reference/chat/create#chat-create-store)). ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
8-
- Use this property to indicate whether or not to store the output of the chat completion for use in model distillation or evals.
9-
- Added a `Metadata` property to `ChatCompletionOptions` ([`metadata` in the REST API](https://platform.openai.com/docs/api-reference/chat/create#chat-create-metadata)). ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
10-
- Use this property to add custom tags and values to the chat completions for filtering in the OpenAI dashboard.
11-
- Added an `InputTokenDetails` property to `ChatTokenUsage` ([`usage.prompt_token_details` in the REST API](https://platform.openai.com/docs/api-reference/chat/object#chat/object-usage)). ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
12-
- The property is of a new type called `ChatInputTokenUsageDetails`, which contains properties for `AudioTokenCount` and `CachedTokenCount` for usage with supported models.
13-
- Added an `AudioTokenCount` property to `ChatOutputTokenUsageDetails` ([`usage.completion_token_details` in the REST API](https://platform.openai.com/docs/api-reference/chat/object#chat/object-usage)). Audio support in chat completions is coming soon. ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
14-
- Added `Illicit` and `IllicitViolent` properties `ModerationResult` to represent these two new moderation categories. ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
15-
- Made improvements to the experimental Realtime API. Please note this features area is currently under rapid development and not all changes may be reflected here. ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
16-
- Several types have been renamed for consistency and clarity.
17-
- `ConversationRateLimitsUpdate` (previously `ConversationRateLimitsUpdatedUpdate`) now includes named `RequestDetails` and `TokenDetails` properties, mapping to the corresponding named items in the underlying `rate_limits` command payload.
34+
- OpenAI.Chat:
35+
- Added a `StoredOutputEnabled` property to `ChatCompletionOptions` ([`store` in the REST API](https://platform.openai.com/docs/api-reference/chat/create#chat-create-store)). ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
36+
- Use this property to indicate whether or not to store the output of the chat completion for use in model distillation or evals.
37+
- Added a `Metadata` property to `ChatCompletionOptions` ([`metadata` in the REST API](https://platform.openai.com/docs/api-reference/chat/create#chat-create-metadata)). ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
38+
- Use this property to add custom tags and values to the chat completions for filtering in the OpenAI dashboard.
39+
- Added an `InputTokenDetails` property to `ChatTokenUsage` ([`usage.prompt_token_details` in the REST API](https://platform.openai.com/docs/api-reference/chat/object#chat/object-usage)). ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
40+
- The property is of a new type called `ChatInputTokenUsageDetails`, which contains properties for `AudioTokenCount` and `CachedTokenCount` for usage with supported models.
41+
- Added an `AudioTokenCount` property to `ChatOutputTokenUsageDetails` ([`usage.completion_token_details` in the REST API](https://platform.openai.com/docs/api-reference/chat/object#chat/object-usage)). Audio support in chat completions is coming soon. ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
42+
- OpenAI.Moderations:
43+
- Added `Illicit` and `IllicitViolent` properties `ModerationResult` to represent these two new moderation categories. ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
44+
45+
### Breaking Changes in Preview APIs
46+
47+
- OpenAI.RealtimeConversation:
48+
- Made improvements to the experimental Realtime API. Please note this features area is currently under rapid development and not all changes may be reflected here. ([b0f9e5c](https://github.com/openai/openai-dotnet/commit/b0f9e5c3b9708a802afa6ce7489636d2084e7d61))
49+
- Several types have been renamed for consistency and clarity.
50+
- `ConversationRateLimitsUpdate` (previously `ConversationRateLimitsUpdatedUpdate`) now includes named `RequestDetails` and `TokenDetails` properties, mapping to the corresponding named items in the underlying `rate_limits` command payload.
1851

1952
### Bugs Fixed
2053

21-
- Fixed serialization and deserialization of `ConversationToolChoice` literal values (such as `"required"`). ([9de3709](https://github.com/openai/openai-dotnet/commit/9de37095eaad6f1e2e87c201fd693ac1d9757142))
54+
- OpenAI.RealtimeConversation:
55+
- Fixed serialization and deserialization of `ConversationToolChoice` literal values (such as `"required"`). ([9de3709](https://github.com/openai/openai-dotnet/commit/9de37095eaad6f1e2e87c201fd693ac1d9757142))
2256

2357
### Other Changes
2458

@@ -27,9 +61,8 @@
2761

2862
## 2.1.0-beta.1 (2024-10-01)
2963

30-
With this updated preview library release, we're excited to bring early support for the newly-announced `/realtime` beta API. You can read more about `/realtime` here: https://openai.com/index/introducing-the-realtime-api/
31-
32-
Given the scope and recency of the feature area, the new `RealtimeConversationClient` is subject to substantial refinement and change over the coming weeks -- this release is purely intended to empower early development against `gpt-4o-realtime-preview` as quickly and efficiently as possible.
64+
> [!NOTE]
65+
> With this updated preview library release, we're excited to bring early support for the newly-announced `/realtime` beta API. You can read more about `/realtime` here: https://openai.com/index/introducing-the-realtime-api/. Given the scope and recency of the feature area, the new `RealtimeConversationClient` is subject to substantial refinement and change over the coming weeks -- this release is purely intended to empower early development against `gpt-4o-realtime-preview` as quickly and efficiently as possible.
3366
3467
### Features Added
3568

0 commit comments

Comments
 (0)