Skip to content

Releases: 64bit/async-openai

v0.16.2

10 Nov 00:23
async-openai-v0.16.2
15838b5
Compare
Choose a tag to compare

New

  • bug fix: expires_at needs to be Optional in RunObject #141
  • spec update: Added system_fingerprint field to CreateChatCompletionStreamResponse; updates to few doc comments #142

New Contributors

v0.16.1

08 Nov 16:58
async-openai-v0.16.1
83d4128
Compare
Choose a tag to compare

New

  • bug fix: Add missing pub modifiers from couple of struct fields #139 #137

v0.16.0

07 Nov 21:33
async-openai-v0.16.0
bc79fcf
Compare
Choose a tag to compare

New

  • added: Text to speech API #130 by @m1guelpf
  • updated: Crate is updated to new spec released on DevDay #131

Notes about this release:

  • Most of the existing examples/* are tested.
  • Assistants and related API are least tested.
  • Please do send a PR if you find any issues.

Thank you

Many thanks to contributor @m1guelpf

v0.15.0

30 Oct 06:55
async-openai-v0.15.0
50019ca
Compare
Choose a tag to compare

New

  • added : Use secrecy crate to store api_key : Secret<String> in configs #114 by @ironman5366
  • added: Derive Copy for enums: ImageSize, ResponseFormat, TextModerationModel, Role, and AudioResponseFormat #117 by @m1guelpf
  • added: Expose config getter in Client #123 by @Czechh
  • updated: Enum type for finish_reason to match latest spec for chat completions API #111 by @retrage
  • updated: ChatCompletionFunctionCall enum for better DX #118 by @m1guelpf

Updates from latest upstream spec 2.0.0

Chat & Completion:

  • use enums FinishReason & CompletionFinishReason for finish_reason instead of String
  • Rename struct Usage to CompletionUsage

Embeddings:

  • Add field encoding_format in CreateEmbeddingRequest

Files:

  • Update status_detail field type in OpenAIFile from object to String

Images:

  • Rename ImageData to Image to match spec
  • Rename ImageResponse to ImagesResponse to match spec

Moderations:

  • Add new fields in moderation request and response types.

Fine Tuning

  • Add new Fine Tuning APIs

Fine Tunes & Edit

  • Mark Edit and FineTunes to be deprecated

Doc comments

  • Update doc comments to match latest spec

Thank you

Thank you to the contributors (@m1guelpf , @Czechh ) and first time (@ironman5366 , @retrage ) contributors! 🎉

v0.14.3

24 Sep 22:41
async-openai-v0.14.3
3db68af
Compare
Choose a tag to compare

New

  • updated: Custom Debug implementation for AzureConfig and OpenAIConfig to prevent printing of API key #112

New Contributors

v0.14.2

15 Sep 01:08
async-openai-v0.14.2
20e55fb
Compare
Choose a tag to compare

New

  • added: derive Deserialize for OpenAIConfig and AzureConfig to read configurations from files #107 #108

New Contributors

v0.14.1

08 Sep 23:21
async-openai-v0.14.1
f9bf345
Compare
Choose a tag to compare

New

  • fixed: Propogate error up on failure to create reqwest::Request
  • fixed: Serialize "content": null as required by chat completion API: #103

v0.14.0

23 Aug 12:15
async-openai-v0.14.0
3776935
Compare
Choose a tag to compare

New

This release makes all multipart form submissions (file uploads) retry on rate limit. #100
There are no breaking changes.
The minor version was bumped because of internal refactor to support file upload retries.

v0.13.1

17 Aug 14:09
async-openai-v0.13.1
db03584
Compare
Choose a tag to compare

New

  • fixed : Bug fix to handle function call streaming #98

Example Updated

  • examples/function-call-stream is now fully streamable #98

New Contributors

v0.13.0

08 Aug 21:51
async-openai-v0.13.0
263eb70
Compare
Choose a tag to compare

New

Breaking changes

  • updated: Chat streaming response types now reflect the OpenAPI spec #92
    • ChatCompletionResponseStreamMessage is now ChatCompletionStreamResponseDelta
    • ChatChoiceDelta is now ChatCompletionResponseStreamMessage
  • fixed: r#type field of ApiError is changed from String to Option<String> to support Azure OpenAI service error spec #95

New Examples

New Contributors