Releases: 64bit/async-openai
v0.17.1
New
- fixed: Fix: Make ChatCompletionToolChoiceOption enum variants lowercase #158 by @dmweis
- fixed: Issue reported in #140 is fixed including tests in #157 by @katya4oyu
Thank you Contributors
- @dmweis 🎉
- @katya4oyu made their first contribution 🎉
v0.17.0
Overview
This release introduces breaking change for file input (from filesystem or in-memory) but is backward compatible, hence bumping the minor version.
New
- fixed: added optional name field to chat completion request message structs for chat completion APIs #150 by @ifsheldon
- added support for file uploads (audio, image, files for fine tuning) from in-memory #154 by @prosammer
Experimental WASM support
@ifsheldon's great effort has added WASM support, it lives in experiments branch. To use it please pin directly to git sha in your Cargo.toml. Any discussion, issues, related to WASM are welcome in #102 . Any WASM related PRs are welcome in experiments
branch.
New Examples
- Assistant Example #145 by @Strange-Knoll
- Tool Call and Tool Call with Stream examples #153 by @frankfralick
Thank you contributors
While OpenAI was going through unprecedented times, these people were shipping! so in OpenAI style:
❤️ 💙 💛 💚 ❤️ 💙 💛
@ifsheldon
@Strange-Knoll
@frankfralick
@prosammer
❤️ 💙 💛 💚 ❤️ 💙 💛
v0.16.3
v0.16.2
v0.16.1
v0.16.0
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
New
- added : Use
secrecy
crate to storeapi_key : Secret<String>
in configs #114 by @ironman5366 - added: Derive
Copy
for enums:ImageSize
,ResponseFormat
,TextModerationModel
,Role
, andAudioResponseFormat
#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
forfinish_reason
instead ofString
- Rename struct
Usage
toCompletionUsage
Embeddings:
- Add field
encoding_format
inCreateEmbeddingRequest
Files:
- Update
status_detail
field type inOpenAIFile
from object toString
Images:
- Rename
ImageData
toImage
to match spec - Rename
ImageResponse
toImagesResponse
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
andFineTunes
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
New
- updated: Custom
Debug
implementation forAzureConfig
andOpenAIConfig
to prevent printing of API key #112
New Contributors
- @Emilgardis made their first contribution in #112 🎉