Skip to content

Latest commit

 

History

History
147 lines (110 loc) · 5.65 KB

CHANGELOG.md

File metadata and controls

147 lines (110 loc) · 5.65 KB
Raw

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog and this project adheres to Semantic Versioning.

v0.7.3 (2023-09-08)

Added

  • Add "has_more" to fine-tuning jobs and events list responses (#206)

Changed

  • Add parameters to the fine-tuning jobs list request to filter the results (#206)

Fixed

  • error_code may be int

v0.7.2 (2023-08-31)

Fixed

  • Missing openai-version header from Azure

v0.7.1 (2023-08-29)

Fixed

  • Typo in class name MetaInformationOpenAI

v0.7.0 (2023-08-29)

Added

  • Add support for the fine-tuning API (#199)
  • Provide access to header / meta information for all responses (#195)

Changed

  • Mark FineTunes resource as deprecated
  • Mark Edits resource as deprecated
  • Add missing moderation enums (#178)

Fixed

  • Chat completion create response with function calling on Azure (#184)
  • Breaking change on OpenAI API regarding "transient" field in Audio translations (#168)
  • Docs: fix OpenAI URL

v0.6.3 (2023-07-07)

Fixed

  • Breaking change on OpenAI API regarding "transient" field in Audio (#160)

v0.6.2 (2023-06-23)

Changed

  • Error handling: use error code as exception message if error message is empty (#150)

Fixed

  • Error handling: Catch error in stream responses (#150)
  • Error handling: Handle errors where message is an array (#150)

v0.6.1 (2023-06-15)

Fixed

  • Chat/CreateResponse faking with function_call (#145)

v0.6.0 (2023-06-14)

Added

  • Add support for function calling in the Chat Completions API (#144)

v0.5.3 (2023-06-07)

Fixed

  • Exception handling for server error with non default content type header (#134)
  • Faking embedding responses for multidimensional vectors (#131)

v0.5.2 (2023-05-27)

Added

  • Add support for psr/http-message ^2.0 (#130)

v0.5.1 (2023-05-24)

Fixed

  • fix: stream broken after checking for errors (regression of #113)

v0.5.0 (2023-05-24)

Added

  • Support for HTTP base uri (#106)

Changed

  • unify exception handling between HTTP client implementations (#113)

Fixed

  • fix toArray() on CreateStreamedResponseDelta to match the original API response (#108)

Docs

  • explain usage for "OpenAI on Azure" (#109)

v0.4.2 (2023-04-12)

Added

  • Testing support (#71)

Changed

  • Trim ApiKey before sending it to the API (#101)

Fixed

  • Nullable fields on error response (#102)

v0.4.1 (2023-03-24)

Added

  • Stream suppport (#84)

v0.4.0 (2023-03-17)

Changed

  • Removed dependency for guzzlehttp/guzzle and use PSR-18 client discovery instead (#75)
  • Add Client factory which allows for a custom HTTP client
  • Client factory further accepts custom HTTP headers, query parameters and API URI

v0.3.5 (2023-03-08)

Fixed

  • status_details can be a string in file responses. Affects Files and FineTunes resources (#68)

v0.3.4 (2023-03-03)

Added

  • Audio resource to turn audio into text powered by whisper-1 (#62)

v0.3.3 (2023-03-02)

Added

  • Chat resource aka ChatGPT powered by gpt-3.5-turbo (#60)

v0.3.2 (2023-02-28)

Fixed

  • Nullable finish_reason on Completions CreateResponse (#52, 545e0ab)

v0.3.1 (2023-02-07)

Fixed

  • Missing events on FineTunes RetrieveResponse (#41)

v0.3.0 (2023-01-03)

Changed

  • OpenAI::client() first argument changed from apiToken to apiKey (#25)

Fixed

  • Getting contents from Guzzle's response causing issues with middleware (#33)

v0.2.1 (2022-11-09)

Fixed

  • FineTunes create response: batch_size, learning_rate and fine_tuned_model are nullable (#16)
  • File responses: add missing fields status and status_details

v0.2.0 (2022-11-07)

Added

  • Add images() resource to interact with DALL-E

Fixed

  • Parse completions create response with logprobs correctly

v0.1.0 (2022-10-20)

Added

  • First version