mirror of
https://gh.wpcy.net/https://github.com/presswizards/FreeScoutGPT.git
synced 2026-07-15 04:11:15 +08:00
4.2 KiB
4.2 KiB
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.
1.4.0 - 2023-03-02
Added
- Add support for the new ChatGPT API, including
gpt-3.5-turbomodel and the new Chat completions endpoint. Chat completions guide. - Add support for the new Whisper API, allowing Transcriptions and Translations, accepting a variety of formats (
m4a,mp3,mp4,mpeg,mpga,wav,webm). Speech to text guide. - Add new
AudioTranscriptionsHandler, which transcribes audio into the input language text using the Whisper API. - Add new
AudioTranslationsHandler, which transcribes audio into english text using the Whisper API. - Add new
ChatCompletionsHandler, which creates a completion for one or more chat messages using the ChatGPT API.
Changed
- Clarify which models can be used in
\Tectalic\OpenAi\Models\Edits\CreateRequest::$modelwhen performing Edits. - Clarify that
\Tectalic\OpenAi\Models\Embeddings\CreateRequest:$inputcan be a maximum of 8192 tokens (not 2048 tokens). - Clarify that
\Tectalic\OpenAi\Models\ImagesEdits\CreateImageRequest::$maskis no longer a required field. - API version updated from 1.1.0 to 1.2.0.
1.3.1 - 2023-02-23
Added
- Add support for PHPUnit v9.6.x and v10.x.
Changed
- Remove
idandmodelrequired properties from theTectalic\OpenAi\Models\Edits\CreateResponsemodel, as they are no longer returned by OpenAI's API. - Improve compatibility with the
php-http/discoverypackage v1.15.0 and newer. - Use Fully Qualified Class Names for Examples in Readme.
- Update Copyright year.
Fixed
- Fix
Response body parse failederror when retrieving a Model response from theEdits::create()handler and method. - Fix incorrect Error handling example in Readme.
1.3.0 - 2022-12-21
Added
- Use parameters defined outside endpoint methods.
Changed
- Encourage the use of
php-http/mock-clientfor testing and mocking API responses. - Remove the
Tests\MockHttpClientclass, and use thephp-http/mock-clientpackage instead. - Make Handler and Model class names more readable.
Fixed
- Use correct model type for nested models.
1.2.0 - 2022-11-07
Added
- Add support for DALL·E image generation.
- Add new
ImageGenerationsHandler, which creates an image given a prompt. - Add new
ImagesEditsHandler, which creates an edited or extended image given an original image and a prompt. - Add new
ImagesVariationsHandler, which creates a variation of a given image.
Changed
- Improve Handler unit tests.
- API version updated from 1.0.6 to 1.1.0.
1.1.0 - 2022-10-31
Changed
- Improve readme.
Removed
- Remove deprecated
Answershandler and associated models. - Remove deprecated
Classificationshandler and associated models. - Remove deprecated
Engineshandler and associated models. - Remove deprecated
EnginesSearchhandler and associated models.
1.0.2 - 2022-10-28
Changed
- Switch License.
1.0.1 - 2022-10-24
Added
- Add support for Moderation using a new
Moderations::create()Handler class and Method. - Add usage information to response models:
Completions::create(),Edits::create()andEmbeddings::create().
Changed
- Define required properties for response models.
- Rename all nested response models.
- Change default value for
Tectalic\OpenAi\Models\FineTunes\CreateRequest::$prompt_loss_weight. - 22 API Methods are now supported, grouped into 14 API Handlers.
- API version updated from 1.0.5 to 1.0.6.
Fixed
- Don't run CI for tags.
- Use correct model type for nested models:
Tectalic\OpenAi\Models\FineTunes\CreateResponse,Tectalic\OpenAi\Models\FineTunes\RetrieveResponseandTectalic\OpenAi\Models\FineTunesCancel\CancelFineTuneResponse.
1.0.0 - 2022-07-11
Added
- Initial release.