Wagtail AI 2.1.2

This minor-releases fixes how the 'loading' indicator renders on newer versions of Wagtail

What's Changed

• Fix loading indicator in newer versions of Wagtail by @tomusher

Full Changelog: v2.1.1...v2.1.2

Wagtail AI 2.1.1

This minor-releases fixes an issue when running collectstatic.

What's Changed

• Avoid top-level versioned_static calls by @tomkins in #89

New Contributors

• @tomkins made their first contribution in #89

Full Changelog: v2.1.0...v2.1.1

Wagtail AI 2.1.0

With Wagtail AI 2.1.0 we're experimenting with introducing AI features to more areas of the Wagtail interface, in particular; image uploads with automatic alt-tag generation.

This feature is experimental and is currently only supported when using OpenAI as a provider - we intend to expand support for this feature to more backends soon. See the Images Integration documentation for details on how to enable this feature.

Screen.Recording.2024-03-08.at.17.07.18.mov

Added

• Automatic alt-text generation for images (experimental) (Alex Morega)

Fixed

• Add a default_auto_field to avoid creation of extra migration (Stefan Hammer)
• Documentation fixes (Kyle Bayliss)
• Improvements to pricing calculations in README (Fauzaan Gasim)

New contributors/thanks

• @mgax
• @fauzaanu
• @kbayliss
• @th3hamm0r

Wagtail AI 2.0.1

Our first major version increase for Wagtail AI is out! For this release we've focused on improving the developer experience, making the user interface more resilient, and adding support for loads more LLMs.

Added

• New setting for specifying AI backends, with a new default backend using llm (Tomasz Knapik)
• Support for many different LLMs such as GPT-4, local models, Mistral and Claude using llm plugins (Tomasz Knapik)
• Customisable text splitting backends (Tomasz Knapik)
• More complete documentation (Tomasz Knapik)
• Custom prompts can now be managed through Wagtail admin (Ben Morse)

Changed

• Removed Langchain dependency. Text splitting is now customisable and defaults to a vendorised version of Langchain's text splitter. (Tomasz Knapik)
• Various developer experience improvements. (Tomasz Knapik, Dan Braghis)
• Minimum supported versions increased to Wagtail 5.2, Django 4.2 and Python 3.11 (Dan Braghis)
• Improved how prompts are passed to the admin (Ian Meigh)

Upgrade Considerations

Prompts managed in Wagtail admin

The WAGTAIL_AI_PROMPTS setting is no longer used. Prompts are now managed through the Wagtail admin under Settings -> Prompts.

Any custom prompts should be migrated to this new model, the WAGTAIL_AI_PROMPTS setting can then be removed.

See the installation documentation for the new configuration options, and the backend customisation documentation for further customisation options.

New Contributors/Thanks

• @tm-kn - AI backends/text splitting restructure
• @zerolab - support with developer tooling
• @Morsey187 - frontend refinements and admin prompt management
• @ianmeigh - improvements to admin integration

2.0.1

Changed

• Made llm a required dependency to simplify the installation process

Wagtail AI 2.0.0

Our first major version increase for Wagtail AI is out! For this release we've focused on improving the developer experience, making the user interface more resilient, and adding support for loads more LLMs.

Added

• New setting for specifying AI backends, with a new default backend using llm (Tomasz Knapik)
• Support for many different LLMs such as GPT-4, local models, Mistral and Claude using llm plugins` (Tomasz Knapik)
• Customisable text splitting backends (Tomasz Knapik)
• More complete documentation (Tomasz Knapik)
• Custom prompts can now be managed through Wagtail admin (Ben Morse)

Changed

• Removed Langchain dependency. Text splitting is now customisable and defaults to a vendorised version of Langchain's text splitter. (Tomasz Knapik)
• Various developer experience improvements. (Tomasz Knapik, Dan Braghis)
• Minimum supported versions increased to Wagtail 5.2, Django 4.2 and Python 3.11 (Dan Braghis)
• Improved how prompts are passed to the admin (Ian Meigh)

Upgrade Considerations

Prompts managed in Wagtail admin

The WAGTAIL_AI_PROMPTS setting is no longer used. Prompts are now managed through the Wagtail admin under Settings -> Prompts.

Any custom prompts should be migrated to this new model, the WAGTAIL_AI_PROMPTS setting can then be removed.

New Contributors/Thanks

• @tm-kn - AI backends/text splitting restructure
• @zerolab - support with developer tooling
• @Morsey187 - frontend refinements and admin prompt management
• @ianmeigh - improvements to admin integration

Wagtail AI 1.1.1

Changed

The URL used by the rich text editor button is now dynamically populated, fixing the issue where it would break if the admin URL had been changed.

Wagtail AI 1.1.0

Added

• Support for customising prompts using the WAGTAIL_AI_PROMPTS setting

Changed

• Content is now split based on token length before being sent to the API
• Significantly reduced bundle size (now using Draftail and Draft.js from Wagtail)
• Added better loading/error handling indicators

New Contributors/Thanks

• @tomdyson for readme improvements, feature suggestions and a great demo in What's New in Wagtail

Wagtail AI v1.0.1

🔧 Fixes a bug when running completions

Wagtail AI v1.0.0

Initial release!