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.
- Adjust rich text loading indicator to look correct in newer versions of Wagtail
- Remove top-level
versioned_static
calls
- Automatic alt-text generation for images (experimental) (Alex Morega)
- 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)
- Made
llm
a required dependency to simplify the installation process
- 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)
- 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)
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.
- @tm-kn - AI backends/text splitting restructure
- @zerolabl - support with developer tooling
- @Morsey187 - frontend refinements and admin prompt management
- @ianmeigh - improvements to admin integration
- Support for customising prompts using the
WAGTAIL_AI_PROMPTS
setting
- 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
- @tomdyson for readme improvements, feature suggestions and a great demo in What's New in Wagtail
- Fixes an issue with 'completion' where it would throw a JS error trying to insert a new line.
- Wagtail AI has appeared!