Wagtail Vector Index

Wagtail Vector Index provides a way to turn Django models, Wagtail pages, and anything else in to embeddings which are stored in a one of multiple vector database backends.

This provides the backbone for features including:

• Natural language search
• Similarity search
• Content recommendations

Links

• Documentation
• Changelog
• Contributing
• Discussions
• Security

Supported Versions

• Wagtail 5.2
• Django 4.2
• Python 3.11, 3.12

Contributing

Install

To make changes to this project, first clone this repository:

git clone https://github.com/wagtail/wagtail-vector-index.git
cd wagtail-vector-index

With your preferred virtualenv activated, install testing dependencies:

Using pip

python -m pip install --upgrade pip>=21.3
python -m pip install -e .'[testing,llm,numpy,pgvector,qdrant,weaviate]' -U

Using flit

python -m pip install flit
python -m flit install -s

pre-commit

Note that this project uses pre-commit. It is included in the project testing requirements. To set up locally:

# go to the project directory
$ cd wagtail-vector-index
# initialize pre-commit
$ pre-commit install

# Optional, run all checks once for this, then the checks will run only on the changed files
$ git ls-files --others --cached --exclude-standard | xargs pre-commit run --files

How to run tests

Now you can run tests as shown below:

tox

or, you can run them for a specific environment tox -e py3.11-django4.2-wagtail5.2 or specific test tox -e py3.11-django4.2-wagtail5.2 -- tests.test_file.TestClass.test_method

Sometimes tox contains cached dependencies, so if you want to run tests with the latest dependencies, you can use tox -r or run rm -rf .tox to delete the whole tox environment.

To run the test app interactively, use tox -e interactive, visit http://127.0.0.1:8020/admin/ and log in with admin/changeme.