Hey @094459 and thanks for the request. Our general policy (we haven't written it down 🥲 ) is that we won't accept any components that require additional infrastructure to run. Packages installable from PyPI or secrets in the form of environment variables are fine.

That being said, we of course recognize the need for services that require additional infrastructure. This is why we build Ragna to be fully extensible. I acknowledge that it is abysmally documented right now. Just subclass SourceStorage and Assistant and implement whatever you like. As long as it adheres to the signatures of the abstract methods, it will work with Ragna.

For the Python API, you can pass your classes directly to the chat. Have a look at this notebook: https://github.com/Quansight/ragna/blob/main/examples/local_llm/local_llm.ipynb

For the REST API and UI, you need to add them to the source_storages = and assistants = list in the configuration. For example

[core]
# ...
source_storages = [
    "ragna.source_storages.RagnaDemoSourceStorage",
    "my_ragna_plugin.MySourceStorage",
]
assistants = [
    "ragna.assistants.RagnaDemoAssistant",
    "my_ragna_plugin.MyAssistant",
]

Make sure that that the my_ragna_plugin.py Python module is on the PYTHONPATH when starting the API / UI. Just as heads up: to meet the deadline, we hardcoded some assumptions about the source storages in the UI. This will be cleaned up for the next release, but might conflict with your custom classes for now.

It is only the additional assistant I was looking to add, specifically Amazon Bedrock's Anthropic Claude v2. I will take a look at the info and see what I can figure out. Thanks for the response.

#173

Closing this following the discussion in #173.