New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Support for Google Gemini OOTB #1405
Comments
It is doable now, but I find I have to add an extra step to it, after you set up the custom LLM for Gemini, and as long as the docker containers are running, you then have to run the following two commands (assuming you're using docker for this): docker exec -it danswer-stack-api_server-1 pip install -q google-generativeai You'll have to run them everytime you restart Danswer. If you're running from source then you can just run the "pip install googe-generativeai" command locally and you should be good to go. But agreed, it would be nice to not have to do that and just have Gemini "work" right out of box. I've been using Gemini 1.5 pro mostly, lately, and it's does seem to do a pretty decent job (and it doesn't hurt that it's free for the moment! :D) |
LiteLLM already support Gemini so it's probably already doable. Would be nice to support it OOTB as Gemini has a large context window
The text was updated successfully, but these errors were encountered: