Skip to content
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

Ollama and litellm integration #1015

Closed

Conversation

definitiontv
Copy link

This is just an additional docker compose file with support files and some notes in the Docker readme.
This introduces an optional compose file which uses Ollama and litellm to handle all model management
The ollama section is running the official ollama/ollama docker image - note it seems to be 4 months old as of this post, so we need to keep an eye on it.

The litellm docker image is currently also out of date as of this image and also does not have ARM support
For this reason I have created a seperate docker file which creates a container form the published python binaries

The gpt-engineer container is built in the same way as the original

review the .env files and the dc.yml compose file for the environmnt variables that are required
Especially note that you can uncomment the ports sections to make these services available on your local machine or remotely. Be careful about security though. Hackers seem to be stealing free inference endppoints.

A few Comments have been left in to show alternate formulations, you can secure litellm using keys see their documentation

@viborc
Copy link
Collaborator

viborc commented Feb 23, 2024

We are closing this PR since this is adding an extra overhead with Docker. Also, this solution relies on ollama and lite-llm and we decided to avoid it

I am providing this link as an additional context, and @zigabrencic's discussion about lite-llm BerriAI/litellm#2001

@viborc viborc closed this Feb 23, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants