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

Read model name from agent config in Gemini and Ollama APIs. #447

Merged
merged 4 commits into from
Feb 12, 2025

Conversation

mkbehr
Copy link
Collaborator

@mkbehr mkbehr commented Feb 7, 2025

This also removes the llmType field in the Ollama API config.

Depends on #445.

@mkbehr
Copy link
Collaborator Author

mkbehr commented Feb 7, 2025

@vivtsai, are there any extra changes needed to make migration work from old data with the Ollama config's llmType field set?

@dimits-ts
Copy link
Collaborator

@vivtsai, are there any extra changes needed to make migration work from old data with the Ollama config's llmType field set?

Testing the Ollama server is pretty easy, you can have it up and running with two commands. Only commenting this because the way I recommended previously no longer works!

Also freezing development of #433 until this get merged, since it will most likely need a refactor of all models.

@vivtsai
Copy link
Collaborator

vivtsai commented Feb 12, 2025

@vivtsai, are there any extra changes needed to make migration work from old data with the Ollama config's llmType field set?

Thanks for flagging! No, this looks good (the only case where I'm looking at migration is when a new field is added, since that will prevent existing (stored in Firebase) objects from being properly typecast.

@mkbehr mkbehr merged commit 4b91e39 into PAIR-code:main Feb 12, 2025
1 check passed
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.

3 participants