Skip to content

Conversation

@brichet
Copy link
Contributor

@brichet brichet commented Nov 4, 2025

This PR fixes the model of the agent, which is not properly setup because of a typo in the ChatLiteLLM attribute.

Context

I think that the correct parameter should be model=model_id (model instead of model_id), according to the ChatLiteLLM attribute.

When testing this PR, the backend is complaining about missing OpenAi API key. Trying to debug it, it seems that the model setup in ChatLiteLLM is always the default one, gpt-3.5-turbo.

Originally posted by @brichet in #17 (comment)

cc. @3coins @dlqqq

@brichet brichet changed the title Fix the agent model by providing the right attribute to the ChatLiteLLM Fix the agent model by providing the correct attribute to the ChatLiteLLM Nov 4, 2025
@3coins 3coins added the bug Something isn't working label Nov 5, 2025
Copy link
Contributor

@3coins 3coins left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@brichet
Thanks for catching this. Looks good!

@dlqqq
Copy link
Contributor

dlqqq commented Nov 5, 2025

TYSM for catching this!

@3coins 3coins merged commit a9ab819 into jupyter-ai-contrib:main Nov 5, 2025
5 of 8 checks passed
@brichet brichet deleted the fix_agent_model branch November 6, 2025 07:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug Something isn't working

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants