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.

Sign up for GitHub

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

Jump to bottom

ollama embedding with Base API URL ignored #1004

Open
sqlreport opened this issue Sep 19, 2024 · 2 comments
Open

ollama embedding with Base API URL ignored #1004

sqlreport opened this issue Sep 19, 2024 · 2 comments
Labels
bug Something isn't working

Comments

@sqlreport
Copy link

  • jupyter-ai: 2.23.0
  • ollama3.1 working without issue
  • mxbai-embed-large curl on jupyter terminal working without issue

When running /learn command, I am seeing that jupyter ai chat UI calling using localhost instead of specific base api url configured.

HTTPConnectionPool(host='localhost', port=11434): Max retries exceeded with url: /api/embeddings
@sqlreport sqlreport added the bug Something isn't working label Sep 19, 2024
@sqlreport sqlreport mentioned this issue Sep 19, 2024
Closed
@sqlreport
Copy link
Author

This happens when we call /learn command in chat UI. So it seems to be related to embedding model call.

@sqlreport
Copy link
Author

looks like ollama embedding doesn't allow base url to be changed.
langchain-ai/langchain#25022

sqlreport added a commit to sqlreport/jupyter-ai that referenced this issue Sep 20, 2024
@sqlreport
Allow overriding the Ollama base URL
69bf1c0 
jupyterlab#1004
This allows overriding Ollama base URL when using embeddings model.
This was referenced Sep 20, 2024
Closed
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
bug Something isn't working
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@sqlreport