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

Muxing rule errors with Ollama #1178

Closed
danbarr opened this issue Mar 1, 2025 · 1 comment · Fixed by stacklok/codegate-ui#360
Closed

Muxing rule errors with Ollama #1178

danbarr opened this issue Mar 1, 2025 · 1 comment · Fixed by stacklok/codegate-ui#360

Comments

@danbarr
Copy link
Contributor

danbarr commented Mar 1, 2025

Describe the issue

Trying to save the muxing rules for a workspace that had previously been set to an Ollama model, I get an error in v0.1.25:

Model qwen2.5-coder does not exist for provider 6bb9d2d0-57df-4925-9878-8b4287f45a2a

I've tried deleting and re-adding the ollama provider. The available models are successfully loaded in the drop-down, but when I select one and save I get the above error. It seems the :version part of the model name is being dropped, for example I don't see the :1.5b in the input box once I select it and it's not there in the error message.

Other providers are working (I tested OpenAI, OpenRouter, and LM Studio)

Steps to Reproduce

Configure an Ollama provider. Try to select one of the models from that provider in a workspace muxing rule. Try to save the muxing rules.

Operating System

MacOS (Arm)

IDE and Version

NA

Extension and Version

NA

Provider

Ollama

Model

All

Codegate version

v0.1.25

Logs

No response

Additional Context

No response

@aponcedeleonch
Copy link
Contributor

This will be fixed in stacklok/codegate-ui#360

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants