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

Model list update dynamically #1736

Open
ran-haim opened this issue Feb 27, 2025 · 2 comments
Open

Model list update dynamically #1736

ran-haim opened this issue Feb 27, 2025 · 2 comments
Labels
back This issue is related to the Svelte backend or the DB enhancement New feature or request models This issue is related to model performance/reliability

Comments

@ran-haim
Copy link

The ability to refresh the model list dynamically without the need of restarting the chat-ui pod.
maybe listen to a conf file, and if it changes the models list will update - it will need to be in a common volume (if there are multiple instances).
A better way would be to grab it from /v1/models from a URL user provides on deployment.

@ran-haim ran-haim added the enhancement New feature or request label Feb 27, 2025
@nsarrazin
Copy link
Collaborator

I think we could maybe support an alternative MODELS_URL instead of MODELS, not sure if there would be enough info there to generate the list of models but could be a nice feature if that was the case. Would that suit you?

We need to look deeper to see if there are some unforeseen issues when doing this... I would love to hear from others if this is a feature you would like to see, in order to know how to prioritize this 😄

@nsarrazin nsarrazin added back This issue is related to the Svelte backend or the DB models This issue is related to model performance/reliability labels Feb 27, 2025
@ran-haim
Copy link
Author

I actually wouldn't mind implementing a models_list endpoint that will return the format that is currently used in the MODELS env variable.

from the user point of view, I think it should work basically like it is done in openwebui - though there it is more coupled with ollama.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
back This issue is related to the Svelte backend or the DB enhancement New feature or request models This issue is related to model performance/reliability
Projects
None yet
Development

No branches or pull requests

2 participants