-
-
Notifications
You must be signed in to change notification settings - Fork 4.7k
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
feat: configurable model name, description and vision capability #2140
Conversation
About time we make |
Also, it would be perfect if we could rename the fields like such:
|
Done the field rename, and also added settings UI for updating the model info. |
It is so unbelievable. I've been waiting for a long time! @cheahjs i admire you so much!!!🤩🤩🤩 |
This is epic. I am assuming we can extend this (in a separate PR) to configure per-model context window, output tokens, etc. |
On second thought, we might want to save the model configs to our database to cover #665 as well. I'll keep this open in case I change my mind. I appreciate the effort as always 🙌 |
c624800
to
715a4a6
Compare
Was this removed or finally not merged to master? It is a very useful feature but I don't see this functionality in the latest releases. |
Thanks! So it is in "Workspace" I was looking in "Settings" (I think original MR put it there but it has moved since then). Thanks :) |
Pull Request Checklist
dev
branch.Description
Adds the ability to set a custom display name, description, and the vision capability of a model via the web UI, which is then persisted into the database.
A new field
custom_info
is injected into each model list API. An alternative implementation would be to override the model'sname
field, but would require additional mapping inside of the proxy endpoints.If a model is marked as not vision capable,
I've tested locally with Ollama and OpenAI endpoints, have not tested LiteLLM endpoints yet.
Changelog
Added