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

[Feature]: auto-populate and allow overriding of selected provider in litellm_model name #8398

Open
krrishdholakia opened this issue Feb 8, 2025 · 0 comments
Labels
enhancement New feature or request feb 2025 ui

Comments

@krrishdholakia
Copy link
Contributor

krrishdholakia commented Feb 8, 2025

The Feature

my life would be a lot easier if it auto-populated the litellm model name with the provider/, based on what i selected, so i know what it picked and can override it if necessary

so in the case below, it would show me in litellm model name - openai/ and then allow me to override it, to be deepseek/

then in the api request, either the custom_llm_provider is not passed in (the ui currently sends this on /model/new) or update to send the correct one based on what i set

Motivation, pitch

Image

adding a model is really confusing me right now.
i'm trying to update the existing provider for a model, and it looks like when i select a provider on add model that gets sent along with the litellm model name
so in my head i'm finding it hard to construct what the actual litellm model name + custom_llm_provider used is - is it openai/openai/deepseek_chat or is it openai/deepseek_chat

Are you a ML Ops Team?

No

Twitter / LinkedIn details

No response

@krrishdholakia krrishdholakia added enhancement New feature or request ui feb 2025 labels Feb 8, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request feb 2025 ui
Projects
None yet
Development

No branches or pull requests

1 participant