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

updated oobabooga to new api and support for embeddings #1248

Merged
merged 1 commit into from
Dec 27, 2023

Conversation

danikhan632
Copy link

the current implementation uses the old api which has now been deprecated and the openai interface is the default one any my fork adjusts completions function for that.

Additionally it also implements the embeddings function for oobabooga

Copy link

vercel bot commented Dec 27, 2023

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
litellm ✅ Ready (Inspect) Visit Preview 💬 Add feedback Dec 27, 2023 0:50am

@krrishdholakia
Copy link
Contributor

LGTM! @danikhan632 why are you using litellm with oobabooga? It's already openai-compatible

@danikhan632
Copy link
Author

LGTM! @danikhan632 why are you using litellm with oobabooga? It's already openai-compatible

I may have told you about this a while ago however I suppose I did it to make it easier as I am currently working on adding function calling support using guidance and I wanted to also be able to use it with oobabooga.

def function_call_prompt(messages: list, functions: list):
#todo: use guidance to implement this function

@krrishdholakia
Copy link
Contributor

And since oobabooga doesn't support function calling, you're trying to use litellm to do that?

so is it
guidance -> litellm -> oobabooga?

@danikhan632
Copy link
Author

And since oobabooga doesn't support function calling, you're trying to use litellm to do that?

so is it guidance -> litellm -> oobabooga?

I suppose so but not just oobabooga but also all the other models

see #1258 as I have already pushed semi working implementation that uses LlamaCpp as of now but is a work in progress

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

Successfully merging this pull request may close these issues.

2 participants