Skip to content

Conversation

krrishdholakia
Copy link

@krrishdholakia krrishdholakia commented Oct 4, 2023

Hi @rajivpoddar @prthkms

Noticed you're calling the openai chat completions endpoint. I'm working on litellm (simple library to standardize LLM API Calls - https://github.com/BerriAI/litellm) and wanted to see how i could be helpful.

My PR adds support for new LLM providers (anthropic, aws bedrock, azure openai, replicate, ai21, etc.) by replacing ChatOpenai with ChatLitellm.

Curious if you find this useful?

Happy to add additional tests/documentation if the initial PR looks good.

@rajivpoddar
Copy link

Thanks @krrishdholakia.

Does LiteLLM have support for grammars? The issue we have faced with other LLMs is that it does not respond back in JSON. It would be quite useful to have llama.cpp style GBNF grammars.

@krrishdholakia
Copy link
Author

Interesting - is there a known way of applying grammars to openai/hosted models? @rajivpoddar

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