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

Improve LiteLLM docs #397

Merged
merged 2 commits into from
Feb 4, 2025
Merged

Improve LiteLLM docs #397

merged 2 commits into from
Feb 4, 2025

Conversation

JamesGuthrie
Copy link
Member

@JamesGuthrie JamesGuthrie commented Jan 24, 2025

  • document ai.litellm_embed()
  • clarify huggingface vectorizer

@jackyliang
Copy link
Contributor

jackyliang commented Feb 3, 2025

I see openai used as an example for the litellm Vectorizers. Can we include other examples such as HuggingFace?

https://huggingface.co/spaces/mteb/leaderboard

^ Here are the top embedding models on HF

Reason being that create_vectorizer requires an extra_options.wait_for_model, so, does litellm_embed need that too?

@JamesGuthrie JamesGuthrie force-pushed the jg/litellm-extension-docs branch from a169beb to 5a97d1d Compare February 4, 2025 10:29
@JamesGuthrie JamesGuthrie changed the title WIP: LiteLLM extension docs Improve LiteLLM docs Feb 4, 2025
@JamesGuthrie JamesGuthrie marked this pull request as ready for review February 4, 2025 10:29
@JamesGuthrie JamesGuthrie requested a review from a team as a code owner February 4, 2025 10:29
@JamesGuthrie JamesGuthrie merged commit 6aa56a1 into main Feb 4, 2025
5 checks passed
@JamesGuthrie JamesGuthrie deleted the jg/litellm-extension-docs branch February 4, 2025 11:52
'my_table'::regclass,
embedding => ai.embedding_litellm(
'huggingface/BAAI/bge-small-en-v1.5',
, 384
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Does this not need api_key_name => 'HUGGINGFACE_API_KEY',?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It doesn't need it, and TBH it's confusing when it does and doesn't. If the HUGGINGFACE_API_KEY environment variable is set in the vectorizer worker, then it doesn't need to be set. If not, and the vectorizer should get the API key from the database, then the api_key_name parameter must be set.

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.

3 participants