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

feat(rerankers): implement litellm rerankers #96

Open
micpst opened this issue Oct 14, 2024 · 0 comments · May be fixed by #109
Open

feat(rerankers): implement litellm rerankers #96

micpst opened this issue Oct 14, 2024 · 0 comments · May be fixed by #109
Assignees
Labels
document search Changes to the document search package feature New feature or request integrations Changes in vendor integration
Milestone

Comments

@micpst
Copy link
Collaborator

micpst commented Oct 14, 2024

Feature description

Implement the LiteLLM reranker API for the Document Search package. Add a new LiteLLMReranker class that would unlock Cohere, Together AI and Azure endpoints for documents reranking.

Motivation

Currently, we don't have any rerankers defined in the lib that could be used out of the box.

Additional context

Here are the docs for the litellm reranker API - https://docs.litellm.ai/docs/rerank. For development we can easily test using Cohere free tier (please mind the rate limits).

@micpst micpst added feature New feature or request document search Changes to the document search package integrations Changes in vendor integration labels Oct 14, 2024
@mhordynski mhordynski added this to the Ragbits 0.4 milestone Oct 14, 2024
@PatrykWyzgowski PatrykWyzgowski self-assigned this Oct 14, 2024
@PatrykWyzgowski PatrykWyzgowski linked a pull request Oct 16, 2024 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
document search Changes to the document search package feature New feature or request integrations Changes in vendor integration
Projects
Status: In review
Development

Successfully merging a pull request may close this issue.

3 participants