mixedbread-ai/mxbai-rerank

Crispy reranking models by Mixedbread

48
/ 100
Emerging

This project helps improve the quality of search results or document retrieval by reordering a list of documents based on a given query. You input a search query and a list of potentially relevant documents, and it outputs the same documents, but re-ranked from most to least relevant. It's ideal for anyone building search engines, recommendation systems, or intelligent agents who need highly accurate and fast retrieval.

No commits in the last 6 months. Available on PyPI.

Use this if you need to significantly improve the accuracy and relevance of search results, especially across many languages or for technical content like code.

Not ideal if you only need basic keyword matching and are not concerned with nuanced relevance or state-of-the-art performance.

search-relevance information-retrieval content-ranking technical-search multilingual-search
Stale 6m
Maintenance 2 / 25
Adoption 8 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

50

Forks

7

Language

Python

License

Apache-2.0

Last pushed

Sep 17, 2025

Commits (30d)

0

Dependencies

6

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/rag/mixedbread-ai/mxbai-rerank"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.