Repo · Search & RAG

jev-reranker

Python library (PyPI) that scores and optionally filters retrieved documents for RAG with TypeSafe Jev—listwise, pointwise, and pairwise modes with…

Open github.com ↗

From the repository

Jev-powered relevance filtering and reranking for RAG in Python.

How builders describe it

Jev-powered relevance filtering and reranking for RAG in Python.

Python library (PyPI) that scores and optionally filters retrieved documents for RAG with TypeSafe Jev—listwise, pointwise, and pairwise modes with concurrency, splitting, and retries.

A Python library that reranks search results and filters retrieved documents with Jev, scoring each candidate's usefulness as evidence and dropping those below a configurable threshold before RAG context is assembled.

The decision Jev makes

Rank candidates against a query, or answer whether a passage is relevant.

Where it fits

Search pipelines retrieve too much. These projects use Jev as a reranker or relevance check after the first search, so only useful results reach the user or the model. All 108 search & rag projects →

Related projects