Repo · Search & RAG

jev-rag

Vector-free local RAG: SQLite BM25 retrieval, TypeSafe Jev evidence reranking, optional grounded LLM answers (no embeddings).

Open github.com ↗

From the repository

Vector-free local RAG with SQLite BM25, Jev reranking, and grounded LLM answers. No embeddings or vector database.

bm25chinese-nlpfts5jevknowledge-basellmlocal-firstminimaxopenrouterpythonragrerankingretrieval-augmented-generationsqlitevector-free

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 61 search & rag projects →

Related projects