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

How builders describe it

Jev RAG (Jev-RAG / JevRAG): open-source local knowledge search with BM25 + Jev reranking, agentic and hybrid retrieval, cited answers, and reproducible benchmarks.

Local-first knowledge search with seven selectable pipelines: BM25 plus Jev reranking is the default vector-free path, plus agentic, embedding-hybrid, taxonomy, gate and line-search modes. Reranks up to 30 candidates in one batched set of Jev Noul relevance questions and streams cited answers from…

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