Breeze136/kb-rag

README excerpt

kb-rag — Local Literature Knowledge-Base RAG (DSH Plugin) Ingest once, search forever. Only the most relevant few sentences ever reach the LLM — and every claim carries exact provenance. kb-rag is a lightweight local database-RAG plugin for DSH (DeepSeek Harness) : it turns PDF/Zotero literature into a SQLite knowledge base with section structure and vector indexes, providing the full hybrid search + rerank + cited-QA workflow. All indexing, embedding, and reranking run locally — zero API cost, zero upload. Features - 8 model tools : kb ingest (file/folder ingest), kb zotero (Zotero migration), kb search (hybrid search), kb rag (cited QA), kb scope (scope/strict mode), kb dedup (dedup), kb clear (wipe), kb stats (stats) - Structured chunking : paper section recognition (abstract ×1.5, methods ×1.2 weights), inline-heading detection, abstract auto-promotion, caption blocks; paragraph fallback for non-papers - Hybrid retrieval : keyword BM25 (CJK-bigram friendly) + bge-small vector cosine, RRF fusion, × section weights - Reranking : bge-reranker-base Cross-Encoder, Top-20 → Top-3 (auto-fallback to bge-large-en bi-encoder if missing) - Incremental & dedup : sha256 incremental skip (40…

Category