A developer has created an open-source system that gives AI coding agents persistent memory by indexing past conversation transcripts locally. The setup uses a FastMCP server connected to an SQLite FT…
A new arXiv paper (2609.02890v1) introduces PersonaLink, a training-free method that refines a bounded text persona through recursive testing against a user's labeled data, and finds that for classifi…
A new training-free method called PersonaLink can match retrieval-based personalization on classification tasks but not regression, according to a paper posted on arXiv (2609.02890v1). On 200 users of…
Zvec AI has open-sourced zg (zvec-grep), a local-first search infrastructure that combines vector search with BM25 and ripgrep to enable semantic discovery and relevance ranking for local code and doc…
A production-ready multi-stage RAG pipeline that combines vector search with BM25 keyword retrieval and Reciprocal Rank Fusion can scale to thousands of documents while improving answer quality, accor…
Kosha, an open-source storage-disaggregated search engine built in Rust as an alternative to Elasticsearch/OpenSearch, has completed Phase 1 with BM25 lexical and kNN/ANN vector search implemented acr…
A new arXiv study (2608.27470v1) finds that pairing a training-free BM25 retriever with an LLM-based selector achieves state-of-the-art entity disambiguation on the ZELDA benchmark, raising inKB micro…
A developer built an 'Agentic AI Knowledge Assistant' that combines hybrid retrieval-augmented generation (RAG) with an LLM agent to answer questions strictly from a predefined knowledge base. The sys…
A developer detailed five custom skills for Claude Code that reportedly saved 10 hours a week, including test-driven development workflows, schema-first API design, adversarial self-review, hybrid RAG…
A developer built a hybrid RAG system combining FAISS vector search and BM25 keyword search to retrieve relevant information from a knowledge base and generate grounded answers. The system uses weight…
An engineer detailed the design and deployment of a hybrid agentic retrieval-augmented generation (RAG) architecture that combines dense semantic search (FAISS) with exact keyword search (BM25) and us…
A developer has published a guide to implementing hybrid search in retrieval-augmented generation (RAG) pipelines, combining BM25 keyword search with dense vector embeddings using Reciprocal Rank Fusi…
A developer named Pranshu640 built a hybrid retrieval system that combines dense and sparse vectors to search PubMed biomedical research, comparing dense search with sentence-transformers/all-MiniLM-L…
A developer replaced a cloud vector database with SQLite FTS5 and dense embeddings in a hybrid RAG pipeline, reporting a 10x improvement in retrieval accuracy for exact keywords, error codes, and vers…
A new technical notebook on retrieval-augmented generation (RAG) reports that fusing keyword (BM25) and dense-embedding search lifts recall@5 to 0.94 on 18 hand-labelled questions, and adding a cross-…
A developer's production checklist for LLMOps in RAG systems identifies weak retrieval, lack of reranking, poor prompt/version control, insufficient eval coverage, and blunt cost controls as common ro…
A developer detailed how vector databases are critical for retrieval-augmented generation (RAG) systems, recounting a health-tech client's RAG system that gave a dangerously wrong medication dosing su…
A new open-source Common Lisp library, docs-reference, provides a local RAG (retrieval-augmented generation) system for referencing URL documentation with local AI models. The library, available on Gi…
Most RAG implementations are over-engineered, and a simple full-text search (BM25) often suffices, according to a technical guide that outlines a recipe-based approach. The guide recommends starting w…
LatticeDB, an embedded single-file property-graph database developed by Jeff Hajewski, combines graph traversal, HNSW vector similarity search, and BM25 full-text search in one query layer, with perfo…