HNSW, the default graph algorithm powering vector search in Faiss, pgvector, Qdrant, and other stores, trades exactness for speed, offering logarithmic retrieval but occasionally returning wrong memor…
A developer's analysis of RAG retrieval architectures shows that vector-only search fails on exact-match queries like product codes and error numbers, and that hybrid search combining lexical and vect…
An engineer discovered that Qdrant's asynchronous index refresh caused recall inconsistency in an AI agent's memory system, with recall rates dropping from 98% to 60%. They automated consistency testi…
A developer has created a RAG-assisted Model Context Protocol (MCP) server that turns a monorepo into a queryable knowledge base, enabling semantic code search for LLMs and CLI tools. The system uses …
Qdrant's filtered vector search benchmark on one million deep-image-96 vectors shows that ACORN-1, a query-time algorithm, repairs graph connectivity gaps left by Filterable HNSW's index-time extra ed…
DuckDB's official vss extension brings HNSW-based approximate nearest neighbor search directly to its SQL engine, allowing developers to run vector similarity queries without a separate vector databas…
A developer highlights semantic caching as a cost-saving technique for LLM-backed applications, using embeddings to detect similar queries and reduce API costs by 30-70% while cutting latency. The app…
Qdrant, the Rust-based vector database, has been integrated into OpenCrawling's event-driven microservice architecture via a new Qdrant Output Connector that enables sub-millisecond ACL pre-filtering …
RAGless, a retrieval-only question-answering system, eliminates LLM API costs at runtime by using vector retrieval with Gemini embeddings and a local Qdrant database, achieving zero hallucinations and…
A developer detailed the challenges of building write policies for agent memory, arguing that the write-path—deciding what to store, sanitizing it, and maintaining network and RBAC plumbing—is the har…
Enterprise teams are increasingly adopting a 'Dumb RAG' anti-pattern that floods LLM context windows with uncurated document chunks, degrading self-attention and causing 'context thrashing' analogous …
A developer overhauled their hybrid retrieval pipeline for technical documentation, combining Qwen embeddings, BM25 sparse vectors, and reciprocal rank fusion with a FastEmbed reranker. The upgrade im…
DeepMem, a drop-in AI memory layer compatible with the Mem0 API, claims 2× faster response times and 10× lower cost, with self-hosted options at $0 and cloud plans starting at $1.9/month compared to M…
Vector databases have become core infrastructure for modern AI applications, addressing the lack of long-term memory in large language models. They store high-dimensional embeddings and use approximat…
A developer's guide to vector search fundamentals for RAG design covers ANN algorithms like HNSW, distance metrics, metadata filtering, and BM25. It explains trade-offs between accuracy, speed, and co…
RAGproof released an open-source tool, rag-staleness-check, that performs read-only staleness, orphan, duplicate, and retrievability checks on a single pgvector, Qdrant, or Chroma index. The tool, ins…
Qdrant, an AI vector search database supplier, has applied Google Research's TurboQuant compression technique to embeddings, claiming it achieves competitive recall at 8x compression and beats binary …
A new open-source library, hubmesh, adds a graph layer on top of Qdrant to answer multi-hop questions that stymie vector search. The library builds an entity-document graph at index time and uses Pers…
Hubmesh, a new Python library, improves multi-hop RAG retrieval by adding a centrality-aware planner over existing vector databases, eliminating LLM calls in the query path. The library uses multi-com…
Retrieval-Augmented Generation (RAG) is the key to building AI agents that don't hallucinate, according to a new guide that outlines how to set up retrieval layers using vector stores like Chroma, FAI…