Tag
The article discusses ACORN's algorithm for fixing filtered vector search challenges and compares it with Qdrant's filterable HNSW method, including performance benchmarks on a million-point dataset.
A thread warns that choosing a vector database solely on speed benchmarks can be a trap for AI agents, which have constant write workloads unlike RAG's read-heavy patterns. It recommends specific databases based on use case, such as Qdrant for agent memory and pgvector for under 10M vectors on Postgres.
This article provides a practical guide to building a GraphRAG system using LangExtract, Neo4j, Qdrant, and Ollama, combining entity extraction, knowledge graphs, and vector search for context-aware retrieval.
A developer shares that the real problem in a RAG app was the retrieval step failing on version numbers and codes, fixed by hybrid search (vector + BM25 + reciprocal rank fusion), not the model.
Laurie Voss of Arize will speak at QDrant's Vector Space Day conference on June 11 in San Francisco, covering retrieval metrics, golden datasets, LLM-as-judge, and continuous evals for CI pipelines.
This article introduces 7 production-ready skills from the Hermes Skills Hub, covering the full lifecycle from tool integration and structured output to deployment, observability, and security.