Pinecone uses proprietary indexing algorithms—Ananas, PQFS, and IVF with PQFS—selected automatically per slab based on size, instead of general-purpose methods like HNSW. The adaptive approach optimiz…
Manticore Search has introduced early termination for its HNSW-based vector search, a feature that stops distance computations once the result set has converged, reducing unnecessary work. Benchmarks …
A developer built Vektr, a custom RAG engine implementing HNSW graphs from scratch, achieving recall@10 of 0.984 — meaning 98.4% of queries returned all 10 true nearest neighbors in the top results. T…
ON1 (G116 V8) has introduced a virtual chip ISA that achieves 38-microsecond black-box AI memory retrieval by separating vector search into three observable latency stages: fetch, compute, and ANN sea…
SurrealDB 3.1 is now available, marking the first minor release in the 3.x series with a focus on stability, security hardening, and the introduction of DiskANN as a second approximate-nearest-neighbo…
A new coding tutorial demonstrates how to build a complete pgvector-powered vector search system inside Google Colab, supporting semantic, hybrid, sparse, and quantized search methods. The guide walks…