Engineering posts, retrieval research, and customer dispatches from the team building vector search around the questions you actually ask.
Graph-based vector search sounds intimidating, but the core idea is elegant. NSG builds a sparse, well-spread graph that lets you navigate to any nearest neighbor in a handful of hops.
Every memory-first vector database is announcing disk support. But bolt-on tiering solves a cost problem — not the latency, write-throughput, and filtered-query problems that disk-resident workloads actually surface in production.
IVF-PQ is the workhorse of large-scale vector search. OPQ makes it dramatically better by learning a rotation that aligns your data with the quantizer. Here's how both work and why OPQ's trick is so clever.