3 min read
HNSW defaults can look fast while missing useful results. Production tuning needs recall@k, p99, index build time, memory, and filtered result count together.
Database Topic Archive
pgvector and RAG Articles
HNSW, IVFFlat, recall, embedding search, and production RAG performance notes.
3 min read
Vector search looks easy until tenant filters, permissions, freshness, and deleted content arrive. The hard part is not nearest neighbors; it is filtered recall under production rules.
3 min read
Multi-tenant vector search is a correctness and isolation problem. Namespaces, filters, and partitions each fail differently under tenant skew and ACL rules.
3 min read
Hybrid search helps when exact terms and semantic meaning both matter. It fails when teams blend rankings without query intent, calibration, or evaluation.
7 min read
The hard vector database decision is not pgvector versus Pinecone on a checklist. It is whether your filters, recall target, update rate, and incident budget still fit inside Postgres.