A comprehensive operational guide for running pgvector on Amazon Aurora PostgreSQL in production. Covers choosing between HNSW and IVFFlat indexes (or no index at all for small/partitioned datasets), configuring distance operators (cosine vs inner product), scaling to millions of vectors with quantization and partitioning, managing HNSW index churn via REINDEX CONCURRENTLY or partition-based rebuilds, capacity planning for memory-resident HNSW graphs, and observability using pg_stat_statements, CloudWatch metrics, and custom recall tracking. Includes concrete SQL examples, recommended parameter values (m=16, ef_construction=128), and a two-stage binary quantization retrieval pattern for large datasets.
Table of contents
How this post is organizedPrerequisitesChoosing the right index strategyA runnable baselineSimilarity functions at scaleScaling to millions of vectorsManaging index churnCapacity planningObservabilityClean upKey takeawaysConclusionAbout the authors297 Impressions