pgvector in 2024: HNSW Indexes and Real Scaling

pgvector matured in 2023-2024 with the HNSW index type and parallel construction that arrived in version 0.6. For projects already running PostgreSQL, a dedicated vector database is not needed in most cases: this guide explains when PostgreSQL is enough, how to configure the index, and where it starts to fall short.

January 21, 2024 5 min 243 4.4

Architecture

pgvector: Semantic Search Without Leaving Postgres

pgvector turns PostgreSQL into a fully functional vector database without adding a separate service to the stack. It extends Postgres with the vector type, IVFFlat indexes for approximate nearest-neighbour search (ANN), and the ability to combine relational SQL filters with vector ranking in a single query. For most RAG projects and internal chatbots, those limits never become a problem.

November 1, 2023 6 min 232