TECHNOLOGY PROFILE · TECH-0200
pgvector
PostgreSQL extension for vector similarity search.
Core capability checked in primary documentation. This profile preserves the prepared catalog’s original descriptions. Advantages depend on the workload; comparisons are editorial, not benchmark results.
Where it has an edge
Keeps vectors, relational joins and transactional data together instead of introducing a separate vector database.
Best-fit problems
RAG systems already using PostgreSQL and requiring SQL filtering.
Tradeoffs & cautions
Index/recall tuning and database resource contention still matter.
What to test before choosing
Measure recall@k, filtered recall, indexing cost, p95 query latency, updates, backup and access control.
Runtime & hardware
Embedded, self-hosted or managed
Access & licensing
Open-source or commercial depending on edition
Execution
Local / self-hosted
Lifecycle
Not independently audited
Comparison basis
Editorial problem-fit judgement; no head-to-head benchmark performed
Connected concepts
Alternatives to investigate
Qdrant · Milvus · FAISS