Source: pgvector README

Official README of pgvector, the PostgreSQL extension for vector similarity search: types, operators, HNSW and IVFFlat indexes, iterative scans and filtering.

Contents
  • What: project README (reference documentation)
  • Author: pgvector maintainers (Andrew Kane and contributors)
  • Date: latest version mentioned is 0.8.7 (read 2026-11-14)
  • Original: github.com/pgvector/pgvector

Summary

pgvector adds vector types, distance operators and two approximate index types to Postgres 13+. The README is the authoritative reference for limits and tuning knobs, and it is unusually candid about how approximate indexes interact with SQL WHERE clauses.

Key claims

  • Types: vector (float32, up to 16,000 dims stored, 2,000 indexable), halfvec (float16, 4,000 indexable), bit (64,000 indexable), sparsevec (up to 1,000 non-zeros indexable, HNSW only).
  • Operators: <-> L2, <#> negative inner product, <=> cosine distance, <+> L1, <~> Hamming, <%> Jaccard.
  • HNSW: build params m (default 16) and ef_construction (default 64); query param hnsw.ef_search (default 40). Better speed/recall than IVFFlat but slower build and more memory; can be created on an empty table.
  • IVFFlat: lists at build, ivfflat.probes (default 1) at query. Build after data is loaded. Suggested lists = rows/1000 up to 1M rows, sqrt(rows) beyond; start probes at sqrt(lists).
  • Filtering is applied after the index scan: with ef_search 40 and a filter matching 10% of rows, about 4 rows come back on average.
  • Iterative index scans (0.8.0+): hnsw.iterative_scan = strict_order or relaxed_order, bounded by hnsw.max_scan_tuples (default 20,000).
  • For selective filters use a B-tree on the filter column; partial indexes for a few filter values; partitioning for many values or multitenancy.
  • HNSW build is much faster when the graph fits in maintenance_work_mem; parallel builds use max_parallel_maintenance_workers.
  • Binary quantization via binary_quantize() expression index plus Hamming search, then re-rank by full vectors; halfvec expression indexes shrink indexes.

Feeds

Vector databases · ANN indexes

Suggest changes →