select open change scope Open full search

PG.CENTER connects PostgreSQL documentation, reference, and ecosystem knowledge. Maintained by Pigsty.

Extensions / AI and vectors

pgvector

Custom vector type with Euclidean distance, cosine similarity, and prototype IVFFlat helpers.

pgext.cloud · Source code · Documentation · Control file

Overview

Packagepgvector
Version0.0.0
RepositoryUnspecified
Extension typeStandard
Project statusActive
Requires CREATE EXTENSIONYes
Requires preloadNo
TrustedNo
RelocatableNo
Stars1
Latest commit2025-03-15
Catalogue updated2026-08-30

Related extensions

See also

smlarEffective similarity search
pgcontextVector, filter-aware HNSW, and hybrid retrieval over authoritative PostgreSQL tables.
vectorizeThe simplest way to do vector search on Postgres
sparse_vectorC data type and functions for sparse float vectors, normalization, dot product, and cosine similarity.
hamming_distanceHamming distance and similarity functions for hexadecimal feature-vector strings.
pg_similaritysupport similarity queries
pgmnemoSingle-plan multimodal agent memory for PostgreSQL
tlsh_gistTLSH fuzzy-hash data type, distance operations, and GiST indexing for similarity search.
pg_trgmtext similarity measurement and index searching based on trigrams
embeddingHNSW vector similarity search extension for PostgreSQL real[] embeddings.
pg_emdFast approximate Earth Mover's Distance using dynamic tree embeddings
ruvectorSIMD-accelerated vector type and indexes with graph, solver, TDA, local embedding, and AI SQL functions.

Same project

vectorvector data type and ivfflat and hnsw access methods