HNSW vector similarity search extension for PostgreSQL real[] embeddings.
pgext.cloud · Source code · Documentation · License text · Control file
| Package | embedding |
|---|---|
| Version | 0.3.6 |
| PostgreSQL versions | 12 · 13 · 14 · 15 · 16 |
| Repository | Unspecified |
| Extension type | Standard |
| Project status | Deprecated |
| Requires CREATE EXTENSION | Yes |
| Requires preload | No |
| Trusted | No |
| Relocatable | Yes |
| Stars | 579 |
| Latest commit | 2023-09-28 |
| Latest release | 2023-09-12 |
| Catalogue updated | 2026-08-30 |
| pgcontext | Vector, filter-aware HNSW, and hybrid retrieval over authoritative PostgreSQL tables. |
| vector | vector data type and ivfflat and hnsw access methods |
| vectorize | The simplest way to do vector search on Postgres |
| ruvector | SIMD-accelerated vector type and indexes with graph, solver, TDA, local embedding, and AI SQL functions. |
| smlar | Effective similarity search |
| pg_similarity | support similarity queries |
| quria | quria: experimental pgrx extension for BM25 full-text and HNSW vector search |
| pgmnemo | Single-plan multimodal agent memory for PostgreSQL |
| pg_cuvs | ⚡ Blazing-fast GPU vector search for PostgreSQL powered by NVIDIA cuVS. |
| sparse_vector | C data type and functions for sparse float vectors, normalization, dot product, and cosine similarity. |