Azure Database for PostgreSQL extension for DiskANN approximate-nearest-neighbor vector indexes.
| Package | pg_diskann |
|---|---|
| Version | 0.6.5 |
| PostgreSQL versions | 14 · 15 · 16 · 17 · 18 |
| Repository | Unspecified |
| Extension type | Standard |
| Project status | Active |
| Distribution | azure-postgresql |
| Vendor | Microsoft Azure |
| Requires CREATE EXTENSION | Yes |
| Requires preload | No |
| Catalogue updated | 2026-07-30 |
| vector | vector data type and ivfflat and hnsw access methods |
| vector | vector data type and ivfflat and hnsw access methods |
| pgcontext | Vector, filter-aware HNSW, and hybrid retrieval over authoritative PostgreSQL tables. |
| vectorize | The simplest way to do vector search on Postgres |
| pgmnemo | Single-plan multimodal agent memory for PostgreSQL |
| vectorscale | Advanced indexing for vector data with DiskANN |
| pg_similarity | support similarity queries |
| smlar | Effective similarity search |
| pg_bestmatch | Generate BM25 sparse vector inside PostgreSQL |
| alloydb_scann | AlloyDB ScaNN extension for approximate nearest-neighbor vector indexes. |
| pg_sorted_heap | Sorted heap table AM with zone map scan pruning and built-in vector search |