Compact TurboQuant approximate-nearest-neighbor index access method for pgvector vector and halfvec data.
pgext.cloud · Source code · Documentation · License text · Control file
| Package | pg_turboquant |
|---|---|
| Version | 0.1.0 |
| PostgreSQL versions | 16 · 17 |
| Repository | Unspecified |
| Extension type | Standard |
| Project status | Active |
| Requires CREATE EXTENSION | Yes |
| Requires preload | No |
| Trusted | No |
| Relocatable | Yes |
| Stars | 14 |
| Latest commit | 2026-04-05 |
| Catalogue updated | 2026-08-30 |
| 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 |
| alloydb_scann | AlloyDB ScaNN extension for approximate nearest-neighbor vector indexes. |
| pase | PostgreSQL ultra-high dimensional approximate nearest neighbor search extension. |
| pg_ivfflat | Experimental pgrx extension providing a Vector type and an in-memory IVFFlat index access method. |
| pgturbohybrid | hybrid vector and BM25 search for PostgreSQL on top of pgvector |
| pgmnemo | Single-plan multimodal agent memory for PostgreSQL |
| llama_embed | llama.cpp embedding extension for dense and multivector search |
| pg_colbert_llama | ColBERT embedding companion extension for pgturbohybrid |