PostgreSQL extension that provides (RAG capable)SQL functions to interpret data using multi modal LLMs and vectors.
pgext.cloud · Source code · Documentation · Control file
| Package | pg_ai |
|---|---|
| Version | 0.0.1 |
| Repository | Unspecified |
| Extension type | Standard |
| Project status | Active |
| Requires CREATE EXTENSION | Yes |
| Requires preload | No |
| Trusted | No |
| Relocatable | No |
| Stars | 25 |
| Latest commit | 2024-04-05 |
| Catalogue updated | 2026-08-30 |
| vectorize | The simplest way to do vector search on Postgres |
| pgmnemo | Single-plan multimodal agent memory for PostgreSQL |
| vector | vector data type and ivfflat and hnsw access methods |
| pgcontext | Vector, filter-aware HNSW, and hybrid retrieval over authoritative PostgreSQL tables. |
| rds_ai | Alibaba Cloud RDS extension for calling LLMs, generating embeddings, semantic retrieval, and end-to-end RAG from SQL |
| neurondb | AI database extension for vector search, ML inference, hybrid search, and RAG in PostgreSQL. |
| ai | Helper functions for AI workflows in PostgreSQL |
| pg_deeplake | Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training. |
| lantern_extras | Convenience functions for working with vector embeddings |
| pgedge_vectorizer | Asynchronous text chunking and embedding generation for PostgreSQL using background workers and pgvector. |