| ai | Helper functions for AI workflows in PostgreSQL |
| aidb | In-database AI pipelines for chunking, embedding, retrieval, and generation. |
| alloydb_scann | AlloyDB ScaNN extension for approximate nearest-neighbor vector indexes. |
| avocado | AvocadoDB PostgreSQL extension for deterministic context compilation for AI agents. |
| documentdb | API surface for DocumentDB for PostgreSQL |
| embedding_search | LangChain/Supabase helper package for storing and searching document embeddings with pgvector. |
| hybrid_search | Hybrid pgvector and full-text search helper functions for LangChain and Supabase. |
| maludb_core | A memory DBMS for long-term institutional memory, human-AI knowledge sharing, and contextual recall. PostgreSQL 17 extension. |
| paves | Filtered L2 vector search with CPU and optional GPU execution |
| pg_cuvs | ⚡ Blazing-fast GPU vector search for PostgreSQL powered by NVIDIA cuVS. |
| pg_diskann | Azure Database for PostgreSQL extension for DiskANN approximate-nearest-neighbor vector indexes. |
| pg_gembed | Generate embeddings inside PostgreSQL |
| pg_knowledge_graph | Knowledge graph extension for PostgreSQL with graph algorithms and pgvector integration. |
| pg_llm | Integrates local and remote large-language models with chat, sessions, text-to-SQL, audit and vector-backed knowledge features. |
| pg_llm_helper | Captures PostgreSQL errors in shared memory and exposes history plus an optional pgai-backed LLM troubleshooting function. |
| pg_sag_rag | Pure-SQL multi-hop event/entity retrieval, query routing, and in-database RAG evaluation. |
| pg_search | Full text search for PostgreSQL using BM25 |
| pg_semantic_cache | Caches query results and retrieves semantically similar results using pgvector embeddings and configurable eviction policies. |
| pg_sentence_transformer | Runs a Hugging Face sentence-transformer model inside a preload background worker and maintains pgvector embeddings for a configured table. |
| pg_splade | Generate SPLADE sparse-vector embeddings inside PostgreSQL |
| pg_turboquant | Compact TurboQuant approximate-nearest-neighbor index access method for pgvector vector and halfvec data. |
| pg_vector_embedding | Trigger-driven vector embedding through external HTTP services and a background queue. |
| pgcontext_pgvector | Optional pgvector compatibility bridge for pgcontext HNSW indexes. |
| pgedge_vectorizer | Asynchronous text chunking and embedding generation for PostgreSQL using background workers and pgvector. |
| pgembed | Generate vector embeddings through Ollama, OpenAI, or custom HTTP services |
| pgmnemo | Single-plan multimodal agent memory for PostgreSQL |
| pgpu | GPU acceleration for PostgreSQL vector index builds using NVIDIA CUDA/cuVS and VectorChord. |
| pgturbohybrid | hybrid vector and BM25 search for PostgreSQL on top of pgvector |
| pgvecutils | This project is a PostgreSQL extension that provides vector manipulation utilities. |
| postvec | Automatic embeddings, hybrid search, and embedding model migration |
| rag | Deprecated RAG helper extension for document extraction/chunking and remote embedding, reranking, and chat APIs. |
| rag_bge_small_en_v15 | rag_bge_small_en_v15: local bge-small-en-v1.5 embeddings in PostgreSQL |
| rag_jina_reranker_v1_tiny_en | Runs jina-reranker-v1-tiny-en locally in a preloaded background worker and exposes SQL rerank scores and distances. |
| rds_ai | Alibaba Cloud RDS extension for calling LLMs, generating embeddings, semantic retrieval, and end-to-end RAG from SQL |
| rds_embedding | Alibaba Cloud RDS text-to-vector model invocation extension |
| svs | SVS Vamana approximate-nearest-neighbor index with LeanVec and LVQ compression for pgvector. |
| vchord | Vector database plugin for Postgres, written in Rust |
| vectorize | The simplest way to do vector search on Postgres |
| vectorscale | Advanced indexing for vector data with DiskANN |