ruvector-postgres

PGvector is an open-source PostgreSQL extension for vector similarity search, adding vector data type and operators like cosine and L2 distance. It supports HNSW and IVFFlat indexes for fast ANN search on high-dimensional data, integrating seamlessly with SQL for hybrid queries. Ideal for apps needing ACID transactions and relational data alongside vectors, unlike pure vector DBs like Milvus; outperforms native Postgres for vectors.

ClickHouse's vector search extension that adds kNN similarity search capabilities to the ClickHouse columnar database, enabling hybrid analytical + vector queries at scale.

Experimental extension for DuckDB that adds HNSW indexing support to accelerate vector similarity search queries using DuckDB's fixed-size ARRAY type. First custom index type provided through a DuckDB extension.

A SQLite extension for efficient vector similarity search based on FAISS, enabling semantic search, recommendations, and question-answering directly within SQLite databases.

PostgreSQL-based vector search solution built on Timescale Cloud with pgai extensions including pgvector, pgvectorscale, and pgai. Features StreamingDiskANN index for high-performance embedding search at scale.

A feature for MySQL that integrates vector store capabilities, allowing users to store and process vector embeddings for AI applications.