VectorChord

VectorChord (vchord) is a PostgreSQL extension designed for scalable, high-performance, and disk-efficient vector similarity search. It serves as the successor to pgvecto.rs and enables developers to build AI applications at scale using familiar SQL syntax. The extension is 16x faster than pgvector for indexing and 14x faster for inserts, efficiently handling billions of vectors on a single machine.

• Better Filtering allows applying any filter conditions and joining with other tables while achieving high recall and low latency, providing a distinctive edge over other vector databases.

• External Index Build offloads indexing to a powerful machine, enabling faster processing and efficient handling of large-scale datasets on a single system.

• PGVector-Compatible offers a fully compatible solution designed to seamlessly replace PGVector with enhanced performance, scalability, and advanced vector search capabilities.

• Hybrid Search leverages the full-text search functionality in PostgreSQL to search text and vector data within a single query.

• Complete SQL Support provides full SQL capabilities, enabling joins and filters without limitations or extra configuration.

• High Performance delivers 4x faster performance than other PostgreSQL-based solutions for vector operations.

To get started, users can create a table with a vector column, insert vector values, create an index using the vectors extension, and query for similar embeddings using standard SQL syntax. VectorChord Cloud offers a free starter tier with no credit card required, making it easy to experiment with vector search capabilities. The enterprise tier supports holding 100 million 768-dimensional vectors with self-healing high availability PostgreSQL, pre-configured point-in-time recovery, on-demand backup, workflow support, and high-performance connection pooling.