Pg_vectorsearch: An index that is faster than pgvector's IVFFlat and HNSW
A new PostgreSQL extension called PRISM has been released to improve the speed of approximate nearest neighbor searches. It utilizes hierarchical centroid trees and advanced quantization to outperform existing methods like HNSW and IVFFlat.
Why it matters
High-performance vector search is essential for modern AI and machine learning applications, and this tool offers significant efficiency gains for database-heavy workloads.
A PostgreSQL extension for high-performance approximate nearest neighbor (ANN) search.
Status: alpha. Meant for testing, not production. Upgrading between prereleases may not be possible; plan to drop and recreate the extension and its indexes. See the changelog for known issues.
PRISM (Partitioned Routing Index for Similarity Matching) is a PostgreSQL-native index access method that is conceptually similar to pgvector 's IVFFlat, but it is built around state-of-the-art quantization, routing, and partitioning techniques. It is implemented in C for high performance and seamless integration with PostgreSQL.
The result: an index that is significantly faster than pgvector's IVFFlat and HNSW, for both querying and index building. In fact, compared to graph-based HNSW, PRISM is faster at equivalent recall on a 100-million-vector dataset, on an instance with a quarter of the memory.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in