Termsslug: prism-index

PRISM Index

PRISM 索引

Vector index using partitioning and compressed lists instead of graphs to cut memory and build cost.

Curated Intelligence

1 items · Page 1/1
InfoQ 中文T2·Open Source
72 pts
Tiger Data Open-Sources pg_vectorsearch with 25x Faster Index Builds

Tiger Data (formerly Timescale) released pg_vectorsearch, an Alpha-stage open-source PostgreSQL extension whose PRISM index uses partitioning and compression instead of pgvector's graph-based HNSW. In a 100M-vector benchmark, PRISM built its index in 1h40m on 128 GB RAM versus 42 hours on 512 GB for HNSW. It works with existing pgvector columns, letting apps run vector search without a separate vector database.