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.
Toolsslug: pgvector
pgvector
Open-source PostgreSQL extension for vector similarity search, enabling embeddings storage and query in relational databases.
Curated Intelligence
InfoQ 中文T2·Open Source
72 pts
Hacker News AIT2·Tools
62 pts
Onehouse announced that Lakegres now supports native vector indexes built directly on existing Hudi and Iceberg open tables, exposing similarity search through a Postgres endpoint while keeping both index and data in open formats inside the customer's own bucket. This lets agents query lakehouse-scale logs, documents and event history without moving data into a separate application database.