Hacker News · AI·· 1 d agoAI score63
Onehouse Lakegres adds vector search on existing Hudi and Iceberg tables
Lakegres: Vector search on existing Open/Hudi/Iceberg tables
AI summary
Onehouse announced vector search in Lakegres, with a native index stored inside existing and new open tables and queried through a Postgres endpoint, so embeddings can be searched without copying lake data into a separate database. The index is derived metadata kept in the table's metadata and updated with table writes, leaving the underlying Parquet files unchanged. On a 247M-vector Cohere Wikipedia table, Onehouse reports warm p50 latency of 63.5 ms versus 655 ms for Databricks AI Search, with Recall@10 of 0.95 versus 0.952, and an index build of 18 minutes versus about 3 hours 10 minutes.
Source:Hacker News · AI · onehouse.ai