Lakegres: Vector search on existing Open/Hudi/Iceberg tables
cloud8bits
40 points
8 comments
November 18, 2026
Related Discussions
Found 5 related stories in 162.1ms across 13,334 title embeddings via pgvector HNSW
- Pg_vectorsearch: An index that is faster than pgvector's IVFFlat and HNSW jascha_eng · 200 pts · October 14, 2026 · 57% similar
- Show HN: Pivot – fast analytics on Iceberg, 2x+ faster than ClickHouse / DuckDB dkgs · 11 pts · October 08, 2026 · 54% similar
- BigLake's Iceberg REST Catalog advaita_datazip · 16 pts · August 21, 2026 · 53% similar
- Show HN: ParqDB – Vector search in the browser from Parquet over HTTP" petrizhang · 11 pts · August 21, 2026 · 51% similar
- Aurora PostgreSQL now supports querying of Apache Iceberg and Parquet data daigoba66 · 14 pts · September 30, 2026 · 51% similar
Discussion Highlights (4 comments)
tokYoComPleX
This is a solidly built feature with great performance eclipsing other competing solutions on the market.
jauntywundrkind
Pretty good write up, talking to the problem, surveying what and how other players do things? Went looking to see if there was going to be anything open (mostly it's product pitch), found: > Iceberg support builds on the Hudi-backed indexing work in Apache XTable (Incubating). We developed the design in the open with engineers from Uber and Walmart to support their planet-scale tables. The open RFC documents the storage layout, query path and consistency model. > The design is settled and ships in Lakegres today; the Hudi implementation is being upstreamed and XTable is in release-candidate testing ahead of OSS releases that other engines can integrate. With two links inline, https://github.com/apache/incubator-xtable/pull/935 https://github.com/apache/hudi/blob/master/rfc/rfc-109/rfc-1...
sherlockbeard
any measured commit latency overhead from the vector index on a streaming job, once it's built? post benchmarkss build time + query latency but not the write path stuff.
rjshmhndr
vector search with < 100msecs on a lake is unheard of - pretty impressive