Databricks makes Lakebase Search GA, benchmarks show it beating Pinecone at far lower cost
matei_zaharia · x · 2026-11-11
Databricks' Lakebase Search is now generally available on AWS and Azure, bringing vector, BM25 full-text, and hybrid search into the same Postgres database as operational data—no separate search engine or ETL pipeline, searchable via SQL against live data. Benchmarks show 1500-2000 QPS at 80-112 CUs, outperforming Pinecone Serverless ($80/hr, low throughput), Zilliz Cloud, and pgvector/DiskANN setups.
More from Infra
- CoreWeave upgrades to CNCF Platinum member, runs its GPU cloud entirely on Kubernetes — altryne · 2026-11-11
- SpaceX teams with Qualcomm to build AI-native base stations, eyeing first AI carrier — elonmusk · 2026-11-11
- Prism capability extraction: specialists carved from Qwen 27B at <20% memory match full model — tokenbender · 2026-11-11
- Apple reportedly building Harbor app to turn Macs into private AI inference servers with Thunderbolt 5 clustering — BenBajarin · 2026-11-11
- Agent Arena: Gemini 4 Carbon Gets More Cost-Competitive as Tasks Get Harder — rseroter · 2026-11-11
- AMD Zen 6 deep dive: cheaper branch mispredicts and a return to Zen 3/4 integer scheduling — jedisct1 · 2026-11-11