Lakebase Search
GALast seen at this status: 2026-09-18·42d ago
Adds vector, keyword and hybrid search to Lakebase Postgres through two extensions: lakebase_vector, a pgvector-compatible approximate nearest-neighbor index, and lakebase_text, a BM25 full-text index. The two can be combined to return semantic and exact-term matches in one ranked list without a separate search system.
Status history
- GA
- Beta2026-06-16 · Jun 2026Release notes
Sources (4)
- 2026-09-28Databricks Blog GA
- 2026-09-18Release notes GA
- 2026-06-16Release notes Beta
- —Databricks Blog
Recent coverage
- 2026-10-29Creating a Digital Twin with Spark Real-Time Mode and Lakebase video
- 2026-10-26How to teach with Databricks Free Edition news
- 2026-10-26The media industry is becoming a prediction economy news
- 2026-10-26Lakebase Search: Build AI Retrieval for Agents with Lakebase Postgres video
- 2026-10-23Real-time energy trading and analytics on Databricks news
- 2026-10-22The Fraud Analyst AI Coworker: Detecting Telecom Fraud in Real-Time on One Platform news
Status and dates are extracted from public sources only. We don't see the private AE-shared roadmap. If something looks wrong, tell us.