Zilliz previews Vector Lakebase for one-copy AI search data
Vector Lakebase is now available in public preview on Zilliz Cloud. It combines a production with a shared lake-native data base, so teams can use one copy of their data for online serving, on-demand search, and . The main promise is fewer data moves and fewer duplicate stores across different workloads.
The webinar will explain how Vector Lakebase fits next to Milvus and existing . It will also cover external collections on Iceberg, Lance, and Parquet, plus one data layer, one index, and one . Search support is described as covering vector, text, JSON, location data, and .
The speakers are James Luan, Zilliz CTO and Milvus maintainer, and Jiang Chen, Director of Technical GTM at Zilliz. The webinar is scheduled for July 1, 2026 at 11:00 AM PDT.
Key points
- Vector Lakebase is in public preview on Zilliz Cloud.
- It is designed to use one data copy for online serving, on-demand search, and .
- The webinar will explain how it relates to Milvus and .
- It mentions external collections over Iceberg, Lance, and Parquet.
- It covers vector, text, JSON, location, and .