Key Highlights
- Zilliz introduced Vector Lakebase in public preview on Zilliz Cloud.
- The platform combines vector search, analytics, and data discovery in one place.
- It is available in public preview and supports 30+ regions across AWS, Google Cloud, and Microsoft Azure.
Zilliz, the company behind Milvus, has launched Vector Lakebase, a new platform designed to help enterprises manage AI data workloads from a single data foundation.
The company announced that Vector Lakebase is now available in public preview through Zilliz Cloud, expanding beyond real-time vector search to include interactive data discovery, batch analytics, and direct search on external data lakes.
Zilliz said the platform is designed to help organizations avoid the delays and added costs that come with moving data between different systems.
“Production vector search is and will remain at the heart of what Zilliz does – it’s why thousands of teams choose Milvus and Zilliz Cloud, and it’s getting faster and more cost-efficient every release,” said Charles Xie, Founder and CEO of Zilliz.
“Vector Lakebase is what we believe comes next: one data foundation where the same vectors can serve a production query, anchor a discovery session, and power a multi-petabyte training-data pipeline – without copies, migration, or a parallel stack,” Xie added.
Platform Combines Search, Analytics and Data Discovery
According to Zilliz, AI teams often use separate systems for serving queries, exploring datasets and processing large amounts of information. Moving billions of vectors between those systems can take time and increase operational costs.
The company said Vector Lakebase is built to solve that problem by allowing multiple workloads to run on the same logical copy of data.
The platform keeps real-time vector search at its core while also enabling interactive discovery and large-scale analytics. Zilliz said customers can run workloads across cloud, edge and on-premises environments without having to repeatedly copy or migrate data.
Robert Guo, Vice President of Product at Zilliz, said companies had been looking for a way to manage different workloads without separating data into multiple systems.
“Teams asked for a way to keep their data in one place and run very different workloads against it – from real-time agent memory to overnight semantic deduplication,” Guo said.
Zilliz said the platform introduces several new capabilities, including tiered real-time serving, on-demand search, external data lake search, and full-spectrum AI search across vectors, text, JSON and geospatial data.
The company also said the system is built on Vortex, an open columnar storage format designed to improve read speeds and reduce costs for AI workloads.
Vector Lakebase is currently available in public preview through Zilliz Cloud and supports deployments across more than 30 regions on AWS, Google Cloud and Microsoft Azure. New users signing up with a work email can receive $100 in free credits, according to the company.
Read more related news on Big Data or Data Analytics.