Webinar
From Vector Database to Vector Lakebase
Join the Webinar
Loading...
About Webinar
Zilliz Vector Lakebase is now available in public preview on Zilliz Cloud — a major evolution that pairs the production vector database with a shared, lake-native data foundation. One source of truth now serves multiple workloads — online serving, iterative discovery, and batch analytics — and lets you index and search directly on open formats like Iceberg, Lance, and Parquet, with no data movement.
Join Zilliz CTO James Luan and Jiang Chen (Director of Technical GTM) for a live walkthrough of what a Vector Lakebase is, the architecture behind it, and how it collapses online serving, on-demand search, and batch processing onto one copy of your data — across production RAG, agentic memory, semantic search, recommendation systems, LLM training-data deduplication, data mining, and more.
What You'll Expect
- A clear view of Vector Lakebase and where it fits your stack — what it actually is, and how it relates to the Milvus, vector database, and lakehouse you already run.
- One copy of data, no sync tax — how online serving, on-demand search, and offline batch run on the same lake data instead of three systems wired together by copy-and-sync pipelines.
- How vector lakebase actually works under the hood — the design behind One Data / One Index / One Semantic Layer: indexes that lazy-load on object storage, External Collection over your existing Iceberg / Lance / Parquet, and full-spectrum (vector + text + JSON + geo + hybrid) search on one query plane.
- Proof at your scale — concrete numbers you can map to your own stack: a real workload that costs ~$7,000/month on a dedicated cluster running under $500 on on-demand compute, and 1B vectors indexed directly from Iceberg in ~20 minutes with no data movement.
- Live AMA with Zilliz core engineers — bring your own architecture, performance, migration, and cost questions for James Luan (Zilliz CTO, Milvus maintainer) and Jiang Chen (ex-Google web-scale search). The last 20 minutes are yours.
Vector Lakebase Highlighted Features
- Tiered Serving Solutions — Match real-time vector workloads with the right serving tier for performance, efficiency, or large-scale cost optimization.
- On-Demand Search — Run infrequent search, data exploration, and batch-style analytics without keeping compute always on.
- External Data Lake Search — Add vector indexing and large-scale search directly to existing lake data without moving the original files.
- Full-Spectrum Search — Combine vector, text, JSON, geo, hybrid retrieval, filtering, and reranking in one semantic layer.
- Unified Lake-Native Storage — Use Vortex-based storage to support both serving and analytics with faster random reads and flexible per-column formats.
Meet the Speaker
Join the session for live Q&A with the speaker
James Luan
CTO of Zilliz
James Luan is the CTO of Zilliz. With a master's degree in computer engineering from Cornell University, he has extensive experience as a Database Engineer at Oracle, Hedvig, and Alibaba Cloud. James played a crucial role in developing HBase, Alibaba Cloud's open-source database, and Lindorm, a self-developed NoSQL database. He is also a respected member of the Technical Advisory Committee of LF AI & Data Foundation, contributing his expertise to shaping the future of AI and data technologies.
Jiang Chen
Director of Technical GTM
Jiang is currently Director of Technical GTM at Zilliz. He has years of experience in data infrastructures and cloud security. Before joining Zilliz, he had previously served as a tech lead and product manager at Google, where he led the development of web-scale semantic understanding and search indexing that powers innovative search products such as short video search. He has extensive industry experience handling massive unstructured data and multimedia content retrieval. He has also worked on cloud authorization systems and research on data privacy technologies. Jiang holds a Master's degree in Computer Science from the University of Michigan.