What's New in Milvus 3.0- Live Walkthrough & AMA with Core Maintainers

Jun 08, 2026 16:00 Pacific

Jun 08, 2026 19:00 Eastern

Zilliz Webinar | Zoom

Join the Webinar

About webinar:

Milvus 3.0 beta is the biggest architectural upgrade since the project began — Milvus can now index and query vectors directly on your data lake, and its query engine goes well beyond top-K.

Join core maintainers Liu Li and Jiang Chen for a live walkthrough of what shipped, what it solves, where the roadmap is heading, and a first look at Milvus 3.0 on Zilliz Cloud alongside Zilliz Vector Lakebase. Bring your questions — the last 15-20 minutes are open AMA.

What You'll Expect

First-hand walkthrough from the engineers who built it — not a recap of the release notes, but the design decisions behind Milvus 3.0 and why they matter for your stack
A clear picture of the roadmap — what's in beta now, what's coming in GA, and the timeline
Zilliz Vector Lakebase preview — how Milvus 3.0 powers Zilliz Vector Lakebase, and what it means for managed users
Direct access to core maintainers — 15 -20min live AMA, ask anything: migration, performance, architecture, timeline

Milvus 3.0 Highlighted Features

External Collection — Define a Milvus Collection over data that stays in S3, Iceberg, Lance, Parquet, or Vortex
Vortex + Lance Support — Support next-gen open columnar formats inside Milvus
Snapshot — Point-in-time MVCC views for batch and discovery jobs alongside serving
Spark Connector — Use Milvus as a Spark SQL table
Flexible Schema — Add, backfill, or drop columns at runtime
TEXT LOB — Store large text fields natively in Milvus
Search / Query Order By — Push multi-field sorting into the engine
Search / Query Aggregation — Support scalar aggregation and vector-native faceting
StructList Family — Support one entity, many vectors workloads
Entity TTL and RLS — GDPR-friendly Entity TTL and row-level security for multi-tenant SaaS
And More...

Meet the Speaker

Join the session for live Q&A with the speaker

Li Liu
Director of Engineering
Li Liu is the Director of Engineering at Zilliz, leading vector search research and development. Before joining Zilliz, he was a Senior Engineer at Meta, designing and shaping numerous advertising stream data frameworks. With a Master's degree from Carnegie Mellon University, he boasts extensive experience in databases and big data. Li Liu's expertise in technology and innovation continues to drive advancements in vector searching, leaving a lasting impact on the field.
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.