Multimodal Vector Databases with LanceDB

Welcome back to LAML!!!!!! It's been a while since we've hosted a Meetup, but we're excited to bring it back. Please come join us Zefr as we talk about how to store information in LanceDB (a vector database) and how that data is used to power AI applications.

Here is the schedule:

5:30 Meetup attendees arrive
5:30 - 6:30 Pizza and mingling
6:30 - 7:15 Presentation
7:15 - 7:30 Q&A
8 PM Doors close

Abstract:

Come learn how AI leaders from ByteDance, Runway, Midjourney, Character AI, and Second Dinner scale multimodal applications and cut down data plumbing, speed up experimentation, and ship AI features faster by unifying their multimodal data with LanceDB, a high-performance, AI-native database built for multimodal workloads. It combines lightning-fast vector search with a columnar format optimized for raw content, metadata, and embeddings. Hear about common challenges

Speaker Bio:
Jonathan Hsieh is a member of the technical staff at LanceDB. Most recently, he has been an independent consultant advising startups building AI and LLM-powered RAG services. Previously he has had product management roles focused on lineage and anomaly detection at Bigeye, and data governance and cloud deployments Cloudera. Preceding that, he was a principal engineer/tech director for Cloudera’s internal engineering infrastructure team and the tech lead/manager for Cloudera’s the Apache HBase team. Jonathan has an M.S. in Computer Science from University of Washington and also has an M.S. and a B.S. in Electrical and Computer Engineering from Carnegie Mellon University.