BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//global2023.pydata.org//cfp//8VYY8L
BEGIN:VEVENT
UID:pretalx-cfp-BWN7JQ@global2023.pydata.org
DTSTART:20231206T190000Z
DTEND:20231206T193000Z
DESCRIPTION:With LanceDB you can make your laptop more powerful than any di
 stributed vector database for semantic search. LanceDB is an open-source e
 mbedded vector database. It's lightweight like SQLite but powerful enough 
 to deliver real-time semantic search over a billion vectors on a laptop.\n
 LanceDB is backed by Lance columnar format\, which delivers up to 100x per
 formance improvement over parquet for managing multimodal AI data (e.g.\, 
 vectors\, images\, point clouds\, and more). With it\, Lance gives AI team
 s a high performance single-source of truth across the whole AI life-cycle
  from analytics to training to debugging.\n\nIn this talk we'll cover the 
 use cases for production inference and in the data lake. We'll talk about 
 the technical details of the Lance columnar format and what makes it diffe
 rent. And we'll show a demonstration of LanceDB for multi-modal semantic s
 earch.
DTSTAMP:20250709T214719Z
LOCATION:Data Track
SUMMARY:LanceDB: lightweight billion-scale vector search for multimodal AI 
 - Chang She
URL:https://global2023.pydata.org/cfp/talk/BWN7JQ/
END:VEVENT
END:VCALENDAR