This is the website for an older EuroPython. Looking for the latest EuroPython? Click here!
Skip to main content

Serverless billion-scale vector search for AI applications

north hall
30 minutes


From recommendation systems to LLM-based applications, vector search is a critical component of the modern AI workflow. Existing vector solutions are complicated to use, hard to maintain, and cost too much. LanceDB is a free open-source vector store that can perform low latency vector search on billion-scale vector datasets on a single node.

TalkPyData: Deep Learning, NLP, CV


LanceDB is powered by Lance format, a modern columnar data format for machine learning and data science. Compatible with pandas/polars/duckdb, Lance format supports vector index, predicate pushdown, and random access performance 2000x faster than parquet.

This talk will:

  1. Introduce LanceDB and show some example workflows
  2. Outline Lance format design and what makes it so fast
  3. Review the Lance roadmap and ecosystem integrations

You can find Lance here:

The speaker

Chang She

Chang She

Chang is the CEO/Co-founder of Eto Labs and a co-creator of LanceDB, a new open source vector database that supports low-latency vector search on billion-scale vectors on a single node. Previously Chang was VP of Engineering at Tubi TV and was a co-author of the pandas library from 2009-2014.

← Back to schedule