Serverless billion-scale vector search for AI applications
Room: Saphire B - PyData
Time: 14:00 - 14:25
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. 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.
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.