Exa-Scale Search with Lance and Ray

​*Please register here: http://events.builder.aws.com/d/73q3y1

​Join LanceDB, Anyscale, and Exa for a look inside the infrastructure powering Exa’s AI search engine!

​Exa ingests and processes web-scale data — continuously crawling, deduplicating, generating embeddings, and updating search signals across billions of documents. At the core of this system are Lance, providing fast multimodal storage and efficient vector access, and Ray, powering distributed processing and large-scale embedding pipelines.

​We’ll share how Lance and Ray form the foundation of Exa’s search stack, enabling scalable ML workloads and high-performance semantic retrieval.

​If you’re building AI search, large-scale retrieval systems, or ML data pipelines — this session is for you! Come learn how Exa runs search on Lance + Ray, and meet the teams behind the stack.

​Speakers

• ​Lei Xu, CTO @ LanceDB

• ​Goutam Venkatramanan, Software Engineer @ Anyscale

• ​Hubert Yuan, Software Engineer @ Exa