2024-05-07 –, Moskau
When we work with information systems, we capture information in text and find information with text queries. Advances in AI have made it possible to move from word-to-word matching to something like meaning-to-meaning matching. Learn how search and OpenSearch unlock the meaning in your information.
This session is foundational, covering why we search, and how we search to retrieve the best results. I will cover the core search algorithm, BM25 scoring, vectors (dense and sparse), LLMs, embedding generation and the neural and kNN plugins, exact, and approximate scoring. I will demo different modalities with this site: https://ml-search-331750873.us-east-1.elb.amazonaws.com/ (time permitting)
Jon Handler is a Senior Principal Solutions Architect on the OpenSearch Service team at Amazon Web Services, based in Palo Alto, CA. Jon works closely with OpenSearch and Amazon OpenSearch Service, providing help and guidance to a broad range of customers who have search and log analytics workloads for OpenSearch. Prior to joining AWS, Jon’s career as a software developer included four years of coding a large-scale, eCommerce search engine. Jon holds a Bachelor of the Arts from the University of Pennsylvania, and a Master of Science and a Ph. D. in Computer Science and Artificial Intelligence from Northwestern University.