AWS re:Invent 2023 - Making semantic search & RAG real: How to build a prod-ready app (AIM201)

Private data retrieval is a key to the puzzle that is making LLMs work at scale. However, is it really about the fastest kNN implementation that can return search results? For developers to build magical search experiences at scale, you’ll need fast kNN search, but you’ll also need it to be simple, repeatable, and secure. You’ll want elegant APIs that can store, sort, search, and aggregate data across data stores, middleware, and internal apps while ticking every box—RBAC, HA, DR—across clouds and on premises. Learn what it takes to operationalize enterprise-grade AI search with LLMs. This presentation is brought to you by Elastic, an AWS Partner.

Subscribe:

ABOUT AWS
Amazon Web Services (AWS) hosts events, both online and in-person, bringing the cloud computing community together to connect, collaborate, and learn from AWS experts.

AWS is the world's most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Millions of customers—including the fastest-growing startups, largest enterprises, and leading government agencies—are using AWS to lower costs, become more agile, and innovate faster.

#AWSreInvent #AWSreInvent2023

[MarkuBernardut]

Wow Professor Heldebrant gave an amazing dissertation of the value of Elasticsearch when using vector search and LLMs. Obviously the best holistic tool for Semantic Search

[bartoszwesoowski]

Great presentation - would be great to have some hands on presentation that would present how to work with this and for example how to build an actual app using this approach ;)