In recent years, ML techniques have become increasingly popular to enhance search. Among them are the use of embedding models, a type of model that can encode a large body of data into vectors. By searching for the nearest vectors to encoded documents you can find the most semantically similar documents and enable use cases such as semantic search, RAG, recommendation engines and rich media search.

Join this session to explore the transformational impact of using the vector engine for Amazon OpenSearch  Serverless as one way to build scalable and future-proof AI applications in Financial Services.

Two hands-on labs will be delivered where you will be working with your assigned AWS technical consultant to learn how to use Amazon OpenSearch Service as Gen AI enabled multi-modal search and observability solutions.

Who Should Attend

Application developers, Data scientists, ML-scientists, Database developers, ML-Engineers, CTO, CIO

Featured Speakers

• Ashley Mitchell - Sr OpenSearch GTMS
• Hugh Christensen - Principal Analytics Specialist
• Praveen Mohan Prasad - Sr Technical Account Manager, Big Data

Agenda

Welcoming Note

How Financial Services customers are utilizing Gen AI Search

Amazon OpenSearch Service Overview and highlights

Lab1 - Semantic & Vector Search

Security analytics/ SIEM with Security Lake

BigData Boutique - Transforming Search: OpenSearch, ML, and Generative AI

What's New in Amazon OpenSearch Service

Lab 2- Observability workshop

Closing