In this session, discover how AWS storage solutions form the backbone of advanced AI techniques, particularly Retrieval-Augmented Generation (RAG). We'll explore how traditional storage and databases support RAG implementations, then dive into Vector RAG and semantic search capabilities that enhance AI model performance through contextually relevant data retrieval. Whether you're customizing foundation models or building your own, you'll learn how to harness the full potential of your data for generative AI initiatives. This session is ideal for developers, data scientists, and AI/ML practitioners with basic understanding of AI/ML concepts and AWS services. In the hands-on portion, participants will build a custom RAG application using their choice of vector database, gaining practical experience with AWS's comprehensive suite of AI tools while implementing real-world use cases for semantic search and context-enhanced generation.

The agenda will include:

• Deep dive into data foundations for generative AI
• Deep dive into Vector RAG and Vector Databases
• Interactive Q&A with AWS experts
• Hands-on workshops, demos, and networking opportunities