Generative AI on AWS: Building Meta XR Apps, Agentic Code Interpreter, Multi-Modal RAG
Join us for this in-person special at the AWS GenAI Loft in San Francisco with a special guest speaker from Meta!
From Multi-Modal Breakthroughs and Building XR Applications to Code-Savvy Assistants and Multi-Modal RAG.
Agenda:
5.00pm: Doors open
5:00pm-6:00pm: Checkin, food, and networking
6:00pm-6:10pm: Welcome, Community update
6:10pm-8:00pm: Tech talks and Q&A
8:00pm-8:30pm: Open discussion, mixer, and closing
Tech Talks, starting at ~6:10pm PT:
Intro: Recent Advancements in Multi-Modal Gen AI - Segment Anything Model 2 by Meta
By Antje Barth, Principal Developer Advocate, Generative AI @ AWS
As generative AI continues to evolve at a rapid pace, we're witnessing a paradigm shift towards multi-modal models that can seamlessly integrate and generate across various forms of data. This talk explores the recent advancements in multi-modal generative AI with a focus on the Segment Anything Model 2 by Meta.
Talk #1 Creating Extended Reality (XR) Applications on the Web
By Felix Zhang, Immersive Web Engineer @ Meta Reality Labs
Explore how to create cutting-edge Extended Reality (XR) applications, from integrating Generative AI for immersive 3D environments and realistic interactions to building productivity-boosting utility applications and WebXR-based e-commerce solutions. Whether you're an experienced XR developer or new to the field, this session will provide practical insights and real-world examples to help you unlock the full potential of XR.
Talk #2 AI running it’s own code: Agentic Code Interpreter
By Mike Chambers, Senior Developer Advocate, Generative AI @ AWS
AI and large language models often face challenges when it comes to complex data analysis and mathematical operations, limiting their utility in solving sophisticated problems. This session shows how Agentic Code Interpreters bridge this gap, allowing AI agents to execute code and tackle tasks like data visualization and advanced analytics. Discover how this innovation can transform your workflows and unlock new possibilities for AI-driven solutions.
Talk #3 Beyond text: A multimodal chat interface with storage, compute, and web access
By Danilo Poccia, Principal Developer Advocate, Generative AI @ AWS
In this session, we’ll dive deep into enhancing a basic chat by adding multimodal support, persistent storage, document and image access, computational abilities, web search, and connectivity. We’ll use multiple large language models (LLMs) via Amazon Bedrock Converse API. With tool use, we’ll give the model new capabilities. We’ll implement a multimodal in-memory or on-disk vector store to process long content more efficiently and out of context.
Notes:
* Please use your full name for registration and bring gov ID for security check.
* Snacks and drinks will be provided.