Watch a 44-minute conference talk from GOTO Chicago 2024 exploring how to build domain-specific generative AI chatbots using serverless technologies. Learn essential terminology and architectural options for working with Large Language Models (LLMs) through AWS services. Discover how to leverage embeddings with Retriever-Augmented Generation (RAG) and AWS Step Functions to streamline GenAI application development. Follow along with a practical demonstration showing how Amazon Bedrock simplifies LLM interactions. Principal Developer Advocate for Serverless at AWS, Eric Johnson, breaks down complex concepts into clear, actionable insights for creating effective and targeted GenAI applications. Access the complete source code on GitHub to implement these solutions in your own projects.