Generative AI and the emergence of LLMs are radically changing content retrieval and generation industries. Using a combination of Natural Language Processing (NLP) techniques, foundation Machine Learning models (GPT and friends), and vector databases, chat-driven smart applications are changing the landscape of modern apps. This presentation explores the Retrieval-Augmented Generation (RAG) approach, which leverages semantic search to dynamically infuse factual knowledge into a large language model (LLM) prompt. This technique enables contextual augmentation of the LLM, enhancing its performance in various tasks such as answering questions, summarizing content, or generating new content. Redis, a vector database and full-text search engine, enables RAG workflows. In this session, we'll explore building RAG applications using Redis and Spring Boot.