Retrieval Augmented Generation (RAG) has quickly become a popular choice for building intelligent AI applications, yet taking one from concept to production can often be complex. This workshop aims to demystify that process, showing you just how straightforward it is to create and deploy powerful RAG applications. We'll walk through the development and OpenShift deployment of a simple chatbot that provides specialized insight into GitHub repositories, delivering context-aware answers based on the repository's content.

You'll discover how Llamastack, a powerful API layer, simplifies the entire RAG development lifecycle by providing a unified framework for agents, tooling, and vector I/O. We'll also dive into automated deployment capabilities, demonstrating how Helm charts enable seamless orchestration on OpenShift, giving you a scalable and robust infrastructure for your LLM and vector database. This workshop will equip you with the practical knowledge and tools to bring your RAG ideas to life at scale.