Building Easily Deployable RAG Applications with Llamastack

Learn to build and deploy production-ready Retrieval Augmented Generation (RAG) applications using Llamastack in this 11-minute conference talk from DevConf.US 2025. Discover how to overcome the complexity of moving RAG applications from concept to production by developing a specialized chatbot that provides context-aware insights into GitHub repositories. Explore Llamastack's unified API framework that streamlines the RAG development lifecycle through integrated agents, tooling, and vector I/O capabilities. Master automated deployment techniques using Helm charts for seamless orchestration on OpenShift, creating scalable and robust infrastructure for large language models and vector databases. Gain practical knowledge and tools to transform RAG concepts into production-scale applications with simplified development and deployment processes.