Effortlessly Build, Run, Secure, and Manage Traffic for a Generative AI Application From Scratch

Learn to build, deploy, and manage a complete generative AI application from the ground up in this comprehensive demo-driven conference talk. Discover how to navigate key decisions when developing GenAI applications, including selecting appropriate Large Language Models (LLMs) and implementing Retrieval-Augmented Generation (RAG) for enhanced functionality. Master the process of transitioning from native application setup to Kubernetes deployment while incorporating domain-specific knowledge through RAG techniques. Explore essential cloud-native tools including Kubernetes, Prometheus, Kiali, Istio, and the Kubernetes Gateway API to ensure secure, efficient operation with robust observability and debugging capabilities. Gain practical insights into managing API calls, controlling costs for external LLMs, and implementing comprehensive traffic management strategies for production-ready generative AI applications.