GenAI Recipes for Cloud Native Deployment Using OPEA Framework

Explore a 37-minute conference talk that delves into practical implementations of Generative AI applications in cloud-native environments using OPEA (Open Platform for Enterprise AI). Learn about this new Linux Foundation project that offers a framework of composable microservices for state-of-the-art GenAI systems, including LLMs, data stores, and prompt engines. Discover how to deploy GenAI applications on Kubernetes clusters across various hyperscalers, and understand the implementation of RAG capabilities using both opensource vector databases and managed services. Gain insights from scale testing results with 50K documents and understand the blueprints for end-to-end workflows in popular applications like ChatQnA, CodeGen, and RAG systems. Master the deployment of GenAI applications in a cloud-native way while learning about specific contribution opportunities within the OPEA framework.