Building RAG-based LLM Applications for Production - LLMs III Talk

Explore the development and deployment of RAG-based LLM applications for production in this 30-minute talk by Philipp Moritz and Yifei Feng. Learn how to scale major workloads like data loading, preprocessing, embedding, and serving on a cluster. Discover techniques for evaluating different configurations and deploying applications effectively. Gain insights into Anyscale Endpoints, a cost-effective solution for serving popular open-source models. Benefit from the expertise of Philipp Moritz, co-creator of Ray and CTO of Anyscale, and Yifei Feng, who leads Infrastructure and SRE teams at Anyscale, as they share their knowledge on building scalable AI applications.

Building RAG-based LLM Applications for Production // Philipp Moritz & Yifei Feng // LLMs III Talk