Developing and Serving RAG-Based LLM Applications in Production

Explore a comprehensive guide for developing retrieval augmented generation (RAG) based LLM applications in production. Learn about scaling techniques for embedding, indexing, and serving, as well as component-wise and overall evaluation methods. Discover advanced topics like hybrid routing to bridge the gap between open-source and closed LLMs. Gain insights on evaluating RAG-based LLM applications to identify and productionize optimal configurations. Understand how to develop LLM applications with scalable workloads using minimal code changes. Explore the potential of Mixture of Experts (MoE) routing in enhancing LLM performance. Access the accompanying slide deck for visual references and additional information on developing and serving RAG-based LLM applications at scale.

Developing and Serving RAG-Based LLM Applications in Production