Mastering RAG Evaluation with MLflow and Open Source LLMs

Dive into this comprehensive tech tutorial where Cyril Kondratenko and Mikhail Rozhkov demonstrate how to evaluate Retrieval-Augmented Generation (RAG) pipelines using MLflow and open-source Large Language Models. Learn to implement and track LLM-specific metrics, optimize RAG systems, and manage experiments efficiently. Follow along as they explain the setup process for MLflow, creation of custom metrics, and evaluation techniques for different RAG pipeline components. Gain practical skills for visualizing results and enhancing the performance of RAG systems through this 88-minute session recorded at DSC EUROPE 24 in Belgrade on November 19th.