End-2-End Evaluation of RAG-Based Applications | LLM Evaluation


In this session, Noam Bressler and Shay Tsadok from Deepchecks discussed the methodologies and best practices for evaluating RAG-based systems, covering initial experiments, version comparison, and ongoing evaluation in production. 🚀

Sign up for Deepchecks LLM Evaluation Solution here:

Topics that were covered:

✅ Setting up initial experiments for RAG systems.

✅ Methods for comparing different versions of RAG systems.

✅ Continuous evaluation techniques in production settings.

✅ Strategies for effective performance evaluation, including relevant metrics and tools.

LLMOps.Space LLMOps.Space

Deepchecks is a founding member of LLMOps.Space, a global community for LLM
practitioners. The community focuses on LLMOps-related content, discussions, and
events. Join thousands of practitioners on our Discord.
Join Discord ServerJoin Discord Server