RAG Evaluation

Goal: Learn to measure retrieval and answer quality separately (faithfulness, groundedness, relevance) so you can pinpoint exactly where a RAG system breaks and fix it.

Do:

1. Read this guide: https://www.ibm.com/think/tutorials/evaluate-rag-pipeline-using-ragas-in-python-with-watsonx

2. Complete this course https://learn.deeplearning.ai/courses/building-evaluating-advanced-rag/