Evaluating RAG in Python: Retrieval Metrics, Faithfulness and Regression Tests
A golden set, recall@k, MRR, nDCG, claim-level faithfulness and a pytest gate that fails the build when quality drops
A golden set, recall@k, MRR, nDCG, claim-level faithfulness and a pytest gate that fails the build when quality drops
Retrieval-augmented generation looks easy in a demo. Load a few PDFs, split them into chunks, embed them, store the vectors, retrieve the top five, and ask a model to answer. On ten hand-picked questi
