JUPYTER NOTEBOOK01
Your RAG pipeline needs a test set
Measure retrieval recall per question and compare pipeline changes against a versioned evaluation set.
Essays, notebooks, and field notes connected by rag.
Measure retrieval recall per question and compare pipeline changes against a versioned evaluation set.
A LangGraph loop that separates retrieval failures from writing failures and retries each one differently.
A practical map of retrieval quality, answer quality, and the tests needed before a grounded answer earns trust.