# Retrieval recall, per question, per intent
def evaluate_retrieval(reference_set, retrieve_fn):
    rows = []
    for ref in reference_set:
        retrieved_lines = retrieve_fn(ref.question)
        recall = len(set(retrieved_lines) & set(ref.expected_lines)) / len(ref.expected_lines)
        rows.append({
            "question": ref.question,
            "intent":   ref.intent,
            "recall":   recall,
            "hit":      recall > 0,
        })
    return pd.DataFrame(rows)
# Always break down by question type, never just an aggregate
df.groupby("intent")["hit"].mean()
# point_lookup        0.92
# section_retrieval   0.41   <-- this is the real problem
# comparison          0.55