chore: run full RAGAS eval — all 4 metrics now populated cf657d7 benroshan Claude Sonnet 4.6 commited on May 31
chore: update RAGAS benchmark with real scores (faithfulness=1.0, answer_relevancy=0.90) 6b88803 benroshan Claude Sonnet 4.6 commited on May 30
feat: RAGAS benchmark driven by JSON, local runner script c549f0b benroshan Claude Sonnet 4.6 commited on May 30