バージョンごとの RAG 取得品質の評価

SELECT
  pipeline_version,
  COUNT(*) AS test_cases,
  100.0 * SUM(CASE WHEN relevant_document_retrieved THEN 1 ELSE 0 END)
    / NULLIF(COUNT(*), 0) AS retrieval_relevance_pct,
  100.0 * SUM(CASE WHEN answer_grounded THEN 1 ELSE 0 END)
    / NULLIF(COUNT(*), 0) AS grounded_answer_pct,
  AVG(retrieval_latency_ms) AS avg_retrieval_latency_ms,
  SUM(cost_usd) AS evaluation_cost_usd
FROM rag_evaluation_events
WHERE timestamp_utc >= now() - INTERVAL '30 days'
  AND environment = 'evaluation'
GROUP BY pipeline_version
ORDER BY grounded_answer_pct DESC, retrieval_relevance_pct DESC, pipeline_version;