update for ragas

rag_eval/advisor/writer.py

@@ -29,10 +29,15 @@ def _format_log_summary(diagnoses: list[Diagnosis], advice_path: Path) -> str:
 
 
 def _build_fallback_report(diagnoses: list[Diagnosis]) -> str:
-    """Build a rules-only report when LLM analysis is unavailable."""
+    """Build a rules-only report when LLM analysis is unavailable.
+
+    Even without the LLM, embed each metric's worst sample(s) — question,
+    answer, ground truth — so the advice still references concrete problems
+    instead of reading as a purely generic template.
+    """
     if not diagnoses:
         return ""
-    lines = ["## 规则诊断（LLM 分析不可用）\n"]
+    lines = ["## 规则诊断（LLM 分析不可用，以下为规则引擎输出）\n"]
     for d in diagnoses:
         label = _SEVERITY_LABEL.get(d.severity, d.severity)
         lines.append(f"### {d.metric}  [{label}]  均值={d.mean_score:.4f}")
@@ -42,6 +47,22 @@ def _build_fallback_report(diagnoses: list[Diagnosis]) -> str:
         lines.append("\n**建议动作：**")
         for action in d.suggested_actions:
             lines.append(f"- {action}")
+        if d.low_samples:
+            lines.append("\n**低分样本举例拆解：**")
+            for i, sample in enumerate(d.low_samples, 1):
+                score = sample.get(d.metric, "N/A")
+                question = str(sample.get("question", "")).strip() or "（无问题文本）"
+                lines.append(f"\n- **样本 {i}**（{d.metric}={score}）问题：{question}")
+                answer = str(sample.get("answer", "")).strip()
+                if answer:
+                    lines.append(f"  - 生成答案：{answer[:200]}")
+                ground_truth = str(sample.get("ground_truth", "")).strip()
+                if ground_truth:
+                    lines.append(f"  - 标准答案：{ground_truth[:160]}")
+                lines.append(
+                    f"  - 拆解：该样本 {d.metric} 偏低，请对照上述「可能原因 / 建议动作」"
+                    f"重点排查本问题的检索片段与生成答案。"
+                )
         lines.append("")
     return "\n".join(lines)