Wire judge-prompt localization into factory and inline scorer

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

rag_eval/metrics/factory.py

@@ -24,6 +24,7 @@ from ragas.metrics.collections import (
     SemanticSimilarity,
 )
 
+from .judge_prompts import localize_pipeline_prompts
 from .pipeline import MetricPipeline
 
 
@@ -133,7 +134,11 @@ def build_metric_pipeline(
 
     # Build the full registry once using the shared factory, then slice by requested metrics.
     registry = build_metric_registry(llm, embeddings)
+    selected = {name: registry[name] for name in scenario.metrics}
+    # Apply language-specific judge prompt localization (no-op for 'en').
+    language = scenario.judge_language or settings.ragas_judge_language or "en"
+    localize_pipeline_prompts(selected, language)
     return MetricPipeline(
-        metrics={name: registry[name] for name in scenario.metrics},
+        metrics=selected,
         metric_timeout_seconds=settings.ragas_metric_timeout_seconds,
     )