Wire judge-prompt localization into factory and inline scorer

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

webapp/services/inline_scorer.py

@@ -14,6 +14,7 @@ from typing import Any
 
 from rag_eval.compat import ensure_ragas_import_compat
 from rag_eval.metrics.factory import build_metric_registry, build_models
+from rag_eval.metrics.judge_prompts import localize_pipeline_prompts
 from rag_eval.metrics.pipeline import MetricPipeline
 from rag_eval.settings import EvaluationSettings
 from rag_eval.shared.models import NormalizedSample
@@ -21,10 +22,14 @@ from rag_eval.shared.models import NormalizedSample
 ensure_ragas_import_compat()
 
 
-def _build_metric_instances(metrics: list[str], llm: Any, embeddings: Any) -> dict[str, Any]:
-    """Instantiate only the RAGAS metric objects requested."""
+def _build_metric_instances(
+    metrics: list[str], llm: Any, embeddings: Any, judge_language: str = "en"
+) -> dict[str, Any]:
+    """Instantiate only the RAGAS metric objects requested, localized if needed."""
     registry = build_metric_registry(llm, embeddings)
-    return {name: registry[name] for name in metrics if name in registry}
+    selected = {name: registry[name] for name in metrics if name in registry}
+    localize_pipeline_prompts(selected, judge_language)
+    return selected
 
 
 class InlineScorer:
@@ -69,10 +74,11 @@ class InlineScorer:
         judge_model: str,
         embedding_model: str,
         settings: EvaluationSettings,
+        judge_language: str = "en",
     ) -> dict[str, float | None]:
         """Score one sample synchronously and return {metric_name: score | None}."""
         llm, embeddings = self._get_models(judge_model, embedding_model, settings)
-        metric_instances = _build_metric_instances(metrics, llm, embeddings)
+        metric_instances = _build_metric_instances(metrics, llm, embeddings, judge_language)
 
         pipeline = MetricPipeline(
             metrics=metric_instances,