diff --git a/qdrant-landing/content/documentation/tutorials-search-engineering/retrieval-quality-golden-set.md b/qdrant-landing/content/documentation/tutorials-search-engineering/retrieval-quality-golden-set.md
index c96a0192c..3169aeda8 100644
--- a/qdrant-landing/content/documentation/tutorials-search-engineering/retrieval-quality-golden-set.md
+++ b/qdrant-landing/content/documentation/tutorials-search-engineering/retrieval-quality-golden-set.md
@@ -117,6 +117,7 @@ def retrieval_run(golden_set: list, collection: str, k: int = 10) -> Run:
             query=entry["query_vector"],
             limit=k,
         ).points
+        # p.id type must match the doc_id type in labels (ranx matches by equality).
         run[entry["query_id"]] = {p.id: p.score for p in results}
     return Run(run)
 
diff --git a/qdrant-landing/content/documentation/tutorials-search-engineering/retrieval-quality-pipeline-output.md b/qdrant-landing/content/documentation/tutorials-search-engineering/retrieval-quality-pipeline-output.md
index 82a4c8c6e..952d9bb17 100644
--- a/qdrant-landing/content/documentation/tutorials-search-engineering/retrieval-quality-pipeline-output.md
+++ b/qdrant-landing/content/documentation/tutorials-search-engineering/retrieval-quality-pipeline-output.md
@@ -119,12 +119,13 @@ Pass the eval samples into `evaluate()` with those three metrics:
 
 ```python
 from ragas import EvaluationDataset, evaluate
-from ragas.metrics import faithfulness, answer_relevancy, context_precision
+from ragas.metrics.collections import faithfulness, answer_relevancy, context_precision
 
 dataset = EvaluationDataset(samples=samples)
 scores = evaluate(
     dataset,
     metrics=[faithfulness, answer_relevancy, context_precision],
+    # For a non-OpenAI judge, pass llm= and embeddings= (see Ragas docs).
 )
 ```