Update evaluation.py

evaluation.py

@@ -153,7 +153,7 @@ def calculate_metrics(question, q_dataset, response, docs, time_taken):
         
     # Convert ground truth to numeric form (e.g., using cosine similarity or some metric)
     # Here, let's assume completeness is based on cosine similarity between the response and the ground truth
-    ground_truth_completeness = compute_cosine_similarity(response, ground_truth_answer)
+    # ground_truth_completeness = compute_cosine_similarity(response, ground_truth_answer)
     
     # Predicted metrics