Update rag.py

rag.py

@@ -27,6 +27,12 @@ GREETINGS = [
     "hey there", "greetings"
 ]
 
+# Normalize user input for internal processing
+def normalize_input(text):
+    text = text.lower().strip()
+    text = text.replace("which", "what")
+    return text
+
 # Load local dataset
 try:
     with open('dataset.json', 'r') as f:
@@ -100,7 +106,9 @@ def get_best_answer(user_input):
             "🔗 https://ue.edu.pk/allfeestructure.php"
         )
 
-    user_embedding = similarity_model.encode(user_input_lower, convert_to_tensor=True)
+    # Normalize only for similarity
+    normalized_input = normalize_input(user_input_lower)
+    user_embedding = similarity_model.encode(normalized_input, convert_to_tensor=True)
     similarities = util.pytorch_cos_sim(user_embedding, dataset_embeddings)[0]
     best_match_idx = similarities.argmax().item()
     best_score = similarities[best_match_idx].item()
@@ -111,27 +119,21 @@ def get_best_answer(user_input):
     if best_score >= 0.65:
         original_answer = dataset_answers[best_match_idx]
         prompt = f"""Name is UOE AI Assistant! You are an official assistant for the University of Education Lahore.
-
 Rephrase the following official answer clearly and professionally. 
 Use structured formatting (like headings, bullet points, or numbered lists) where appropriate.
 DO NOT add any new or extra information. ONLY rephrase and improve the clarity and formatting of the original answer.
-
 ### Question:
 {user_input}
-
 ### Original Answer:
 {original_answer}
-
 ### Rephrased Answer:
 """
     else:
         prompt = f"""Name is UOE AI Assistant! As an official assistant for University of Education Lahore, provide a helpful response:
 Include relevant details about university policies.
 If unsure, direct to official channels.
-
 ### Question:
 {user_input}
-
 ### Official Answer:
 """