Update rag.py

rag.py

@@ -27,12 +27,6 @@ GREETINGS = [
     "hey there", "greetings"
 ]
 
-# Normalize user input for internal processing (with 'which' to 'what' replacement)
-def normalize_input(text):
-    text = text.lower().strip()
-    text = text.replace("which", "what")  # Add your requested replacement
-    return text
-
 # Load local dataset
 try:
     with open('dataset.json', 'r') as f:
@@ -43,8 +37,8 @@ except Exception as e:
     print(f"Error loading dataset: {e}")
     dataset = []
 
-# Precompute normalized dataset embeddings
-dataset_questions = [normalize_input(item.get("Question", "")) for item in dataset]
+# Precompute embeddings
+dataset_questions = [item.get("Question", "").lower().strip() for item in dataset]
 dataset_answers = [item.get("Answer", "") for item in dataset]
 dataset_embeddings = similarity_model.encode(dataset_questions, convert_to_tensor=True)
 
@@ -82,17 +76,12 @@ def query_groq_llm(prompt, model_name="llama3-70b-8192"):
         print(f"Error querying Groq API: {e}")
         return ""
 
-# Main logic function (with hidden 'which' to 'what' replacement)
+# Main logic function to be called from Gradio
 def get_best_answer(user_input):
     if not user_input.strip():
         return "Please enter a valid question."
 
-    # Preserve original input for display
-    original_input = user_input
-    
-    # Normalize input for processing (with hidden replacement)
-    processed_input = normalize_input(user_input)
-    user_input_lower = processed_input  # Use normalized version for processing
+    user_input_lower = user_input.lower().strip()
 
     if len(user_input_lower.split()) < 3 and not any(greet in user_input_lower for greet in GREETINGS):
         return "Please ask your question properly with at least 3 words."
@@ -100,7 +89,7 @@ def get_best_answer(user_input):
     if any(greet in user_input_lower for greet in GREETINGS):
         greeting_response = query_groq_llm(
             f"You are an official assistant for University of Education Lahore. "
-            f"Respond to this greeting in a friendly and professional manner: {original_input}"
+            f"Respond to this greeting in a friendly and professional manner: {user_input}"
         )
         return greeting_response if greeting_response else "Hello! How can I assist you today?"
 
@@ -111,33 +100,38 @@ def get_best_answer(user_input):
             "🔗 https://ue.edu.pk/allfeestructure.php"
         )
 
-    # Use normalized input for similarity matching
     user_embedding = similarity_model.encode(user_input_lower, 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()
 
     if best_score < 0.65:
-        manage_unmatched_queries(original_input)  # Store original query
+        manage_unmatched_queries(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:
-{original_input}  # Show original to user
+{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:
-{original_input}  # Show original to user
+{user_input}
+
 ### Official Answer:
 """
 
@@ -154,4 +148,4 @@ If unsure, direct to official channels.
             "📞 +92-42-99262231-33\n"
             "✉️ info@ue.edu.pk\n"
             "🌐 https://ue.edu.pk"
-        )
+        )