Update rag.py

rag.py

@@ -26,7 +26,6 @@ dataset_embeddings = similarity_model.encode(dataset_questions, convert_to_tenso
 # Use absolute path for unmatched_queries.csv
 base_dir = os.path.dirname(os.path.abspath(__file__))
 file_path = os.path.join(base_dir, "unmatched_queries.csv")
-print(f"[DEBUG] Writing to absolute path: {file_path}")
 
 def query_groq_llm(prompt, model_name="llama3-70b-8192"):
     try:
@@ -41,13 +40,30 @@ def query_groq_llm(prompt, model_name="llama3-70b-8192"):
         )
         return chat_completion.choices[0].message.content.strip()
     except Exception as e:
-        print(f"Error querying Groq API: {e}")
+        print(f"[ERROR] Groq API: {e}")
         return ""
 
+def log_unmatched_query(query):
+    try:
+        # Create file with header if not exists
+        if not os.path.exists(file_path):
+            with open(file_path, mode="w", newline="", encoding="utf-8") as file:
+                writer = csv.writer(file)
+                writer.writerow(["Unmatched Queries"])
+
+        # Append unmatched query
+        with open(file_path, mode="a", newline="", encoding="utf-8") as file:
+            writer = csv.writer(file)
+            writer.writerow([query])
+        print(f"[DEBUG] Logged unmatched query: {query}")
+
+    except Exception as e:
+        print(f"[ERROR] Logging unmatched query failed: {e}")
+
 def get_best_answer(user_input):
     user_input_lower = user_input.lower().strip()
 
-    # 👉 Fee-specific shortcut
+    # 🧾 Fee-specific shortcut
     if any(keyword in user_input_lower for keyword in ["fee", "fees", "charges", "semester fee"]):
         return (
             "💰 For complete and up-to-date fee details for this program, we recommend visiting the official University of Education fee structure page.\n"
@@ -61,31 +77,11 @@ def get_best_answer(user_input):
     best_match_idx = similarities.argmax().item()
     best_score = similarities[best_match_idx].item()
 
-    # ✏️ Log to CSV if similarity is low
+    # ✏️ Log unmatched queries
     if best_score < 0.65:
-        print(f"[DEBUG] Similarity score too low: {best_score}. Logging query to: {file_path}")
+        log_unmatched_query(user_input)
 
-        # Create CSV with header if it doesn't exist
-        if not os.path.exists(file_path):
-            print(f"[DEBUG] File {file_path} does not exist. Creating file with header.")
-            try:
-                with open(file_path, mode="w", newline="", encoding="utf-8") as file:
-                    writer = csv.writer(file)
-                    writer.writerow(["Unmatched Queries"])
-                print(f"[DEBUG] Header written successfully.")
-            except Exception as e:
-                print(f"[ERROR] Failed to create file: {e}")
-
-        # Append unmatched query
-        try:
-            with open(file_path, mode="a", newline="", encoding="utf-8") as file:
-                writer = csv.writer(file)
-                writer.writerow([user_input])
-                print(f"[DEBUG] Query logged: {user_input}")
-        except Exception as e:
-            print(f"[ERROR] Failed to write query to CSV: {e}")
-
-    # 🧠 Construct prompt
+    # 🧠 Prompt for LLM
     if best_score >= 0.65:
         original_answer = dataset_answers[best_match_idx]
         prompt = f"""As an official assistant for University of Education Lahore, provide a clear response:
@@ -99,21 +95,19 @@ def get_best_answer(user_input):
         Question: {user_input}
         Official Answer:"""
 
-    # 🧠 Query LLM
+    # 🔗 Query Groq LLM
     llm_response = query_groq_llm(prompt)
 
-    # 🧾 Process LLM output
+    # ✂️ Process LLM output
     if llm_response:
         for marker in ["Improved Answer:", "Official Answer:"]:
             if marker in llm_response:
-                response = llm_response.split(marker)[-1].strip()
-                break
-        else:
-            response = llm_response
+                return llm_response.split(marker)[-1].strip()
+        return llm_response
     else:
-        response = dataset_answers[best_match_idx] if best_score >= 0.65 else """For official information:
-        📞 +92-42-99262231-33
-        ✉️ [email protected]
-        🌐 ue.edu.pk"""
-
-    return response
+        return dataset_answers[best_match_idx] if best_score >= 0.65 else (
+            "For official information:\n"
+            "📞 +92-42-99262231-33\n"
+            "✉️ info@ue.edu.pk\n"
+            "🌐 ue.edu.pk"
+        )