Update app.py

app.py

@@ -33,18 +33,15 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
     # Append current user message
     messages.append({"role": "user", "content": message})
 
-    # Generate response from model
-    response = ""
-    for message in client.chat_completion(
+    # Generate response (non-streaming fix)
+    response_data = client.chat_completion(
         messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-        response += token
-        yield response  # Stream response to user
+    )
+
+    response = response_data["choices"][0]["message"]["content"]
 
     # Save to session history
     session_history.append((message, response))
@@ -53,7 +50,8 @@ def respond(message, history, system_message, max_tokens, temperature, top_p):
     most_asked = max(user_preferences, key=user_preferences.get, default=None)
     if most_asked and most_asked in message.lower():
         response += f"\n\nI see you're interested in {most_asked} a lot! Want to explore more details?"
-        yield response  # Update response with learning behavior
+    
+    return response  # Return final response instead of streaming
 
 # Create Chat Interface
 demo = gr.ChatInterface(