Update app.py

app.py

@@ -12,18 +12,12 @@ def respond(message, history):
     
     messages.append({"role": "user", "content": message})
     
-    try:
-        response = client.chat_completion(
-            messages,
-            max_tokens=100,
-        )
-        reply = response['choices'][0]['message']['content'].strip()
-    except Exception as e:
-        reply = f"Error during inference: {e}"
-        # Optionally log the error
-        print(reply)
-
-    return reply
+    response = client.chat_completion(
+        messages,
+        max_tokens=512,
+    )
+    
+    return response['choices'][0]['message']['content'].strip()
 
 chatbot = gr.ChatInterface(respond, type="messages")