Update app.py

app.py

@@ -62,19 +62,19 @@ def call_nvidia_api(history, max_tokens, temperature, top_p):
 def update_chatbot(message, chat_history):
     """Updates the chatbot with the user message and generates a response."""
     print("Updating chatbot...")
-    system_message = system_msg.value
+    system_message = system_msg.value  # Get values from components
     max_tokens_val = max_tokens.value
     temperature_val = temperature.value
     top_p_val = top_p.value
+
     if not chat_history or (chat_history and chat_history[-1]["role"] != "user"):
         chat_history = user(message, chat_history, system_message)
     else:
         chat_history = user(message, chat_history)
+
     chat_history = call_nvidia_api(chat_history, max_tokens_val, temperature_val, top_p_val)
     return chat_history
 
-
-
 # Gradio interface components
 system_msg = gr.Textbox(BASE_SYSTEM_MESSAGE, label="System Message", placeholder="System prompt.", lines=5)
 max_tokens = gr.Slider(20, 1024, label="Max Tokens", step=20, value=1024)
@@ -84,7 +84,7 @@ top_p = gr.Slider(0.0, 1.0, label="Top P", step=0.05, value=0.7)
 with gr.Blocks() as demo:
     chat_history_state = gr.State([])
     chatbot = gr.ChatInterface(
-        fn=update_chatbot,
+        fn=lambda message, history: update_chatbot(message, history),  
         additional_inputs=[system_msg, max_tokens, temperature, top_p],
         title="LLAMA 70B Free Demo",
         description="""