Update app.py

app.py

@@ -7,10 +7,10 @@ pipe = load_model()
 
 # Wrapper to handle dynamic output length
 def smart_response(command, execute):
-    # Dynamically adjust max_new_tokens based on complexity
-    simple_keywords = ["open", "close", "shutdown", "restart", "lock", "screenshot"]
+    # Dynamically adjust max_new_tokens based on command complexity
+    simple_keywords = ["hi", "hello", "open", "close", "shutdown", "restart", "lock", "screenshot"]
     is_simple = any(keyword in command.lower() for keyword in simple_keywords)
-    max_tokens = 128 if is_simple else 1024  # Shorter for quick commands, longer for reasoning
+    max_tokens = 64 if is_simple else 512  # fast replies for simple commands
 
     return get_assistant_response(pipe, command, execute, max_new_tokens=max_tokens)
 
@@ -28,7 +28,7 @@ demo = gr.Interface(
     outputs="text",
     title="🧠 Smart AI Assistant",
     description=(
-        "AI assistant powered by **Mistral-7B-Instruct** 🧠\n\n"
+        "AI assistant powered by **Qwen/Qwen3-1.7B** 🧠\n\n"
         "Try commands like:\n"
         "• 'Open Chrome'\n"
         "• 'Take a screenshot'\n"
@@ -42,4 +42,4 @@ demo = gr.Interface(
 )
 
 if __name__ == "__main__":
-    demo.launch(share=True, server_name="0.0.0.0", server_port=7860)
+    demo.launch(share=False, server_name="0.0.0.0", server_port=7860)