Update app.py

app.py

@@ -2,8 +2,8 @@ import gradio as gr
 from generator import generate_text
 
 def respond(message, history):
-    response = generate_text(message)
-    return response
+    # Trả về generator (stream text dần)
+    return generate_text(message)
 
 chatbot = gr.ChatInterface(
     fn=respond,
@@ -18,4 +18,5 @@ chatbot = gr.ChatInterface(
 )
 
 if __name__ == "__main__":
-    chatbot.launch()
+    # stream=True để Gradio hiển thị token dần
+    chatbot.launch(stream=True, server_name="0.0.0.0", server_port=7860)