limit responses

app.py

@@ -97,6 +97,7 @@ chat_interface = gr.ChatInterface(
     additional_inputs=[
         gr.Textbox(system_prompt, label="System Prompt (Change the language of the prompt for better replies)"),
     ],
+    concurrency_limit=1,
 )
 
 # https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI/blob/main/app.py#L219 - we use this with construction b/c Gradio barfs on autoreload otherwise