cache example

app.py

@@ -231,8 +231,9 @@ with gr.Blocks() as iface:
     examples = gr.Examples(
         examples=examples,
         inputs=[image_input, chat_input],
-        examples=True,
+        cache_examples=True,
         fn = inference_chat,
+        outputs = [chatbot, state],
     )
 
 iface.queue(concurrency_count=1, api_open=False, max_size=10)