fixed last lines - yield vs return

app.py

@@ -21,9 +21,9 @@ def respond(message, history):
         stream=True
     ):
         token = message.choices[0].delta.content
-        response += token 
+        response += token
+        yield response
     
-    return response['choices'][0]['message']['content'].strip()
 
 chatbot = gr.ChatInterface(respond, type="messages")