Update app.py

app.py

@@ -28,9 +28,10 @@ def respond(message, history):
         temperature = 0.5,
         stream = True):
         
-        token = message.choices[0].delta.content
-        response += token
-        yield response
+        token = message.choices[0].delta.content #extracts the new token (word/character - like "add") that just arrived
+        response += token #adding token onto response, like a snowball effect
+        yield response #not 'return response -- return would end loop & return only 1st some tokens that are printed
+            #yield - sends current 'response' back to Gradio -> Gradio updates chatbot screen, then waits for next turn of loop
 
 # defining chatbot
 chatbot = gr.ChatInterface(respond, title = "", description = "")