Update app.py

app.py

@@ -55,7 +55,7 @@ def respond(
         verbose=True,
     )
     response = ""
-    for chunk in llm.stream_chat(chat_template):
+    for chunk in llm.stream_complete(message):
         print(chunk.delta, end="", flush=True)
         response += str(chunk.delta)
         yield response