update

app.py

@@ -18,7 +18,7 @@ def respond(message,history):
 
     messages.append({"role":"user", "content": message})
 
-    response=client.chat_completion(messages, temperature=0.8, stream=True, max_tokens=300) #capping how many words the LLM is allowed to generate as a respond (300 words)
+    response=client.chat_completion(messages, temperature=0.8, stream=True, max_tokens=100) #capping how many words the LLM is allowed to generate as a respond (300 words)
 
     for message in client.chat_completion():
         token=message.choices[0].delta.content