update

app.py

@@ -20,7 +20,7 @@ def respond(message,history):
 
     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():
+    for message in client.chat_completion(messages):
         token=message.choices[0].delta.content
         response+=token
     yield response['choices'][0]['message']['content'].strip() #storing value of response in a readable format to display