temp and changed max tokens

app.py

@@ -133,7 +133,7 @@ def respond(message,history):
         
     messages.append({"role":"user","content": message})
 
-    response=client.chat_completion(messages, max_tokens=100)#capping how many words the LLM is allowed to generate as a respond (100 words)
+    response=client.chat_completion(messages, temperature=0.2, max_tokens=250)#capping how many words the LLM is allowed to generate as a respond (100 words)
     
     return response['choices'][0]['message']['content'].strip() #storing value of response in a readable format to display