reduced temp

app.py

@@ -136,7 +136,7 @@ def predict(prompt):
     response = client.chat.completions.create(
         model="llama-3.1-70b-versatile",
         messages=historyFormatted,
-        temperature=1.2,
+        temperature=0.8,
         max_tokens=4000,
         stream=True
     )