Update app.py

app.py

@@ -3,6 +3,7 @@ import toml
 from omegaconf import OmegaConf
 from query import VectaraQuery
 import os
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
 import streamlit as st
 from PIL import Image
@@ -90,8 +91,7 @@ def launch_bot():
                 if response == 'The returned results did not contain sufficient information to be summarized into a useful answer for your query. Please try a different search or restate your query differently.':
                     st.write("reroute to LLM")
                 else:
-                    from transformers import AutoModelForCausalLM, AutoTokenizer
-
+                    #call in Mistral
                     device = "cuda" # the device to load the model onto