Update app.py

app.py

@@ -89,8 +89,7 @@ def launch_bot():
                 prompt2 = prompt + master_prompt
                 response = generate_response(prompt2) 
                 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:
+                    #st.write("reroute to LLM")
                     #call in Mistral
                     device = "cuda" # the device to load the model onto
 
@@ -109,7 +108,8 @@ def launch_bot():
 
                     generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
                     st.write(tokenizer.batch_decode(generated_ids)[0])
-                    # st.write(response) 
+                else:
+                    st.write(response) 
         message = {"role": "assistant", "content": response}
         st.session_state.messages.append(message)