Update app.py

app.py

@@ -91,7 +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")
                     #call in Mistral
-                prompt3 = prompt2 + "context:" + response
+                prompt3 = master_prompt + prompt2 + "context:" + response
                 print("Called in Mistral")
                 device = "cuda" # the device to load the model onto
 
@@ -109,7 +109,7 @@ 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("Mistral:" + tokenizer.batch_decode(generated_ids)[0])
               #  else:
                #     st.write(response) 
         message = {"role": "assistant", "content": response}