Testing mistral recieving the response from vectara and returning an answer

app.py

@@ -88,29 +88,30 @@ def launch_bot():
             with st.spinner("Thinking..."):
                 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.':
+              #  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
-                    print("Called in Mistral")
-                    device = "cuda" # the device to load the model onto
+                prompt3 = prompt2 + "context:" + response
+                print("Called in Mistral")
+                device = "cuda" # the device to load the model onto
 
 
-                    model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
+                model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
 
-                    tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
+                tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
 
 #from mistral docs: prompt = "My favourite condiment is"
 
 
-                    model_inputs = tokenizer([prompt2], return_tensors="pt").to(device)
+                model_inputs = tokenizer([prompt3], return_tensors="pt").to(device)
 
-                    model.to(device)
+                model.to(device)
 
 
-                    generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
-                    st.write(tokenizer.batch_decode(generated_ids)[0])
-                else:
-                    st.write(response) 
+                generated_ids = model.generate(**model_inputs, max_new_tokens=100, do_sample=True)
+                st.write(tokenizer.batch_decode(generated_ids)[0])
+              #  else:
+               #     st.write(response) 
         message = {"role": "assistant", "content": response}
         st.session_state.messages.append(message)