Update app.py

app.py

@@ -171,6 +171,7 @@ def get_llama_response(message: str, history: list) -> str:
 
     query = prompt_template.format(query=message, context=context_text)
     #query=query.format(context=context_text,question=message)
+    print('im gonna generate response')
     sequences = llama_pipeline(
         query,
         do_sample=True,
@@ -180,10 +181,12 @@ def get_llama_response(message: str, history: list) -> str:
         max_length=1024,
     )
 
+    print('igenerated response')
     generated_text = sequences[0]['generated_text']
     response = generated_text[len(query):]  # Remove the prompt from the output
 
     print("Chatbot:", response.strip())
+    print('i wanna return')
     return response.strip()