Is there any way to do query_engine.query(query) without doing a refinement?
query_engine = index.as_query_engine(similarity_top_k=1, response_mode='compact')
query_engine.query(query)
I do this, but the refine runs multiple times.

I am currently trying to do a basic task of creating a chatbot on LlamaIndex that indexes a group of texts (multiple text files) and responds based on that information. However, when indexing, I want to divide the text into certain sizes, but when responding, I want to quote the original text longer (the entire contents of each text file). How can I do this?