If I understand correctly how llamaindex works, it splits each long document to several smaller chunks, and then passes them as context part in LLM prompt. I am following this guide I am trying to create chatbot that is capable of discussing movies, its knowledge base is wikipedia plots. So, I assume it is crucial for chatbot to see not only relevant part of the plot, but also a title, so it can tell what film the user is talking about. How am I adding title to each chunk, so the context looks like:
{title}
{relevant plot chunk}
