Hello there! I am very very new to llamaindex and working with openai in general so I apologize if this is a stupid question. I'm trying to create a chatbot that is supposed to act as a "conflict coach", but there is no way we will receive enough data to properly train it by the time it's due. So I was wondering if there is a way to not just use the context we provide, but use chatgpt's existing knowledge as a backup?
