Hi Is there a way to set the rate of

hmmm, there is not a way to set this as a user.

However, I wouldn't be too worried until you actually hit a rate error 🙂

When dealing with large documents, do LlamaIndex have a mechanism for splitting them up, or if it sends one massive request to OpenAI all at once?

Yea whenever you put a document into llama index, it gets broken into smaller chunks

Right now, by default it splits into 1024 token chunks (with slight overlap) using a token text splitter