I haven't found any frameworks that offer it. The best explanation of an implementation that can take a stream of unformatted text and map over it to determine when a topic changes is explained in this video: https://youtu.be/8OJC21T2SL4?t=1932

They compute embeddings using a window of three sentences and then compute distance to find the largest deltas to break up the text into "topics". It is computationally expensive.

Using content appropriate delimiters to create the chunks. If its a Python document, split it at the proper delimiters. If its an HTML document, JSON, etc. We wouldn't want to split a chunk in the middle of a function or paragraph. Or maybe we would. But that is what OP is refering to I believe.