[JadoJodo]

(This critique is unrelated to this project. It works as expected, OP, and looks good.)

How could one ever trust the output of ChatGPT?

This feels to me a bit like non-L5 autonomous driving: If I have to assist at all, it'd be easier to do it myself. In the same vein, for this project (and ChatGPT generally): Can I actually trust that the output from ChatGPT in answering my question about the document is factually correct?

e.g., If I hand it a home rental agreement legal document and ask "What is the late move out penalty if I am 10-minutes late in dropping off the keys?", it may give the correct answer. Or it may generate a plausible-sounding answer using the words in the document that is completely (or perhaps even just slightly) incorrect.

How could I possibly know without reading it myself?

[ilaksh]

If it's using a search then it is possible to identify the paragraphs with a number in the database along with the embeddings. Then once the similar chunks are retrieved, part of the prompt could be to return the paragraph, line numbers or exact quote(s) used to answer the question.

Yours is not a good example though because "10 minutes late" is never going to be in a document like that.