#How do I find relevant insights between 2 large documents?

23 messages · Page 1 of 1 (latest)

gray sage
#

If I have a legal document A and a legal document B. How could I go about getting results like: give me 5 questions about legal Document A given the situations described in Legal document B. ? Looking for insights/best practices on this, maybe an article if one exists?

#

How do I find relevant insights between 2 large documents?

coral vale
#

Just use GPT4 API and give relevant promts

gray sage
#

@coral vale I dont have access to 4

coral vale
#

You can join the waitlist, either I was testing a way to use GPT3 as 4 by giving multiple promts, but it uses alot of tokens, if that's fine, you can consider this

gray sage
#

I just applied for waitlist, but I'm also going to operate as if I won't get access for 2 more years, so I am building a solution now and looking for advice regarding my current capabilities with 3.5

coral vale
gray sage
#

@coral vale what about embeddings as a means to a solution?

#

lets assume also for simplicity sake that the sum tokens of document A+B are under the token limit.

coral vale
#

Yeah embedding will work fine, but some details can be lost as we have to compare the documents so it might not be the best practice

gray sage
#

I see. Then assuming sum tokens of document A+B are under the token limit what technique would. you advise? I tried a quick demo using the chat.openai.com and it was confused by the prompt.

coral vale
#

First describe what gpt is, like a highly trained and professional legal advisor or something, and then give a situation which creates a sense of importance, then provide it the documents with some brackets so it is differentiated by rest of the test, and then finally tell what he have to do like 5 questions about the legal document A given the situation described in legal document B

gray sage
#

it may have gotten confused by the lack of "" and its possible the documents had quotes in them in the first place

#

my issue is these documents are thousands of tokens

#

I would rather put document A into "memory" and document B into "memory" and then my prompt does not need to be 4k characters long, but I suspect this may not be possible with 3.5?

coral vale
gray sage
#

like {} ?

#

or {{{ }}} ?

coral vale
gray sage
#

is there an existing example of this multiple prompting?

coral vale
coral vale
gray sage
#

Ok, could you please summarize the technique maybe in a few pseudo code lines?