Welcome to the community!
What you’re asking for is a topic of ongoing debate. IMO it’s unlikely that you’ll achieve a high level of reliability with custom GPTs alone.
This is a topic looking at how to ingest long documents. This specific post concerns itself with comparing regulatory documents: Using gpt-4 API to Semantically Chunk Documents - #145 by jr.2509
If you want useable results, you’ll likely have to get your hands dirty with code, and get into the nitty gritty with embeddings and the intricacies of LLMs.
If you choose to accept this mission, you’re in the right place though 