Ask HN: How to help AI find financials in large PDF faster?

1 points by richardwong1 2mo ago ↗ HN

I am developing an MCP tool that is used by Claude to search company name, director and shareholders on registries of many countries. The tool might send back original PDF that contains shareholders, but the PDF is sometimes 50mb+. I want to keep the PDF original but Claude could not read the large file. But financials might be only on a couple of pages. What might be the best solution? Thx.

1 comment

[ 3.3 ms ] story [ 14.1 ms ] thread

ctxc 2mo ago ↗

I do something tangential. If you can pick out identifiers for these pages with deterministic features (financial pages have the most numbers on the page, or have the word "director", "general manager" and "managing director" on the same page, etc)

Pick those pages out and pipe only those to the llm

Luckily I work with excel w lots of sheets and don't need to do pdf to text conversion etc