Find answers from the community

Updated 3 months ago

Pdf parsing issue with multi-page tables

Hello again.
I'm having an issue parsing a PDF. This same parsing instructions and file used to work 2 weeks ago.

Job id is 4d3d72d7-ab11-4593-83e5-89672a1a523f

The parser seems to not work for tables that start in one page and ends in another page, i'll leave a screenshot.
This screenshot does not contain any sensitive information and its not private btw

Any ideas on a workaround?

Attachment

3 comments

LLogan M

multi-page spanning tables is a feature that is being worked on, but yes, not quite supported yt

vversa

sure, no problem. Would you have any suggestions on a workaround? it would help me a lot

LLogan M

I don't think there is an easy work around. One option is getting an LLM to parse the outputs of every page from llama-parse and combine tables that are continuations of eachother (passing in pairs at a time I suppose?)

Add a reply