Invoice extraction: columns not recognized on subsequent pages
Hello,
I need to extract elements from a table that may span multiple pages. The table header only appears on the first page. I’ve noticed that the extraction works correctly on the first page, but the model doesn’t seem to recognize the structure consistently on the following pages.
I’m not using RAG at the moment because I’m targeting basic, regular invoices. I’d like to know how to solve this issue. I already tried specifying in the schema that the table columns remain consistent across all pages, but this doesn’t seem to improve the results.
Could you please help me resolve this issue ?
Thank you
Log in to comment and vote
Comments2
Jonathan Grandperrin
Aug 19, 2025
Hi Said, thanks for your message!
This should be supported, our data science team will take a look asap. If you can share an example over email (not on this platform), that’d be super helpful!
Said El haddati
Aug 19, 2025
Hello Jonathan,
Thank you for the quick answer, i will do
Regards