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

Please authenticate to join the conversation.

Upvoters
Status

In Progress

Board
💡

Feature Request

Date

6 months ago

Author

Said El haddati

Subscribe to post

Get notified by email when there are changes.