Why OpenAI Models Struggle with PDF Extraction(and Why Gemini Fairs Much Better) (medium.com) 5 points by kapitalx 1y ago ↗ HN
[–] ban-lan-gen 1y ago ↗ Does this only apply to PDFs with many images? If it is mostly text and table, could it just extract plain text? [–] kapitalx 1y ago ↗ This applies to PDFs with lots of text. The smaller the text on the page, the more impacted it is.
[–] kapitalx 1y ago ↗ This applies to PDFs with lots of text. The smaller the text on the page, the more impacted it is.
3 comments
[ 4.0 ms ] story [ 16.8 ms ] thread