Why OpenAI Models Struggle with PDF Extraction(and Why Gemini Fairs Much Better)

Posted by kapitalx on Thursday February 27, 2025 @12:55PM
from the medium.com dept.

( 2 comments | 5 points | on HN )

Re:Why OpenAI Models Struggle with PDF Extraction(and Why Ge... by ban-lan-gen on Thursday February 27, 2025 @01:32PM (#43197039)

Does this only apply to PDFs with many images? If it is mostly text and table, could it just extract plain text?

[ Parent | on HN ]

Re:Why OpenAI Models Struggle with PDF Extraction(and Why Ge... by kapitalx on Friday February 28, 2025 @03:35PM (#43210233)

This applies to PDFs with lots of text. The smaller the text on the page, the more impacted it is.

[ Parent | on HN ]