News for hackers. Stuff that matters.

A comment on Ingesting PDFs and why Gemini 2.0 changes everything. Parent comment

Re:Ingesting PDFs and why Gemini 2.0 changes everything by shermantanktop on Wednesday February 05, 2025 @06:28PM (#42956872)
is "put this glyph at coordinate (x,y)" really what you'd call "structured"?
[ Parent | on HN ]
Re:Ingesting PDFs and why Gemini 2.0 changes everything by dkjaudyeqooe on Wednesday February 05, 2025 @08:01PM (#42957640)
He's calling PDFs unstructured: structured editors -> unstructured PDF -> structured data
[ Parent | on HN ]
Re:Ingesting PDFs and why Gemini 2.0 changes everything by irjustin on Wednesday February 05, 2025 @11:27PM (#42959081)
It's not the structure that allows meaningful understanding.

Something that was clearly a table now becomes a bunch of glphy's physically close to eachother vs a group of other glphys but when considered as a group is a box visually separated from another group of glphys but actually part of a table.

[ Parent | on HN ]