j soma
@dangerscarf.bsky.social
Natural PDF v0.1.13 out – a handful of useful changes but my favorite is🗼page restructuring support!
Grab sections and "flow" them together vertically or horizontally, making multi-column extraction infinitely easier than 24 hours ago.
Details at jsoma.github.io/natural-pdf/...
Grab sections and "flow" them together vertically or horizontally, making multi-column extraction infinitely easier than 24 hours ago.
Details at jsoma.github.io/natural-pdf/...
June 5, 2025 at 2:02 PM
Natural PDF v0.1.13 out – a handful of useful changes but my favorite is🗼page restructuring support!
Grab sections and "flow" them together vertically or horizontally, making multi-column extraction infinitely easier than 24 hours ago.
Details at jsoma.github.io/natural-pdf/...
Grab sections and "flow" them together vertically or horizontally, making multi-column extraction infinitely easier than 24 hours ago.
Details at jsoma.github.io/natural-pdf/...
it looks like someone has been going very hard on scans
ONE MORE DAY OF ACCEPTING BAD PDF SUBMISSIONS
ONE MORE DAY OF ACCEPTING BAD PDF SUBMISSIONS
May 16, 2025 at 12:36 PM
it looks like someone has been going very hard on scans
ONE MORE DAY OF ACCEPTING BAD PDF SUBMISSIONS
ONE MORE DAY OF ACCEPTING BAD PDF SUBMISSIONS
Woke up to ton of new non-English BAD PDF CONTEST submissions: 💥 Serbian! Romanian! Chinese! 💥
Mostly not scans, though, so I predict they'll easy-peasy to extract the info from. I want to have to train a custom OCR model!!! Someone submit a big scanned non-English PDF!!!
Mostly not scans, though, so I predict they'll easy-peasy to extract the info from. I want to have to train a custom OCR model!!! Someone submit a big scanned non-English PDF!!!
May 12, 2025 at 12:56 PM
Woke up to ton of new non-English BAD PDF CONTEST submissions: 💥 Serbian! Romanian! Chinese! 💥
Mostly not scans, though, so I predict they'll easy-peasy to extract the info from. I want to have to train a custom OCR model!!! Someone submit a big scanned non-English PDF!!!
Mostly not scans, though, so I predict they'll easy-peasy to extract the info from. I want to have to train a custom OCR model!!! Someone submit a big scanned non-English PDF!!!
i know you all are hiding worse scans from me
May 11, 2025 at 1:33 PM
i know you all are hiding worse scans from me
i love this giant-pdf-with-tiny-text submission, we need a smallest font size category
May 8, 2025 at 3:24 PM
i love this giant-pdf-with-tiny-text submission, we need a smallest font size category
Live colab demo/walkthrough here: colab.research.google.com/github/jsoma...
April 3, 2025 at 4:16 PM
Live colab demo/walkthrough here: colab.research.google.com/github/jsoma...
New release of 📝 Natural PDF 📝
A million and one table extraction/document layout/Q&A/quality of life improvements for all your PDF-processing needs
jsoma.github.io/natural-pdf/
A million and one table extraction/document layout/Q&A/quality of life improvements for all your PDF-processing needs
jsoma.github.io/natural-pdf/
April 3, 2025 at 4:16 PM
New release of 📝 Natural PDF 📝
A million and one table extraction/document layout/Q&A/quality of life improvements for all your PDF-processing needs
jsoma.github.io/natural-pdf/
A million and one table extraction/document layout/Q&A/quality of life improvements for all your PDF-processing needs
jsoma.github.io/natural-pdf/