Paperless-ngx that allows you to self host an easily browseable archive of your documents. Fully featured with OCR, ML-powered categorization and the works.

https://docs.paperless-ngx.com/

[–] squidspinachfootball@lemm.ee 2 points 6 months ago (1 children)

Do you know if the ML works offline? Or does it require an internet connection?

[–] tinsuke@lemmy.world 4 points 6 months ago

Everything runs locally, OCR, ML, etc, which can be a bit taxing on lower end hardware, but there are ways to disable the more advanced and computationally expensive features, like NLTK for advanced Natural Language processing.

Your data is stored locally on your server and is never transmitted or shared in any way.

https://docs.paperless-ngx.com/

[–] federico3@lemmy.ml 2 points 6 months ago (1 children)

How does it compare with Paperwork? https://www.openpaper.work/en/

[–] tinsuke@lemmy.world 4 points 6 months ago (1 children)

There seems to be a huge overlap in functionality. But a major difference is that Paperwork is a local application that runs on Windows and Linux, while Paperless has a web front end that makes it accessible anywhere (it also has some independently native apps for mobile).

[–] federico3@lemmy.ml 1 points 6 months ago

Thanks!

[–] brbposting@sh.itjust.works 2 points 6 months ago

Impressive, thank you!