DocJev is the fastest way to classify and split complex document packets ⚡️. (and the default is fully free and OSS!) I made a sick teaser video below. TY Opus 5.5 🙏 check it out:

how i made the video 😂

351 bookmarks vs 301 likes is the most honest metric in dev tools, everyone plans to try it right after they finish the other 3,000 repos they bookmarked.

Already on my directory 😄 Great tool Thank you for sharing it 🙏🏻

Two invoices can have every page classified correctly and still get merged into one document. DocJev's default 0.1 boundary-review margin flags uncertain continuations too, not just cuts.

can it classify between scanned pdf or text-based pdf?

did you make the video with remotion? looks nice

bro idk i pointed claude code opus 5.5 at it and made it go brrr

Really cool. If I understand correctly, you classify full documents and - currently - don't look into classifying chunks/subsections (e.g for RAG), right?

This video is super cool! I'd love to know what tool you used to make it.

Splitting document packets. The least glamorous demo and the one I want.

this operate on the text layer tho right?

yep. there are VLM options with llamaparse, which would increase parse latency (though not extract)

Do you think it will be able to do page level classification of say a form vs a table? I have so many customers asking me how to chunk a table.

I wonder how this would pair with PageIndex 👀

For packet splitting, we'd validate page coverage separately: every source page belongs to exactly one output, with order preserved. That catches dropped or duplicated pages even when category predictions look sensible.

We are so done ❤️

❌ doctor jev ✅ doc jev

So how? Like higgsfield

really excellent video. is it remotion?

DocJev sounds promising, but speed isn't everything, accuracy is key too

I have captured multiple small size receipt into single photo. ( with the hope something similar solution will appear in future) Can it clarify and split ?

packet splitting is where most doc systems fail silently. they either over-merge (lose structure) or over-split (create orphans). hard to benchmark.

dope!

I need it to be able to distinguish between the layout providers for the same type of document class... for example, it needs to recognize that Layout X belongs to Supplier A and Layout Y belongs to Supplier B. Can it do that?

Free OSS is a boon, but consider how it scales with volume. Performance gains must meet business needs.