Rendered at 02:37:44 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
fishisnow 14 minutes ago [-]
I built a free tool(https://mdpdf.net), based on the fast PDF conversion library (https://github.com/firecrawl/pdf-inspector). It runs entirely in the user’s browser. In my view, the biggest pain points when converting PDF to Markdown are whether it can properly handle content like tables and code blocks, as well as OCR. Current OCR approaches don’t seem very effective unless you use an LLM.
axm997 8 hours ago [-]
https://github.com/amitxm/AIDocPrep is the one I built that is true local OCR. I made sure there is NO internet use, even accidentally. Also, added redaction.
kennywinker 7 hours ago [-]
Seems like it sends your documents to the LLM of your choice. In what world is that “locally”??
MrDrMcCoy 6 hours ago [-]
LLMs have been self-hostable for a while now.
kennywinker 3 hours ago [-]
I am aware, but unless it includes a model and model runner, it’s not offering local it’s allowing local.
Also, it seems disingenuous to have “locally” in the title when your default is cloud inference providers and I don't see you naming a recommended LLM that could be hosted locally and is proven to work well for this task. You list “Your files” under “Stays on your machine” and then require an API key for a cloud provider.
mrkn1 6 hours ago [-]
Worth noting there’s also textsnap if you want something that’s actually local end-to-end via ONNX on CPU, no GPU, no API key, nothing leaves your machine. https://github.com/kouhxp/textsnap
bbor 9 hours ago [-]
Shoutout to marker-2. By far the best OCR system, IME. The amount of annoying little edge cases they know about and cover for you is dizzying
cyrillsemah 9 hours ago [-]
[flagged]
Benard-dev 10 hours ago [-]
I am also building an app that converts web pages to Markdown.
How do you handle messy scans and tables?
Also, it seems disingenuous to have “locally” in the title when your default is cloud inference providers and I don't see you naming a recommended LLM that could be hosted locally and is proven to work well for this task. You list “Your files” under “Stays on your machine” and then require an API key for a cloud provider.