Llama-Scan: Convert PDFs to Text W Local LLMs • Hacker News Board

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#31

Post by mdaniel » Mon, Aug 18, 2025, 12:29 AM UTC

ahmedhawas123 wrote: post #28

This may be a bit of an irrelevant and at best imaginative rant, but there is no shortage of solutions that are mediocre or near perfect for specific use cases out there to parse PDFs. This is a great addition to that. That said, over the last two years I've come across many use cases to parse PDFs and each has its own requirements (e.g., figuring out titles, removing page numbers, extracting specific sections, etc).…

That ship has sailed, and I'd guess the majority of the folks in these threads are in the same boat I am: one does not get to choose what files your customers send you, you have to meet them where they are

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#32

Post by mdaniel » Mon, Aug 18, 2025, 12:29 AM UTC

bugglebeetle wrote: post #25

thorum wrote: post #23

I’ve been trying to convert a dense 60 page paper document to Markdown today from photos taken on my iPhone. I know this is probably not the best way to do it but it’s still been surprising to find that even the latest cloud models are struggling to process many of the pages. Lots of hallucination and “I can’t see the text” (when the photo is perfectly clear). Lots of retrying different models, switching between LLMs…

Try this: https://github.com/rednote-hilab/dots.ocr

The code is MIT, and the weights are labeled MIT although the actual license file in the weights repo seems to be mostly Apache 2 https://huggingface.co/rednote-hilab/dots.ocr/blob/main/NOTI...

Seems to weigh about 6GB which feels reasonable to manage locally

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#33

Post by treetalker » Mon, Aug 18, 2025, 12:52 AM UTC

nawazgafar wrote: post #20

treetalker wrote: post #15

I presume this doesn't handle handwriting. Does anyone have a suggestion for locally converting PDFs of handwriting into text, say on a recent Mac? Use case would be converting handwritten journals and daily note-taking.

Author here, I tested it with this PDF of a handwritten doc [1], and it converted both pages accurately. 1. https://github.com/pnshiralkar/text-to-handwriting/blob/mast...

Amazing, can't wait to try it!

FYI, your GitHub link tells me it's unable to render because the pdf is invalid.

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#34

Post by evolve2k » Mon, Aug 18, 2025, 1:08 AM UTC

“Turn images and diagrams into detailed text descriptions.”

I’d just prefer that any images and diagrams are copied over, and rendered into a popular format like markdown.

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#35

Post by bm-rf » Mon, Aug 18, 2025, 1:14 AM UTC

ahmedhawas123 wrote: post #28

This may be a bit of an irrelevant and at best imaginative rant, but there is no shortage of solutions that are mediocre or near perfect for specific use cases out there to parse PDFs. This is a great addition to that. That said, over the last two years I've come across many use cases to parse PDFs and each has its own requirements (e.g., figuring out titles, removing page numbers, extracting specific sections, etc).…

For the purposes of an llm "reading" a pdf, it just renders it as an image. The file format does not matter. Let's say you have documents that already exist, a robust ocr solution that can handle tables and diagrams could be very valuable.

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#36

Post by phren0logy » Mon, Aug 18, 2025, 1:22 AM UTC

password4321 wrote: post #21

treetalker wrote: post #15

I presume this doesn't handle handwriting. Does anyone have a suggestion for locally converting PDFs of handwriting into text, say on a recent Mac? Use case would be converting handwritten journals and daily note-taking.

I don't know re: handwriting so only barely relevant but here is a new contender for a CLI "OCR Tool using Apple's Vision Framework API": https://github.com/riddleling/macocr which I found while searching for this recent discussion: My iPhone 8 Refuses to Die: Now It's a Solar-Powered Vision OCR Server https://news.ycombinator.com/item?id=44310944

If you use Docling, you can set your OCR engine to OCRMac then set it to use LiveText. It’s a good arrangement. You can send these as command-line arguments, but I generally configure it from the Python API.

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#37

Post by Y_Y » Mon, Aug 18, 2025, 1:32 AM UTC

HocusLocus wrote: post #11

By 1990 Omnipage 3 and its successors were 'good enough' and with their compact dictionaries and letter form recognition were miracles of their time at ~300MB installed. In 2025 LLMs can 'fake it' using Trilobites of memory and Petaflops. It's funny actually, like a supercomputer being emulated in real time on a really fast Jacquard loom. By 2027 even simple hand held calculator addition will be billed in kilowatt-ho…

https://en.wikipedia.org/wiki/Trilobite

Trilobites? Those were truly primitve computers.

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#38

Post by privatelypublic » Mon, Aug 18, 2025, 1:36 AM UTC

HocusLocus wrote: post #11

By 1990 Omnipage 3 and its successors were 'good enough' and with their compact dictionaries and letter form recognition were miracles of their time at ~300MB installed. In 2025 LLMs can 'fake it' using Trilobites of memory and Petaflops. It's funny actually, like a supercomputer being emulated in real time on a really fast Jacquard loom. By 2027 even simple hand held calculator addition will be billed in kilowatt-ho…

If you think 1990's ocr- even 2000's OCR is remotely as good as modern OCR... I`v3 g0ta bnedge to sell.

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#39

Post by throwaway1777 » Mon, Aug 18, 2025, 1:48 AM UTC

privatelypublic wrote: post #38

HocusLocus wrote: post #11

By 1990 Omnipage 3 and its successors were 'good enough' and with their compact dictionaries and letter form recognition were miracles of their time at ~300MB installed. In 2025 LLMs can 'fake it' using Trilobites of memory and Petaflops. It's funny actually, like a supercomputer being emulated in real time on a really fast Jacquard loom. By 2027 even simple hand held calculator addition will be billed in kilowatt-ho…

If you think 1990's ocr- even 2000's OCR is remotely as good as modern OCR... I`v3 g0ta bnedge to sell.

[dead]

Re: Llama-Scan: Convert PDFs to Text W Local LLMs

#40

Post by ggnore7452 » Mon, Aug 18, 2025, 2:16 AM UTC

I’ve done a similar PDF → Markdown workflow.

For each page:

- Extract text as usual.

- Capture the whole page as an image (~200 DPI).

- Optionally extract images/graphs within the page and include them in the same LLM call.

- Optionally add a bit of context from neighboring pages.

Then wrap everything with a clear prompt (structured output + how you want graphs handled), and you’re set.

At this point, models like GPT-5-nano/mini or Gemini 2.5 Flash are cheap and strong enough to make this practical.

Yeah, it’s a bit like using a rocket launcher on a mosquito, but this is actually very easy to implement and quite flexible and powerfuL. works across almost any format, Markdown is both AI and human friendly, and surprisingly maintainable.