Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o

github.com

Post reply on HN
Print view View original

31–40 of 97 posts

Re: Show HN: PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o

#31

Post by alchemist1e9 »

eth0up wrote: post #29

I used GPT4o to convert heavily convoluted PDFs into csv files. The files were Florida Lottery Pick(n) histories, which they deliberately convolute to prevent automatic searching; ctrl-f does nothing and a fsck-ton of special characters embellish the whole file. I had previously done so manually, with regex, and was surprised with the quality of the end results of GPT, despite many preceding failed iterations. The wo…

Off topic - but the obvious follow up question is why do you want people to have this ability to search the entire history?

Re: Show HN: PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o

#34

Post by eth0up »

alchemist1e9 wrote: post #31
eth0up wrote: post #29

I used GPT4o to convert heavily convoluted PDFs into csv files. The files were Florida Lottery Pick(n) histories, which they deliberately convolute to prevent automatic searching; ctrl-f does nothing and a fsck-ton of special characters embellish the whole file. I had previously done so manually, with regex, and was surprised with the quality of the end results of GPT, despite many preceding failed iterations. The wo…

Off topic - but the obvious follow up question is why do you want people to have this ability to search the entire history?

Thanks for asking...

1) I'm a rebel

2) I am irritated by deliberate obfuscations of public data, especially by a source that I suspect is corrupt. Although my extensive analysis has not yet revealed any significant pattern anomalies in their numbers.

3) It's kind of my re-intro into python, which I never made significant progress in but always wanted to.

4) It's literally the real history of all winning numbers since inception. Individuals may have various reasons for accessing this data, but I've been using it to test for manipulation. I presume for most folks it would be curiosity, or gambler's fallacy type stuff. Regardless, it shouldn't be obfuscated.

Re: Show HN: PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o

#35

Post by Lerc »

llm_trw wrote: post #28
Propelloni wrote: post #15

Earlier quoted context omitted.

> you might get some skipped bits, but that's not a dealbreaker for folks looking to feed PDFs into AI systems Unless it is. We have a few hundred PDF per month (mostly tables) where we need 100% accuracy. Currently we feed them into an OCR and have humans check the result. I do not win anything if I have to check the LLM output, too.

I'm currently solving this problem for work and thinking of a spin out, what's a ballpark figure you'd be willing to pay per 1000 pages for 99.999% character level accuracy?

I guess it depends on the use case, but if it surpasses the error rate that exists in the source document then it would be difficult to argue against.

Specific things like evidentiary use would want 100% but that's at a level where any document processing would be suspect.

What is the the typical range for error rate in PDF generation in various fields? Even robust technical documents have the occasional typo.

Re: Show HN: PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o

#36

Post by alchemist1e9 »

eth0up wrote: post #34
alchemist1e9 wrote: post #31

Earlier quoted context omitted.

Off topic - but the obvious follow up question is why do you want people to have this ability to search the entire history?

Thanks for asking... 1) I'm a rebel 2) I am irritated by deliberate obfuscations of public data, especially by a source that I suspect is corrupt. Although my extensive analysis has not yet revealed any significant pattern anomalies in their numbers. 3) It's kind of my re-intro into python, which I never made significant progress in but always wanted to. 4) It's literally the real history of all winning numbers since…

I had suspected you’re are suspicious of manipulation. I have heard many rumors of lottery corruption and manipulation.

It’s certainly a big red flag if they are deliberately obstructing access to the data.

Make sense your project and I’d probably take 30 mins to look at the data if I came across it. I’m somewhat decent at data and number analysis so if there is something and enough people can easily take a look at it, then it might get exposed.

Interesting and good luck.

Re: Show HN: PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o

#37

Post by rescbr »

hnlmorg wrote: post #25
yigitkonur35 wrote: post #9

Earlier quoted context omitted.

You've got a point, but try testing it on a tricky example like the Apollo 17 document - you know, with those sideways tables and old-school writing. You'll see all three non-AI services totally bomb. Now, if you tweak it to batch = 1 instead of 10, you'll notice there's hardly any made-up stuff. When you dial down the temperature close to zero, it's super unlikely to see hallucinations with limited context. At worst…

AWS Textract does use ML and I’ve personally used it to parse tables for automated invoice processing. You wouldn’t get a markdown document automatically generated (or at least you couldn’t when I last used it a few years ago) but you did get an XML document That XML document was actually better for our purposes because it gives you a confidence score and is properly structured, so floating frame, tables and columns…

For a similar use case I’m using Azure Document AI - at least you can ask for markdown/html output directly from it instead of parsing the output structure from Textract.

And it’s cheaper too.

Re: Show HN: PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o

#38

Post by llm_trw »

Lerc wrote: post #35
llm_trw wrote: post #28

Earlier quoted context omitted.

I'm currently solving this problem for work and thinking of a spin out, what's a ballpark figure you'd be willing to pay per 1000 pages for 99.999% character level accuracy?

I guess it depends on the use case, but if it surpasses the error rate that exists in the source document then it would be difficult to argue against. Specific things like evidentiary use would want 100% but that's at a level where any document processing would be suspect. What is the the typical range for error rate in PDF generation in various fields? Even robust technical documents have the occasional typo.

I'm not using generative models to fill in details not present in the original document. If there's a typo there then there will be a typo in the transcript. If you want to fix that then you can run another model on top of it.

Re: Show HN: PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o

#39

Post by rescbr »

llm_trw wrote: post #28
Propelloni wrote: post #15

Earlier quoted context omitted.

> you might get some skipped bits, but that's not a dealbreaker for folks looking to feed PDFs into AI systems Unless it is. We have a few hundred PDF per month (mostly tables) where we need 100% accuracy. Currently we feed them into an OCR and have humans check the result. I do not win anything if I have to check the LLM output, too.

I'm currently solving this problem for work and thinking of a spin out, what's a ballpark figure you'd be willing to pay per 1000 pages for 99.999% character level accuracy?

At least for my use case, which is Layout processing (i.e. must output tables in some kind of table format), the OCR part (Azure Document AI or AWS Textract) dominates the cost factor.

Running OCR on a document is twice more expensive than processing the output on the most expensive GPT offering. Intuitively, this was kind of unexpected for me. Only when I did some calculations on Excel that I realized it.

If you’re able to halve the pricing for Layout output then you’re unblocking lots of use cases out there.

Re: Show HN: PDF to MD by LLMs – Extract Text/Tables/Image Descriptives by GPT4o

#40

Post by itchyjunk »

fragmede wrote: post #20
zerop wrote: post #18

I had been using GPT4o for extracting insights from Scanned docs, it was doing fine. But very recently (since they launched new model - o1), it's not working. GPT4o is refusing to extract text from images and says it can't do it, though it was doing same thing with same prompts till last week. I am not sure if this is intentional downgrade and it can be clubbed with new model launch, but it's really frustrating for m…

Why not just switch back to GPT-4? it's still there.

So is 4o. Problem isn't the absence of model, it's inconsistency.
Post reply on HN