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

Mistral OCR 4.1

docs.mistral.ai

Post reply on HN
Print view View original

41–50 of 182 posts

Re: Mistral OCR 4.1

#41

Post by piterrro »

pogue wrote: post #37
piterrro wrote: post #32

Earlier quoted context omitted.

Most use cases dont need that kind of accuracy, just doesnt justify the 3-4usd range. I build for that exact case (tender documents, we’re processing north of 100k pages per day), it doesnt need to recognize scanned written text from 1930s, its usually pdf/docs/scanned printed pages. The accuracy is great, bounding boxes are must have for proper grounding for building answers by LLMs. Tesseract was too slow and not e…

If you're getting inaccurate results from OCR what's the purpose of even doing it? Inaccuracy of text of any kind seems like a completely obvious failure of the entire purpose of scanning text into a computer.

Accuracy can have different dimensions, depends on what you can tolerate and whether you can detect it to apply more powerful methods.

Imagine you have a cheap and 99% accurate ocr. The other 1% you can detect and apply more powerful (more accurate but slower and more expensive) ocr method. What would you use? At scale these things add up.

Re: Mistral OCR 4.1

#42

Post by vrganj »

BenzeneDream wrote: post #34
kubb wrote: post #6

Earlier quoted context omitted.

It's not a race. You don't get anything for winning.

? It absolutely is a race. Whether thats a positive thing or not is debatable but every lab is definitely in a race. What prize do you win? Imagine a world where only one country has AGI/ASI. Or a world where Europe only gets access to frontier models 6 months later. Far from ideal.

This presupposes AGI or ASI are a real, reachable thing. My read is they might be, but not as LLMs. Until there's a fundamental rearchitecture, I'm AGI-agnostic and given that view, it doesn't seem rational to bet the house on it.

We'll see.

Re: Mistral OCR 4.1

#43

Post by ux266478 »

jr3592 wrote: post #38
ux266478 wrote: post #35

Earlier quoted context omitted.

> What prize do you win? Imagine a world where only one country has AGI/ASI. "Winning the race" doesn't give you that in any meaningful capacity. It gives you, at the absolute most, a temporary window where that's the case. See: nuclear weapons.

As if time isn't money? Everything is temporary... Getting somewhere first has immense value.

A reductive equation, economics isn't thermodynamics. Money is fictional and value is subjective and unstable. Within this context, being first to AGI means nothing if the second invention of it comes 2 months later and works an order of magnitude faster than what the first iteration had self-improved to at that point in time. First mover advantage isn't decisive, you have to actually be able to capitalize on it in a robust way.

Re: Mistral OCR 4.1

#45

Post by vrganj »

piterrro wrote: post #24

For anyone interested, I have an ocr pipeline running on rented GPUs, doing around 1000pages for 0.05-01 usd with around 0.8 seconds per page with full bounding boxes support for grounding. If you’re interested you can find contact to me via this profile. 3.5 usd/1000 pages is just too expensive…

Is it European-hosted and fully outside of both CLOUD Act and CCP reach?

Because I'm assuming that's why they get to charge more for the right type of customer.

Re: Mistral OCR 4.1

#47

Post by piterrro »

vrganj wrote: post #45
piterrro wrote: post #24

For anyone interested, I have an ocr pipeline running on rented GPUs, doing around 1000pages for 0.05-01 usd with around 0.8 seconds per page with full bounding boxes support for grounding. If you’re interested you can find contact to me via this profile. 3.5 usd/1000 pages is just too expensive…

Is it European-hosted and fully outside of both CLOUD Act and CCP reach? Because I'm assuming that's why they get to charge more for the right type of customer.

You can even run it on your desk if you want, a single gtx 4090 is enough. It can be fully air gapped.

Re: Mistral OCR 4.1

#48

Post by pbkompasz »

king_crimson wrote: post #3

At this point I lost all hope for Europe playing any significant role in the AI race. If that’s a good or a bad thing I don’t know, but it seems to me like that’s the reality.

Not being a rat in the rat race is the real win.

Re: Mistral OCR 4.1

#49

Post by fluoridation »

pogue wrote: post #37
piterrro wrote: post #32

Earlier quoted context omitted.

Most use cases dont need that kind of accuracy, just doesnt justify the 3-4usd range. I build for that exact case (tender documents, we’re processing north of 100k pages per day), it doesnt need to recognize scanned written text from 1930s, its usually pdf/docs/scanned printed pages. The accuracy is great, bounding boxes are must have for proper grounding for building answers by LLMs. Tesseract was too slow and not e…

If you're getting inaccurate results from OCR what's the purpose of even doing it? Inaccuracy of text of any kind seems like a completely obvious failure of the entire purpose of scanning text into a computer.

It depends on what you need. For example a while ago I scanned and OCR'ed a bunch of receipts to get a timeline of my salary. I only cared about the gross and net figures, and nothing else mattered. Tesseract's output had a bunch of errors and misdetections, but the main figures always came out OK, and a local LLM was able to pick them out from the noise every time.

There's a big gulf between "it's as if a human being had transcribed it and reconstructed the original document" and "so completely broken it can't be used for anything".

Re: Mistral OCR 4.1

#50

Post by kergonath »

ComputerPerson wrote: post #5

I've got a scan from a book that I OCR with new releases. Ligatures, critical sigla, Fraktur letterforms, subscripts, superscripts, etc. Nothing special about this model for overly-detailed work like mine. It's been a while since I last tested (and discontinued my subscription), but the "pro" models from OpenAI dominate. Not surprising, given the price difference, but it would be nice if an OCR-specific model could p…

I have been quite happy with Mistral OCR for the documents I needed to process (typeset, but old, with questionable scan quality, sometimes elaborate typesetting or, much worse, typewriter-and-handwriting approximations of it). I do not test every new model when they are released, but I did a review shortly after Mistral OCR 3 was released and it was a very good compromise: cheap, fast, and good results without further processing. I found generalist models to be way too much faf to get them to avoid unnecessary modifications to the text and report accurate bounding boxes for figures and tables.

That said, models have sometimes surprising weaknesses and a model could be terrible overall but magically work for one type of document.

Post reply on HN