Live data from Hacker News

Mistral OCR

mistral.ai

201–210 of 450 posts

Re: Mistral OCR

#201
I feel this is created for RAG. I tried a document [0] that I tested with OCR; it got all the table values correctly, but the page's footer was missing.

Headers and footers are a real pain with RAG applications, as they are not required, and most OCR or PDF parsers will return them, and there is extract work to do to remove them.

[0] https://github.com/orasik/parsevision/blob/main/example/Mult...

Re: Mistral OCR

#203
post #166

It's shocking how much our industry fails to see past its own nose. Not a single example on that page is a Purchase Order, Invoice etc. Not a single example shown is relevant to industry at scale.

Agreed. In general I've had such bad performance for complex table based invoice parsing, that every few months I try the latest models to see if its better. It does say "96.12" on top-tier benchmark under the Table category.

Re: Mistral OCR

#206
post #40

The new Mistral OCR release looks impressive - 94.89% overall accuracy and significantly better multilingual support than competitors. As someone who's built document processing systems at scale, I'm curious about the real-world implications. Has anyone tried this on specialized domains like medical or legal documents? The benchmarks are promising, but OCR has always faced challenges with domain-specific terminology…

$1 for 1000 pages seems high to me. Doing a google search Rent and Reserve NVIDIA A100 GPU 80GB - Pricing Starts from $1.35/hour I just don't know if in 1 hour and with a A100 I can process more than a 1000 pages. I'm guessing yes.

Is the model Open Source/Weight? Else the cost is for the model, not GPU.

Re: Mistral OCR

#207
post #166

It's shocking how much our industry fails to see past its own nose. Not a single example on that page is a Purchase Order, Invoice etc. Not a single example shown is relevant to industry at scale.

We find CV models to be better (higher midpoint on an ROC curve) for the types of docs you mention.

Re: Mistral OCR

#208
post #150

Earlier quoted context omitted.

I never thought driving a car is harder than editing a pdf.

It's not about harder but about what error you can tolerate. Here if you have accuracy 99% for many applications it's enough. If you have 99% accuracy per trip of no crash during self driving then you gonna be dead within a year very likely. For cars we need accuracy at least 99.99% and that's very hard.

I doubt most people have 99% accuracy. The threshold of tolerance for error is just much lower for any self-driving system (and with good reason, because we're not familiar with them yet).

Re: Mistral OCR

#209

Earlier quoted context omitted.

Does doctly do handwritten forms like dates? I have a lot of "This document filed and registered in the county of ______ on ______ of _____ 2023" sort of thing.

We've been getting great results with those aswell. But ofcourse there is always some chance of not getting it perfect, specially with different handwritings. Give it a try, no credit cards needed to try it. If you email me (ali@doctly.ai) i can give you extra free credits for testing.

Just tried it. Got all the dates correct and even extracted signatures really well.

Now to figure out how many millions of pages I have.

Post reply on HN