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

Mistral OCR

mistral.ai

Post reply on HN
Print view View original

101–110 of 450 posts

Re: Mistral OCR

#101

Post by PeterStuer »

epolanski wrote: post #83
cxie wrote: 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…

At my client we want to provide an AI that can retrieve relevant information from documentation (home building business, documents detail how to install a solar panel or a shower, etc) and we've set up an entire system with benchmarks, agents, etc, yet the bottleneck is OCR! We have millions and millions of pages of documents and an off by 1 % error means it compounds with the AI's own error, which compounds with doc…

As someone who has had a home built, and nearly all my friends and acquaintances report the same thing, having a 1% error on information in this business would mean not a 10x but a 50x improvement over the current practice in the field.

If nobody is supervising building documents all the time during the process, every house would be a pile of rubbish. And even when you do stuff stills creeps in and has to be redone, often more than once.

Re: Mistral OCR

#102

Post by sneak »

odiroot wrote: post #94
vessenes wrote: post #4

Dang. Super fast and significantly more accurate than google, Claude and others. Pricing : $1/1000 pages, or per 2k pages if “batched”. I’m not sure what batching means in this case: multiple pdfs? Why not split them to halve the cost? Anyway this looks great at pdf to markdown.

May I ask as a layperson, how would you about using this to OCR multiple hundreds of pages? I tried the chat but it pretty much stops after the 2nd page.

Submit the pages via the API.

Re: Mistral OCR

#104

Post by kapitalx »

vessenes wrote: post #4

Dang. Super fast and significantly more accurate than google, Claude and others. Pricing : $1/1000 pages, or per 2k pages if “batched”. I’m not sure what batching means in this case: multiple pdfs? Why not split them to halve the cost? Anyway this looks great at pdf to markdown.

From my testing so far, it seems it's super fast and responded synchronously. But it decided that the entire page is an image and returned `![img-0.jpeg](img-0.jpeg)` with coordinates in the metadata for the image, which is the entire page.

Our tool, doctly.ai is much slower and async, but much more accurate and gets you the content itself as an markdown.

Re: Mistral OCR

#106

Post by ozim »

abiraja wrote: post #8
vessenes wrote: post #4

Dang. Super fast and significantly more accurate than google, Claude and others. Pricing : $1/1000 pages, or per 2k pages if “batched”. I’m not sure what batching means in this case: multiple pdfs? Why not split them to halve the cost? Anyway this looks great at pdf to markdown.

Batching likely means the response is not real-time. You set up a batch job and they send you the results later.

If only business people I work with would understand 100GB even transfer over the network is not going to return immediately results ;)

Re: Mistral OCR

#108

Post by thiago_fm »

For general use this will be good.

But I bet that simple ML will lead to better OCRs when you are doing anything specialized, such as, medical documents, invoices etc.

Re: Mistral OCR

#109

Post by bob1029 »

themanmaran wrote: post #79
bob1029 wrote: post #54

> It takes images and PDFs as input If you are working with PDF, I would suggest a hybrid process. It is feasible to extract information with 100% accuracy from PDFs that were generated using the mappable acrofields approach. In many domains, you have a fixed set of forms you need to process and this can be leveraged to build a custom tool for extracting the data. Only if the PDFs are unknown or were created by way o…

> Only if the PDFs are unknown or were created by way of a cellphone camera, multifunction office device, etc should you need to reach for OCR. It's always safer to OCR on every file. Sometimes you'll have a "clean" pdf that has a screenshot of an Excel table. Or a scanned image that has already been OCR'd by a lower quality tool (like the built in Adobe OCR). And if you rely on this you're going to get pretty unpred…

It's not guessing if the form is known and you can read the information directly.

This is a common scenario at many banks. You can expect nearly perfect metadata for anything pushed into their document storage system within the last decade.

Re: Mistral OCR

#110

Post by fnordpiglet »

kapitalx wrote: post #81

Co-founder of doctly.ai here (OCR tool) I love mistral and what they do. I got really excited about this, but a little disappointed after my first few tests. I tried a complex table that we use as a first test of any new model, and Mistral OCR decided the entire table should just be extracted as an 'image' and returned this markdown: ``` ![img-0.jpeg](img-0.jpeg) ``` I'll keep testing, but so far, very disappointing…

Interestingly I’m currently going through and scanning the hundreds of journal papers my grandfather authored in medicine and thinking through what to do about graphs. I was expecting to do some form of multiphase agent based generation of LaTeX or SVG rather than a verbal summary of the graphs. At least in his generation of authorship his papers clearly explained the graphs already. I was pretty excited to see your post naturally but when I looked at the examples what I saw was, effectively, a more verbose form of

``` ![img-0.jpeg](img-0.jpeg) ```

I’m assuming this is partially because your use case is targeting RAG under various assumptions bur also partially because multimodal models aren’t near what I would need to be successful with?

Post reply on HN