LLM based OCR is a disaster, great potential for hallucinations and no estimate of confidence. Results might seem promising but you’ll always be wondering.
Mistral OCR
51–60 of 450 posts
Re: Mistral OCR
#52Related, does anyone know of an app that can read gauges from an image and log the number to influx? I have a solar power meter in my crawlspace, it is inconvenient to go down there. I want to point an old phone at it and log it so I can check it easily. The gauge is digital and looks like this: https://www.pvh2o.com/solarShed/firstPower.jpg
You'll be happier finding a replacement meter that has an interface to monitor it directly or a second meter. An old phone and OCR will be very brittle.
Re: Mistral OCR
#53Re: Mistral OCR
#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 of a cellphone camera, multifunction office device, etc should you need to reach for OCR.
The moment you need to use this kind of technology you are in a completely different regime of what the business will (should) tolerate.
Re: Mistral OCR
#55I would like to see how it performs with massively warped and skewed scanned text images, basically a scanned image where the text lines are wavy as opposed as straight horizontal, where the letters are elongated. One where the line widths are different depending on the position on the scanned image. I once had to deal with such a task that somebody gave me with OCR software, Acrobat, and other tools could not decode the mess so I had to recreate the 30 pages myself, manually. Not a fun thing to do but that is a real use case.
Re: Mistral OCR
#56The 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…
> Has anyone tried this on specialized domains like medical or legal documents?
I’ll try it on a whole bunch of scientific papers ASAP. Quite excited about this.
Re: Mistral OCR
#57The hard ones are things like contracts, leases, and financial documents which 1) don’t have a common format 2) are filled with numbers proper nouns and addresses which it’s really important not to mess up 3) cannot be inferred from context.
Typical OCR pipeline would be to pass the doc through a character-level OCR system then correct errors with a statistical model like an LLM. An LLM can help correct “crodit card” to “credit card” but it cannot correct names or numbers. It’s really bad if it replaces a 7 with a 2.
Re: Mistral OCR
#58The 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…
What do you mean by "free"? Using the OpenAI vision API, for example, for OCR is quite a bit more expensive than $1/1k pages.
Re: Mistral OCR
#59Bit unrelated but is there anything that can help with really low resolution text? My neighbor got hit and run the other day for example, and I've been trying every tool I can to make out some of the letters/numbers on the plate https://ibb.co/mr8QSYnj
If it’s a video, sharing a few frames can help as well
Re: Mistral OCR
#60Perusing the web site, it's depressing how much behind Mistral is on basic "how can I make this a compelling hook for customers" for the page.
The notebook link? An ACL'd doc
The examples don't even include a small text-to-markdown sample.
The before/after slider is cute, but useless - SxS is a much better way to compare.
Trying it in "Le Chat" requires a login.
It's like an example of "how can we implement maximum loss across our entire funnel". (I have no doubt the underlying tech does well, but... damn, why do you make it so hard to actually see it, Mistral?)
If anybody tried it and has shareable examples - can you post a link? Also, anybody tried it with handwriting yet?