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

241–250 of 450 posts

Re: Mistral OCR

#241

Post by euleriancon »

lukasb wrote: post #229
bondolo wrote: post #180

Such a shame that PDF doesn’t just, like, include the semantic structure of the document by default. It is brilliant that we standardized on an archival document format that doesn’t include direct access to the document text or structure as a core intrinsic default feature. I say this with great anger as someone who works in accessibility and has had PDF as a thorn in my side for 30 years.

Even assuming you could get people to do the work (probably the real issue here) could a single schema syntax capture the semantics of the universe of documents that exist as PDFs? PDFs succeeded because they could reproduce anything.

html

Re: Mistral OCR

#242

Post by sha16 »

kiratp wrote: 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.

I wanted to apply OCR to my company's invoicing since they basically did purchasing for a bunch of other large companies, but the variability in the conversion was not tolerable. Even rounding something differently could catch an accountant's eye, let alone detecting a "8" as a "0" or worse.

Re: Mistral OCR

#243

Post by troyvit »

pqdbr wrote: post #68

I tried with both PDFs and PNGs in Le Chat and the results were the worst I've ever seen when compared to any other model (Claude, ChatGPT, Gemini). So bad that I think I need to enable the OCR function somehow, but couldn't find it.

It worked perfectly for me with a simple 2 page PDF that contained no graphics or formatting beyond headers and list items. Since it was so small I had the time to proof-read it and there were no errors. It added some formatting, such as bolding headers in list items and putting tics around file and function names. I won't complain.

Re: Mistral OCR

#244

Post by KeplerBoy »

rtsil wrote: post #208
pzo wrote: post #150

Earlier quoted context omitted.

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).

How do you define 99% accuracy?

I guess something like success rate for a trip (or mile) would be a more reasonable metric. Most people have a success rate far higher than 99% for averages trips.

Most people who commute daily are probably doing something like a 1000 car rides a year and have minor accidents every few years. 99% success rates would mean monthly accidents.

Re: Mistral OCR

#245

Post by lblume »

lysace wrote: post #196

Nit: Please change the URL from https://mistral.ai/fr/news/mistral-ocr to https://mistral.ai/news/mistral-ocr The article is the same, but the site navigation is in English instead of French. Unless it's a silent statement, of course. =)

For me, the second page redirects to the first. (And I don't live in France.)

Re: Mistral OCR

#246

Post by troyvit »

roboben wrote: post #45

Le chat doesn’t seem to know about this change despite the blog post stating it. Can anyone explain how to use it in Le Chat?

I asked LeChat this question:

If I upload a small PDF to you are you able to convert it to markdown?

LeChat said yes and away we went.

Re: Mistral OCR

#248

Post by kbyatnal »

techwizrd wrote: post #223
kbyatnal wrote: post #140

We're approaching the point where OCR becomes "solved" — very exciting! Any legacy vendors providing pure OCR are going to get steamrolled by these VLMs. However IMO, there's still a large gap for businesses in going from raw OCR outputs —> document processing deployed in prod for mission-critical use cases. LLMs and VLMs aren't magic, and anyone who goes in expecting 100% automation is in for a surprise. You still n…

The challenge I have is how to get bounding boxes for the OCR, for things like redaction/de-identification.

yeah that's a fun challenge — what we've seen work well is a system that forces the LLM to generate citations for all extracted data, map that back to the original OCR content, and then generate bounding boxes that way. Tons of edge cases for sure that we've built a suite of heuristics for over time, but overall works really well.

Re: Mistral OCR

#249

Post by submeta »

Is this able to convert pdf flowcharts into yaml or json representations of them? I have been experimenting with Claude 3.5. It has been very good at readig / understanding/ converting into representations of flow charts.

So I am wondering if this is more capable. Will try definitely, but maybe someone can chime in.

Re: Mistral OCR

#250

Post by gpvos »

jgalt212 wrote: post #177
qwertox wrote: post #167

We developers seem to really dislike PDFs, to a degree that we'll build LLMs and have them translate it into Markdown. Jokes aside, PDFs really serve a good purpose, but getting data out of them is usually really hard. They should have something like an embedded Markdown version with a JSON structure describing the layout, so that machines can easily digest the data they contain.

I think you might be looking for PDF/A. https://www.adobe.com/uk/acrobat/resources/document-files/pd... For example, if you print a word doc to PDF, you get the raw text in PDF form, not an image of the text.

PDF/A doesn't require preserving the document structure, only that any text is extractable.
Post reply on HN