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

161–170 of 450 posts

Re: Mistral OCR

#161

Post by kergonath »

nicodjimenez wrote: post #41
jcuenod wrote: post #15

Just tested with a multilingual (bidi) English/Hebrew document. The Hebrew output had no correspondence to the text whatsoever (in context, there was an English translation, and the Hebrew produced was a back-translation of that). Their benchmark results are impressive, don't get me wrong. But I'm a little disappointed. I often read multilingual document scans in the humanities. Multilingual (and esp. bidi) OCR is ch…

You can get bounding boxes from our pdf api at Mathpix.com Disclaimer, I’m the founder

Mathpix is ace. That’s the best results I got so far for scientific papers and reports. It understands the layout of complex documents very well, it’s quite impressive. Equations are perfect, figures extraction works well.

There are a few annoying issues, but overall I am very happy with it.

Re: Mistral OCR

#163

Post by trollied »

hubraumhugo wrote: post #123

It will be interesting to see how all the companies in the document processing space adapt as OCR becomes a commodity. The best products will be defined by everything "non-AI", like UX, performance and reliability at scale, and human-in-the loop feedback for domain experts.

They will offer integrations into enterprise systems, just like they do today.

Lots of big companies don't like change. The existing document processing companies will just silently start using this sort of service to up their game, and keep their existing relationships.

Re: Mistral OCR

#164

Post by kergonath »

cooperaustinj wrote: post #141
WhitneyLand wrote: post #50

1. There’s no simple page / sandbox to upload images and try it. Fine, I’ll code it up. 2. “Explore the Mistral AI APIs” ( https://docs.mistral.ai ) links to all apis except OCR. 3. The docs on the api params refer to document chunking and image chunking but no details on how their chunking works? So much unnecessary friction smh.

There is an OCR page on the link you provided. It includes a very, very simple curl command (like most of their docs). I think the friction here exists outside of Mistral's control.

> There is an OCR page on the link you provided.

I don’t see it either. There might be some caching issue.

Re: Mistral OCR

#166

Post by kiratp »

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.

Re: Mistral OCR

#167

Post by qwertox »

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.

Re: Mistral OCR

#168

Post by evmar »

resiros wrote: post #146
evmar wrote: post #129

I noticed on the Arabic example they lost a space after the first letter on the third to last line, can any native speakers confirm? (I only know enough Arabic to ask dumb questions like this, curious to learn more.) Edit: it looks like they also added a vowel mark not present in the input on the line immediately after. Edit2: here's a picture of what I'm talking about, the before/after: https://ibb.co/v6xcPMHv

Arabic speaker here. No, it's perfect.

I am pretty sure it added a kasrah not present in the input on the 2nd to last line. (Not saying it's not super impressive, and also that almost certainly is the right word, but I think that still means not quite "perfect"?)

Re: Mistral OCR

#170

Post by daemonologist »

pilooch wrote: post #158

But what's the need exactly for OCR when you have multimodal LLMs that can read the same info and directly answer any questions about it ? For a VLLM, my understanding is that OCR corresponds to a sub-field of questions, of the type 'read exactly what's written in this document'.

It's useful to have the plain text down the line for operations not involving a language model (e.g. search). Also if you have a bunch of prompts you want to run it's potentially cheaper, although perhaps less accurate, to run the OCR once and save yourself some tokens or even use a smaller model for subsequent prompts.
Post reply on HN