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

301–310 of 450 posts

Re: Mistral OCR

#301

Post by WhitneyLand »

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.

How is it out of their control to document what they mean by chunking in their parameters?

Re: Mistral OCR

#302

Post by anon373839 »

menaerus wrote: post #84
sunami-ai wrote: post #69

Making Transformers the same cost as CNN's (which are used in character-level ocr, as opposed to image-patch-level) is a good thing. The problem with CNN based character-level OCR is not the recognition models but the detection models. In a former life, I found a way to increase detection accuracy, and, therefore, overall OCR accuracy, and used that as an enhancement on top of Amazon and Google OCR. It worked really…

It certainly isn't the same cost if expressed as a non-subsidized $$$ one needs for the Transformers compute aka infra. CNNs trained specifically for OCR can run in real time on as small compute as a mobile device is.

A bit of a tangent, but aren’t CNNs still dominating over ViTs among computer vision competition winners?

Re: Mistral OCR

#303

Post by unboxingelf »

cxie wrote: post #70
unboxingelf wrote: post #47

Earlier quoted context omitted.

We’ll just stick LLM Gateway LLM in front of all the specialized LLMs. MicroLLMs Architecture.

I actually think you're onto something there. The "MicroLLMs Architecture" could mirror how microservices revolutionized web architecture. Instead of one massive model trying to do everything, you'd have specialized models for OCR, code generation, image understanding, etc. Then a "router LLM" would direct queries to the appropriate specialized model and synthesize responses. The efficiency gains could be substantial…

Take a look at MCP, Model Context Protocol.

Re: Mistral OCR

#304

Post by simpaticoder »

JBiserkov wrote: post #287
simpaticoder wrote: post #211

Earlier quoted context omitted.

Another good example would be contracts of any kind. Imagine photographing a contract (like a car loan) and on the spot getting an AI to read it, understand it, forecast scenarious, highlight red flags, and do some comparison shopping for you.

... imagining ... ... hallucinating during read ... ... hallucinating during understand ... ... hallucinating during forecast ... ... highlighting a hallucination as red flag ... ... missing an actual red flag ... ... consuming water to cool myself... Phew, being an AI is hard!

Your points are well-taken, but I think that contracts are a small enough, and well represented enough in the corpus, to actually be pretty solid. This is especially true with good prompting and some sort of feedback loop.

Re: Mistral OCR

#305

Post by nextworddev »

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…

Your customer includes Checkr? Impressive. Are they referencable?

Re: Mistral OCR

#306

Post by low_tech_punk »

This might be a contrarian take: the improvement against gpt-4o and gemini-1.5 flash, both of which are general purpose multi-modal models, seem to be underwhelming.

I'm sensing another bitter lesson coming, where domain optimized AI will hold a short term advantage but will be outdated quickly as the frontier model advances.

Re: Mistral OCR

#308

Post by schcrosby »

dontlikeyoueith wrote: post #277
kbyatnal wrote: post #248

Earlier quoted context omitted.

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.

Why would you do this and not use Textract?

I too have this question.

Re: Mistral OCR

#310

Post by ritvikpandey21 »

as builders in this space, we decided to put it to the test on complex nested tables, pie charts, etc. to see if the same VLM hallucination issues persist, and to what degree. while results were promising, we found several critical failure nodes across two document domains.

check out our blog post here! https://www.runpulse.com/blog/beyond-the-hype-real-world-tes...

Post reply on HN