Hacker News Reader

Comment by sbarre | Hacker News Reader

I find it challenging to accept something that talks about "OCR" but then I upload a PDF with text in images, and when I query the document after upload, I get a message that says "I can't interpret images"..

Then are you actually doing OCR, or are you just extracting embedded text?

View on HN

I’d imagine their capabilities mirror that of Mistral OCR [1]. Mistral outputs markdown, the image would have to be convertible to a reasonably useful markdown structure (charts, tables etc).

[1] https://mistral.ai/en/news/mistral-ocr

This highlights the biggest issue I've found with Mistral OCR. Many of the documents I upload are entirely classified as images, which means no OCR is being run.

Pretty much anything with a different colored background gets returned as (image)[image_001].

Example: https://omni-demo-data.s3.us-east-1.amazonaws.com/test/17398...

LLMs tend to be a hammer in search of a nail when it comes to documents that have imagery. We decided on CV models which results in a high 90s midpoint for the docs our customers care about. If you can afford to go with a cv pipeline, it can outperform all of the LLMs by some margin.

Yes - unfortunately it seems they don't read images in the pdf.

Same vein - YouTube most (all?) llm integrations just scrape the transcript. I -think- google's aistudio does more but I'm unsure.

I mean I get it bulk video processing would be crazy expensive, but at least mention you're only analyzing the transcript especially if you're a paid product.

Whisper does do text to speech but yes, nearly all just read off the subtitles. There's a video by f4mi on YouTube where she tricked the summarizing bots with off-screen captions filled with nonsense.

Reply on news.ycombinator.com