News for hackers. Stuff that matters.
Re:Auntie PDF – an open source app built using Mistral OCR by sbarre on Friday March 07, 2025 @11:25PM (#43297493)
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?

Re:Auntie PDF – an open source app built using Mistral OCR by 0x62 on Friday March 07, 2025 @11:39PM (#43297550)
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

Re:Auntie PDF – an open source app built using Mistral OCR by themanmaran on Friday March 07, 2025 @11:48PM (#43297580)
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...

Re:Auntie PDF – an open source app built using Mistral OCR by mtillman on Saturday March 08, 2025 @12:19AM (#43297691)
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.
Re:Auntie PDF – an open source app built using Mistral OCR by bilater on Saturday March 08, 2025 @11:04AM (#43301192)
Yes - unfortunately it seems they don't read images in the pdf.
Re:Auntie PDF – an open source app built using Mistral OCR by tmpz22 on Friday March 07, 2025 @11:43PM (#43297567)
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.

Re:Auntie PDF – an open source app built using Mistral OCR by wildzzz on Saturday March 08, 2025 @12:27AM (#43297728)
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.