Auntie PDF – an open source app built using Mistral OCR

I find it challenging to accept something that talks about &quot;OCR&quot; but then I upload a PDF with text in images, and when I query the document after upload, I get a message that says &quot;I can&#x27;t interpret images&quot;..<p>Then are you actually doing OCR, or are you just extracting embedded text?

Sweet branding! Grandma told me she&#x27;s not happy with lack of privacy policy.

I built a CLI tool for experimenting with Mistral OCR here: <a href="https:&#x2F;&#x2F;simonwillison.net&#x2F;2025&#x2F;Mar&#x2F;7&#x2F;mistral-ocr&#x2F;" rel="nofollow">https:&#x2F;&#x2F;simonwillison.net&#x2F;2025&#x2F;Mar&#x2F;7&#x2F;mistral-ocr&#x2F;</a><p>Honestly, the vibes aren&#x27;t great. Gemini is a lot more flexible for handling PDFs - you can prompt it to do a bunch of other things - and Mistral OCR appears to hallucinate if it can&#x27;t correctly read handwriting, a common problem with vision LLM based OCR tools.<p>The way Mistral OCR handles images within the text is disappointing - it doesn&#x27;t attempt to interpret them, just extracts them out as binary blobs. A vision LLM can usually do a great job of describing an image, but with Mistral OCR you have to manually run that as a separate step.

OK I&#x27;ve been critical of Mistral AI but credit where credit is due. Mistral OCR seems cool.<p>So cool in fact, I got distracted and ended up building an open source PDF parser and chat app!<p>Presenting Auntie PDF - your all-knowing guide that unpacks every PDF into clear, actionable insights.<p>You can upload a pdf or point to a public link, parse it, and then ask questions. All open source and free.

I have a question about Mistral OCR. If I give the model a PDF that is 90% text, is it actually performing OCR on an image representation of the text? Or is it smart enough to extract the text directly and only use OCR on images?

Love the creativity in the branding but it did not work in my case either. Gibberish raw content and error in answering any question.

What are people using these OCR programs for? Are there really that many PDFs being made without embedded text these days?

It looks great, nice work. I’m impressed at the quick development too.

Thanks for creating, really useful!<p>Would be nice with a [Download Combined Rendered] button to download a self-contained .html web page of the rendered combined page.

I would like it if my chat session did not clear if go to Document Content and back to chat. Or I wish I could see my document when chatting.

Is there a way to use mistral ocr on us servers so your data never leaves our borders?

Unfortunate that Mistral OCR can&#x27;t tell me details presented in charts and graphs.

Pretty impressive and did a good job for an academic pdf I uploaded. Nice UI also.

This is amazing. Could you share the prompts that were used for this product ?

The coolest thing about this is the short and easy to pronounce .com

im on mobile and don’t have a pdf to test it with, but I love your styling and text copy.

what about privacy?

Awesome UI!