markitdown

You don't need to use an online service to do this; you get to avoid spending money on tokens doing it offline. Gemma 4 works perfectly well offline on limited hardware (I have an 8GB video card) and can handle extracting text from image-based PDFs just fine. Take a PDF -> run it through MarkItDown [1], using the OCR plugin if you need (point it to Gemma 4) -> now you can ask Gemma 4 questions about the (markdown) document. I am sure Gemma 4 could even create a GUI to make this process very simple for a non technical user. [1] https://github.com/microsoft/markitdown

Related: https://github.com/microsoft/markitdown

I have a standing instruction for any documents that can't natively be read by a given AI to first be converted into .md using https://github.com/microsoft/markitdown which I've found to work really well

Native support: https://techcommunity.microsoft.com/blog/onedriveblog/introd... Microsoft OSS python: https://github.com/microsoft/markitdown There seem to be many addons that enable this, and pandoc as others have suggested

I use markitdown[0] religiously. You’ll lose fidelity for anything complex (math equations, images), but it does a great job 95% of the time in my experience. I’m assuming the attack surface is reduced. I invoke it through a docker container. But this might be a misplaced sense of safety. [0] https://github.com/microsoft/markitdown

No shade, but it that essentially (or literally) a monetized UI for https://github.com/microsoft/markitdown - if yes respect . If no then also respect for making something

This made me think of Microsoft's MarkItDown tool/library [1] which seems to have quite the overlap in supported file formats [2,3] and conversion options [4]. I couldn't find any reference to the library on the website, so it may be useful to know about. [1] https://github.com/microsoft/markitdown [2] https://tomd.io/#supported-extensions [3] https://github.com/microsoft/markitdown/tree/main/packages/m... [4] https://github.com/microsoft/markitdown/blob/8a9d8f15936b206...

Even though markitdown is a Microsoft project, it's just a thin wrapper around a bunch of 3rd party Python packages. For example, to go from docx to Markdown, it uses mammoth to convert docx to HTML[0], then uses markdownify to convert the HTML into Markdown[1]. [0]https://github.com/microsoft/markitdown/blob/da7bcea527ed04c... [1]https://github.com/microsoft/markitdown/blob/da7bcea527ed04c...

I wonder if this tool by MSFT is able to handle that: https://github.com/microsoft/markitdown I was amazed when I realised that Word docs were just zip files and you could poke around in the xml files embedded inside of them. I almost implemented a working React -> Word document renderer back in 2017, but it didn't have support for creating the xml tags with : inside of them (which OOXML documents use).

> the python library from Microsoft that converts all of their formats to markdown Thank you for pointing me to the MarkItDown library [1]. I had no idea such a thing existed. [1] https://github.com/microsoft/markitdown

How it compares to https://github.com/microsoft/markitdown?

Maybe I'm an out-of-touch nerd who needs to touch grass, but I would love to see a world where Markdown has supplanted this glorified suite of XML editors. Markdown has docs, slides, tables, diagrams (via Mermaid), and can be read on any system that has a text editor. It's simple, non-proprietary, and future proof. This repo says it all: https://github.com/microsoft/markitdown

This is quite cool https://github.com/microsoft/markitdown Is anybody already making a difference using this thing? Seems this might be quite a building block for company RAGs :-)