MarkItDown Reviews

Medium Reviews

MarkItDown mentions (15)

• Meta Caps Internal AI Token Spending After Costs Approach Billions in 2026

  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 document.... - Source: Hacker News / 28 days ago

• Jimmy is a tool to convert your notes from different formats to Markdown

  Related: https://github.com/microsoft/markitdown. - Source: Hacker News / about 1 month ago

• Computer use in Gemini 3.5 Flash

  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. - Source: Hacker News / about 1 month ago

• Ask HN: How should I convert Microsoft Word documents to Markdown?

  Native support: https://techcommunity.microsoft.com/blog/onedriveblog/introducing-markdown-support-in-sharepoint-and-onedrive/4512174 Microsoft OSS python: https://github.com/microsoft/markitdown. - Source: Hacker News / about 1 month ago

• The Best PDF to Markdown Tools in 2026 (Honestly Compared)

  Microsoft's open-source MarkItDown is a Python library and CLI that converts PDFs (plus Office files, images, audio and more) into Markdown aimed squarely at language models. It's fast, free, and trivial to drop into a script. - Source: dev.to / about 2 months ago

Medium mentions (3095)

• Judge Rejects Google's Attempt to DMCA Its Way Out of Being Scraped

  Why is a "Disable Javascript" option provided in every so-called "modern" browser Why would a user prefer in some cases not to use a third party's Javascript Depends on the user. For example, here's one user who publishes a website on the subject https://disable-javascript.org/ Consider the level of data collection and behavioral surveillance enabled by the SearchGuard Javascript at issue in Google LLC v SerpApi... - Source: Hacker News / 2 days ago

• I'm 38 and I Can't Support Myself Anymore

  'If we all woke up tomorrow and thought 'we need 10 million new homes'' The cost of 1 Million homes where people want to live (where your community is), would be roughly 0.5 Trillion to 1 Trillion USD [1]. So, I don't think this is true :(. Again, I want this to be true. But it is not today. [1]: https://medium.com/@dtxtransitposts/how-much-does-it-actually-cost-to-build-housing-14e5fcf35208. - Source: Hacker News / 1 day ago

• Our position on open-weights models

  The letter misses out the key issue here. Should the worlds public knowledge be enclosed by a few powerful private companies or should it be available to all? The original vision for the web was a decentralized, open information sharing space designed to empower humanity. In my view the effort to privatise that via LLM distillation is the antithesis of that vision.... - Source: Hacker News / 2 days ago

• My security camera shipped a GitHub admin token in its login page

  Quantenna used 1.1.1.1 for RPC to their wifi chip in their SDK by default. Should not have been exposed to global routing but of course people screwed that up. https://medium.com/@mrtcve/atts-misuse-of-cloudflare-dns-ip-1-1-1-1-e64901e41a09. - Source: Hacker News / 5 days ago

• Jane Street: Incremental

  It depends on how you define the observable pattern. The fundamental components here are laziness and weak connections between graph nodes. Node values are getting materialized only when you observe them, and the system is flexible for live structural changes. Usually, you don't need to materialize the entire graph when you need to observe just some nodes. Additionally, you can halt computations at any point in... - Source: Hacker News / 9 days ago