How to use Markitdown (microsoft/markitdown): 3 use cases

3 use cases

Turn Word, Excel and PDF files into Markdown for an LLM

Install MarkItDown and convert a folder of documents into token-efficient Markdown an LLM can read.
- REPO microsoft/markitdown
- Claude Code
- Codex
- Cursor
- Research
- Beginner
View prompt
```
Install microsoft/markitdown with `pip install 'markitdown[all]'` and convert every file in <folder> to Markdown with `markitdown <file> -o <name>.md`. Put the results in <output folder> and list any file that failed to convert and why.
```
Pull text out of images inside PDFs and slides

Add the markitdown-ocr plugin so text in embedded images is extracted with a vision LLM.
- REPO microsoft/markitdown
- Claude Code
- Codex
- Cursor
- Research
- Intermediate
View prompt
```
Using microsoft/markitdown with the markitdown-ocr plugin, convert <file> to Markdown with an OpenAI-compatible client and model <model>. Show me which text came from embedded images that the plain converter missed.
```

Extract invoice fields into YAML front matter

Route PDFs through Azure Content Understanding or Document Intelligence to get structured fields with the Markdown.

View prompt

Using microsoft/markitdown with Azure Content Understanding, convert the invoices in <folder> to Markdown with structured fields. Restrict cloud routing to PDFs with cu_file_types and give me a table of VendorName and InvoiceDate from the front matter.

Quick start with Markitdown

Check you have what it needs: Python 3.10 through 3.14, ideally in a virtual environment; Optional dependency groups for each format, or [all] for everything; Optional: an OpenAI-compatible client for image descriptions and the markitdown-ocr plugin.
Open microsoft/markitdown on GitHub and read the README and license.
Create a virtual environment with python -m venv .venv and activate it with source .venv/bin/activate
Install everything with pip install 'markitdown[all]', or only the formats you need with pip install 'markitdown[pdf, docx, pptx]'
Convert one file with markitdown path-to-file.pdf -o document.md
Or pipe content in with cat path-to-file.pdf | markitdown

These steps come from our top use case, Turn Word, Excel and PDF files into Markdown for an LLM, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for microsoft/markitdown

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Best AI repos for Research

About this repo

Who it is forDevelopers and analysts who need to feed office documents, PDFs and other files into an LLM or a text pipeline as clean Markdown.
Why it is hot193k stars, talked about in 2 AI sources we track
LanguagePython
Sourcegithub.com/microsoft/markitdown · Back to Hot repos

Requirements

Python 3.10 through 3.14, ideally in a virtual environment
Optional dependency groups for each format, or [all] for everything
Optional: an OpenAI-compatible client for image descriptions and the markitdown-ocr plugin
Optional: an Azure Document Intelligence or Content Understanding resource, which is billed per call

Add this badge to your README

Maintain Markitdown? Show readers where to find these use cases.

Markdown

[![Use cases on Deduped](https://dedupedai.com/badge/microsoft/markitdown.svg)](https://dedupedai.com/use-cases/microsoft-markitdown/?utm_source=github&utm_medium=badge&utm_campaign=microsoft-markitdown)

HTML

<a href="https://dedupedai.com/use-cases/microsoft-markitdown/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=microsoft-markitdown"><img src="https://dedupedai.com/badge/microsoft/markitdown.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Markitdown

What is Markitdown?

MarkItDown is a lightweight Python utility from Microsoft that converts files to Markdown for use with LLMs and text analysis pipelines. It handles PDF, PowerPoint, Word, Excel, images, audio, HTML, CSV, JSON, XML, ZIP files, YouTube URLs and EPubs, keeping structure such as headings, lists, tables and links, and it works from the command line, from Python or in Docker. It is an open-source project on GitHub: https://github.com/microsoft/markitdown.

How do I use Markitdown?

Create a virtual environment with python -m venv .venv and activate it with source .venv/bin/activate; then install everything with pip install 'markitdown[all]', or only the formats you need with pip install 'markitdown[pdf, docx, pptx]'; Convert one file with markitdown path-to-file.pdf -o document.md. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Markitdown for?

Developers and analysts who need to feed office documents, PDFs and other files into an LLM or a text pipeline as clean Markdown.

What can I do with Markitdown?

3 use cases so far, for example: Turn Word, Excel and PDF files into Markdown for an LLM; Pull text out of images inside PDFs and slides; Extract invoice fields into YAML front matter. Each has steps and a copy-paste agent prompt.

What do I need to run Markitdown?

Python 3.10 through 3.14, ideally in a virtual environment; Optional dependency groups for each format, or [all] for everything; Optional: an OpenAI-compatible client for image descriptions and the markitdown-ocr plugin; Optional: an Azure Document Intelligence or Content Understanding resource, which is billed per call.

What are alternatives to Markitdown?

Other hot AI repos in Research: Sam2, Docling, LightRAG, Ragflow, MinerU.

Is Markitdown safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.