RAG & Knowledge
QAnything
Local knowledge-base Q&A over PDFs, Office files, images and web pages - offline and CPU-friendly.
★ 14.2k starsAGPL-3.0
View guide →LibreAI / RAG & Knowledge / MarkItDown
// rag · microsoft/markitdown
MarkItDown
MarkItDown is an open-source rag & knowledge project by microsoft (microsoft/markitdown on GitHub). It has 193,515 GitHub stars and 14,515 forks, is released under the MIT license, and was last updated on GitHub on 28 October 2026.
MarkItDown — Microsoft tool that converts PDFs, Office files, images and more to clean Markdown for LLMs, MIT
★ 193.5k stars⑂ 14.5k forksMITupdated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- microsoft/markitdown
- GitHub stars
- 193,515
- Forks
- 14,515
- License
- MIT
- Last updated on GitHub
- 28 October 2026
- Category
- RAG & Knowledge
- Listing
- Full install guide
// how it works
How it works
- Install with the extras you need
Install the full set with markitdown[all], or only the format extras you need — for example markitdown[pdf, docx, pptx].
- Convert from the command line
Point the markitdown command at a file and redirect the Markdown output to a file, or pipe a document through it.
- Or use it as a library
Import MarkItDown in Python and convert documents inside your own pipeline, with optional LLM-backed description for images.
// features
Why people love it
Built for LLM pipelines
Output is Markdown that preserves headings, lists, tables and links — exactly what retrieval and analysis tools need.
Very broad format coverage
PDF, Office formats, images, audio, HTML, CSV, JSON, XML and archives, with OCR and transcription where a format needs it.
Install only what you need
Format extras keep the install small: add pdf, docx, pptx, Azure Document Intelligence or other extras individually.
Library and CLI in one
A command-line tool for one-off conversions and a Python library for embedding conversion in a pipeline.
Advertisement
// run it
Run it yourself
- Install everything
The README install route with all format extras.
pip install 'markitdown[all]' - Convert a PDF
The README command-line route: convert and save the Markdown.
markitdown path-to-file.pdf -o document.md - Use it in Python
The library route: import and convert inside your own code.
from markitdown import MarkItDown - Install from source
Clone and install the package in editable mode with all extras.
git clone https://github.com/microsoft/markitdown.git pip install -e 'packages/markitdown[all]'
// use cases
What you can build
- Feeding PDFs and Office documents into RAG pipelines as clean Markdown
- Converting research papers, reports and decks for LLM analysis
- Building document-ingestion steps for agents and search tools
- Turning mixed file archives into one uniform Markdown corpus
Advertisement
// faq
Questions, answered
Who makes MarkItDown?
Microsoft, as a lightweight document-to-Markdown utility for LLM workflows.
Is MarkItDown free?
Yes — MIT licensed.
What formats does it handle?
PDF, Word, PowerPoint, Excel, images (EXIF and OCR), audio (EXIF and transcription), HTML, CSV, JSON, XML and ZIP archives, plus Azure-backed extras.
Is it a high-fidelity document converter for humans?
No — the README says so plainly: output is meant for text-analysis tools and may not suit high-fidelity human conversion.
How do I get started?
pip install 'markitdown[all]', then run markitdown on a file, or import MarkItDown in Python.
// keep exploring
Similar tools
RAG & Knowledge
Marker
Marker — converts PDFs to Markdown and JSON quickly and accurately, with layout, tables and math intact, Apache-2.0
★ 40.6k starsApache-2.0
View guide →RAG & Knowledge
MinerU
MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms
★ 82.5k starsApache-2.0 + terms
View guide →RAG & Knowledge
opendataloader-pdf
Turn PDFs into AI-ready data: extract Markdown, JSON and tables — and auto-tag for accessibility
★ 29.5k starsApache-2.0
View guide →RAG & Knowledge
PaddleOCR
Lightweight OCR toolkit turning PDFs and images into structured, LLM-ready data in 100+ languages
★ 90.8k starsApache-2.0
View guide →RAG & Knowledge
nano-graphrag
nano-graphrag: a small, hackable GraphRAG implementation in about 1,100 lines — no Microsoft GraphRAG bulk
★ 4.0k starsMIT
View guide →// alternatives
Alternatives in RAG & Knowledge
The most-starred other RAG & Knowledge projects in the LibreAI catalogue — the realistic shortlist if MarkItDown is not the right fit.
- Dify★ 157.8k
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or…
- ragflow★ 91.6k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context…
- PaddleOCR★ 90.8k
Lightweight OCR toolkit turning PDFs and images into structured, LLM-ready data in 100+ languages
- MinerU★ 82.5k
MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms
- anything-llm★ 66.7k
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
// more in rag
More in RAG & Knowledge
Nearby RAG & Knowledge projects in the catalogue, closest in stars to MarkItDown — keep exploring the shelf either side of it.
- docuchat.app★ 35
Private document chat for attorneys: local LLMs, verifiable citations.
- Dify★ 157.8k
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or…
- InsightPDF★ 49
Chat with PDFs and see exactly where each answer was found.
- ragflow★ 91.6k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context…
- qdrant-loader★ 55
Free rag & knowledge tool that enterprise-ready vector database toolkit for building s.
- PaddleOCR★ 90.8k
Lightweight OCR toolkit turning PDFs and images into structured, LLM-ready data in 100+ languages
Get MarkItDown
Free and open — grab the source, star the repo, and start creating.