# MarkItDown — Convert Any File to Markdown for LLMs

> Python library by Microsoft that converts PDF, DOCX, PPTX, XLSX, images, audio, and HTML to clean Markdown. Perfect for feeding documents into LLM context windows. 8,000+ stars.

## Install

Save in your project root:

## Quick Use

```bash
pip install markitdown
```

```python
from markitdown import MarkItDown

md = MarkItDown()

# Convert any file to Markdown
result = md.convert("report.pdf")
print(result.text_content)

result = md.convert("presentation.pptx")
print(result.text_content)

result = md.convert("spreadsheet.xlsx")
print(result.text_content)
```

CLI usage:
```bash
markitdown report.pdf > report.md
markitdown presentation.pptx > slides.md
```

---

## Intro

MarkItDown is a Python library by Microsoft that converts virtually any document format to clean Markdown with 8,000+ GitHub stars. Feed PDFs, Word docs, PowerPoints, Excel spreadsheets, images (with OCR), audio (with transcription), and HTML into it and get LLM-ready Markdown out. Unlike Docling which focuses on layout-aware PDF parsing, MarkItDown prioritizes breadth — it handles 10+ formats with a single API. Best for developers building RAG pipelines or tools that need to ingest diverse document types. Works with: any LLM pipeline. Setup time: under 1 minute.

---

## Supported Formats

| Format | Extension | Features |
|--------|-----------|----------|
| PDF | .pdf | Text extraction, tables |
| Word | .docx | Headers, lists, tables, images |
| PowerPoint | .pptx | Slide text, speaker notes |
| Excel | .xlsx | Tables with headers |
| HTML | .html | Clean text extraction |
| Images | .jpg, .png | OCR via Azure/OpenAI Vision |
| Audio | .mp3, .wav | Transcription via Whisper |
| CSV | .csv | Table format |
| JSON | .json | Structured text |
| XML | .xml | Text extraction |
| ZIP | .zip | Processes contained files |

### Batch Conversion

```python
from pathlib import Path

md = MarkItDown()
for file in Path("./documents").glob("*.*"):
    result = md.convert(str(file))
    Path(f"./markdown/{file.stem}.md").write_text(result.text_content)
```

### Image OCR (with LLM)

```python
md = MarkItDown(llm_client=openai_client, llm_model="gpt-4o")
result = md.convert("screenshot.png")
# Uses vision model to describe and extract text from images
```

### Audio Transcription

```python
result = md.convert("meeting_recording.mp3")
# Uses Whisper for speech-to-text, outputs as Markdown
```

### RAG Pipeline Integration

```python
from markitdown import MarkItDown
from langchain.text_splitter import RecursiveCharacterTextSplitter

md = MarkItDown()
doc = md.convert("quarterly_report.pdf")
chunks = RecursiveCharacterTextSplitter(chunk_size=512).split_text(doc.text_content)
# Feed chunks into your vector database
```

### MarkItDown vs Docling

| Feature | MarkItDown | Docling |
|---------|-----------|--------|
| Focus | Format breadth | PDF accuracy |
| Formats | 10+ (PDF, DOCX, PPTX, audio...) | 6 (PDF, DOCX, PPTX, HTML...) |
| Table accuracy | Good | Excellent |
| Figure extraction | Basic | Advanced |
| OCR | Via LLM vision | Built-in models |
| By | Microsoft | IBM Research |

### Key Stats
- 8,000+ GitHub stars
- By Microsoft
- 10+ input formats
- Image OCR and audio transcription
- Single API for all formats

### FAQ

**Q: What is MarkItDown?**
A: A Python library by Microsoft that converts PDF, DOCX, PPTX, XLSX, images, audio, and HTML to clean Markdown for LLM consumption.

**Q: Is MarkItDown free?**
A: Yes, open-source under MIT license.

**Q: MarkItDown or Docling?**
A: MarkItDown for diverse formats (10+ types). Docling for high-accuracy PDF parsing with complex layouts.

---

## Source & Thanks

> Created by [Microsoft](https://github.com/microsoft). Licensed under MIT.
>
> [markitdown](https://github.com/microsoft/markitdown) — stars 8,000+

Thanks to Microsoft for making document-to-Markdown universal.

---

<!-- ZH -->

## 快速使用

```bash
pip install markitdown
markitdown report.pdf > report.md
```

---

## 简介

MarkItDown 是微软开发的 Python 库，GitHub 8,000+ stars。将 PDF、DOCX、PPTX、XLSX、图片、音频和 HTML 转换为干净 Markdown。支持 10+ 格式，单一 API。适合构建需要摄取多种文档类型的 RAG 管道。

---

## 来源与感谢

> Created by [Microsoft](https://github.com/microsoft). Licensed under MIT.
>
> [markitdown](https://github.com/microsoft/markitdown) — stars 8,000+

---
Source: https://tokrepo.com/en/workflows/6fdc90c2-bede-4d3a-98d7-faf751dfb41f
Author: AI Open Source