Unlock the Potential of Your LLMs: Convert Any File to Markdown with MarkItDown

Harness the power of Large Language Models (LLMs) with MarkItDown, the lightweight Python utility that transforms virtually any file into clean, structured Markdown. Stop struggling with incompatible file formats and supercharge your text analysis pipelines today!

Why MarkItDown is a Game-Changer for LLM Workflows

• Universal Compatibility: Converts PDFs, Word documents, PowerPoints, Excels, images, audio files, HTML, text-based formats, ZIPs, YouTube URLs, and even EPUBs into Markdown.
• LLM-Optimized Output: Preserves crucial document structure such as headings, lists, and tables in a format LLMs understand natively.
• Token Efficiency: Leverages Markdown's token-efficient conventions, reducing processing costs and maximizing output quality. Think more insights, less processing time.

Breaking Down the Old Barriers: Simplified Installation and Usage

Get Up and Running in Minutes

Installing MarkItDown is a breeze with pip:

pip install 'markitdown[all]'

This command installs all optional dependencies, ensuring you can convert a wide variety of file types immediately. Need more control? Install specific dependencies:

pip install 'markitdown[pdf, docx, pptx]'

Command-Line Conversion Made Easy

Transform your files with simple commands:

• markitdown path-to-file.pdf > document.md
• markitdown path-to-file.pdf -o document.md
• cat path-to-file.pdf | markitdown (pipe content directly)

Seamless Python Integration

Incorporate MarkItDown directly into your Python scripts:

from markitdown import MarkItDown

md = MarkItDown(enable_plugins=False)
result = md.convert("test.xlsx")
print(result.text_content)

Example: Enhance Image Analysis with LLMs using MarkItDown

from markitdown import MarkItDown
from openai import OpenAI

client = OpenAI()
md = MarkItDown(llm_client=client, llm_model="gpt-4o")
result = md.convert("example.jpg")
print(result.text_content)

Key Features: Level Up Your LLM Workflow

Optional Dependencies: Tailor MarkItDown to your Needs

• [all]: Installs everything for complete format support.
• [pptx], [docx], [xlsx], [xls]: Enable PowerPoint, Word, and Excel processing.
• [pdf]: Convert PDFs with ease.
• [outlook]: Process Outlook messages.
• [az-doc-intel]: Integrates with Azure Document Intelligence for advanced analysis.
• [audio-transcription], [youtube-transcription]: Transcribe audio and YouTube videos directly.

Unleash the Power of Document Intelligence

Enhance conversion accuracy with Microsoft Document Intelligence:

markitdown path-to-file.pdf -o document.md -d -e "<document_intelligence_endpoint>"

Extend Functionality with Plugins

Customize MarkItDown with 3rd-party plugins. Find them on GitHub using the hashtag #markitdown-plugin.

Contribute to the Future of LLM Integration

Your contributions matter! Whether it's reporting issues, reviewing pull requests, or developing plugins, your help is invaluable. Join the community and shape the future of intelligent document processing.