markitdown
by microsoft · AI
Python tool for converting files and office documents to Markdown.
★ New0 ratings178,748 stars● Active
AIDeveloper ToolPythonDockerfile
About this project
MarkItDown is a lightweight Python utility that converts a wide range of files and office documents into Markdown, with an emphasis on preserving the important structure and content of the original document. It is built for feeding documents into large language models and related text-analysis pipelines, and is comparable in purpose to textract. Because it performs I/O with the privileges of the calling process, it should be used with sanitized inputs in untrusted environments.
Technologies
PythonDockerfileautogenautogen-extensionlangchain
Project health
● Actively maintained
Last update4 days ago
Contributors117
Latest releasev0.1.7
Open issues & PRs613
LicenseMIT
On GitHubsince 2024
GitHub
178,748
stars
13,171
forks
117
contributors
613
open issues & PRs
Python
language
4 days ago
last commit
Reviews
No reviews yet
Be the first to review markitdown.
Built by
microsoft
Imported from GitHub · not yet claimed on GitPalace
Maintain microsoft/markitdown? Claiming verifies admin access through your GitHub account and gives you control of this listing.
