Docling
Docling prepares documents for generative AI applications, according to its project description.
About Docling
Docling is an open-source Python project that prepares documents for generative AI applications by parsing many formats into a unified document representation. It processes PDF layout, reading order, tables, formulas and code, applies OCR to scanned PDFs and images, transcribes audio and video, and exports to Markdown, HTML, JSON and other formats for use through a CLI, Python library, API server or MCP server.
It requires Python 3.10 or higher and runs on macOS, Linux and Windows on x86_64 and arm64.
Key features
- Parses PDF, DOCX, PPTX, XLSX, HTML, EPUB and many other formats
- Extracts PDF layout, reading order, tables, formulas and code
- Exports to Markdown, HTML, JSON, DocTags and WebVTT
- Applies OCR to scanned PDFs and images
- Transcribes audio and video files with speech recognition
- Integrates with LangChain, LlamaIndex, Crew AI and Haystack
Best for: Developers building generative AI applications that need structured text from varied documents.
Good for
- Supports many input formats including documents, images, audio and video
- Provides local execution capability described for sensitive and air-gapped environments
- Runs on macOS, Linux and Windows on x86_64 and arm64
Watch out for
- Requires Python 3.10 or higher; Python 3.9 support was dropped
- Metadata extraction and chemistry understanding are listed as coming soon
Docling at a glance
- Category
- Software & Utilities › File Utilities
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Guides for File Utilities
Docling alternatives
Tools and sites you could use instead, ranked by how closely they match.
Browse and print file contents with bat, a command-line cat alternative documented in this repository.
Open source
24 alternatives
Efficient Compression Tool optimizes PNG, JPEG, GZIP, and ZIP files through a C++ file-optimization utility.
Open source
24 alternatives
Umi-OCR processes screenshots, image batches, and PDF documents offline, with OCR support for multiple languages.
Open source
24 alternatives
Magika detects file content types using an AI-based file identification tool, according to its repository description.
Open source
24 alternatives
Phockup sorts photos and videos from a camera into folders by year, month, and day.
Open source
24 alternatives
TextShot takes a screenshot and copies its text to the clipboard using Python, on Windows, macOS, and Linux.
Open source
24 alternativesPopular in File Utilities
Well-known listings from the same topic.
SDeletelearn.microsoft.com/en-us/sysinternals/downloa…PowerRenamelearn.microsoft.com/en-us/windows/powertoys/po…robocopylearn.microsoft.com/windows-server/administrat…VERTvert.shNanaZipnanazip.orgPhotonphotondev.netlify.app
Docling FAQ
How do I install Docling?
Install with pip install docling using Python 3.10 or higher.
How do I convert a document from the command line?
Run docling followed by a local path or URL, which creates a Markdown file in the current directory.
Which operating systems and architectures are supported?
macOS, Linux and Windows on both x86_64 and arm64.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.