LinuxCommandLibrary
GitHubF-DroidGoogle Play Store

docling

Convert documents to Markdown, JSON, HTML, or text

TLDR

Convert a file to Markdown in the current directory
$ docling [path/to/file.pdf]
copy
Write the result to a directory
$ docling [path/to/file.pdf] --output [path/to/directory]
copy
Export images as placeholders or as referenced PNG files
$ docling --image-export-mode [placeholder|referenced] [path/to/file.pdf]
copy
Choose the output format
$ docling --to [json|html|md|text] [path/to/file.pdf]
copy
Skip OCR on a digital PDF
$ docling --no-ocr [path/to/file.pdf]
copy
Use a vision-language model
$ docling --vlm-model granite_docling [https://arxiv.org/pdf/2206.01062]
copy
Show help
$ docling -h
copy

SYNOPSIS

docling [OPTIONS] SOURCE...

DESCRIPTION

docling converts PDF, Office, HTML, and image inputs into Markdown or another structured form. It uses layout analysis and, unless --no-ocr is set, OCR. A source can be a local path or a URL.The package needs Python 3.10 or newer. Release 2.70.0 dropped Python 3.9. The command is the console script of the docling Python package. The CLI also exposes further subcommands; docling --help lists them.Optional pieces such as a VLM model are selected with flags. They are not separate programs.

PARAMETERS

--output DIRECTORY

Write converted files under this directory instead of the current directory.
--image-export-mode MODE
placeholder replaces figures with placeholders. referenced writes PNG files and links them from the output.
--to FORMAT
Output format: json, html, md, or text.
--no-ocr
Do not run OCR. Faster on PDFs that already contain text.
--vlm-model NAME
Select a vision-language model. One name the project documents is the token in the example above.
-h, --help
Show help and exit.

INSTALL

yay -S docling
copy
nix profile install nixpkgs#docling
copy

CAVEATS

Conversion downloads models on first use and can be heavy on CPU. A URL source fetches that document with the privileges of the process.

SEE ALSO

RESOURCES

Copied to clipboard
Kai