Docling

license

MIT(OSI)

source

public(github.com/docling-project/docling)

self-host

primary

core features withheld

no

Docling's code is MIT-licensed and public, and it runs entirely on the user's own machines, including air-gapped ones. Its layout and table-structure models are published on Hugging Face under the permissive Apache-2.0 and CDLA-Permissive-2.0 licenses, so nothing it needs to run is held back.

• https://github.com/docling-project/docling recorded 2026-08-13

  Repo page - MIT badge, 64,719 stargazers. "Local execution capabilities for sensitive data and air-gapped environments"; open-weight VLMs such as GraniteDocling driven from the CLI; docling-serve as the self-run API server. No paid tier, license key or enterprise directory.

• https://huggingface.co/api/models/docling-project/docling-layout-heron recorded 2026-09-28

  Hugging Face model record for Docling's Heron layout model, "docling-project/docling-layout-heron", tagged "license:apache-2.0".

• https://huggingface.co/api/models/docling-project/docling-models recorded 2026-09-28

  Hugging Face model record for "docling-project/docling-models", the table-structure weights, tagged "license:cdla-permissive-2.0" and "license:apache-2.0".

• https://raw.githubusercontent.com/docling-project/docling/main/LICENSE recorded 2026-09-28

  The raw LICENSE is the standard MIT text, "Copyright The Docling Contributors", granting "Permission is hereby granted, free of charge, to any person obtaining a copy" with no added restriction.

• https://raw.githubusercontent.com/docling-project/docling/main/README.md recorded 2026-09-28

  The raw README states "The Docling codebase is under MIT license." and lists "Local execution capabilities for sensitive data and air-gapped environments" and running "Docling as a service" through docling-serve. Searched the body for enterprise, pricing, paid, subscription and license key: none.

Docling's adoption is measured by PyPI downloads of the docling package by itself. A separate package, docling-core, adds further downloads that are not included in this count.

• https://pypistats.org/api/packages/docling/recent recorded 2026-10-07

  2,909,751 downloads in the trailing 30 days for docling (pypistats last_month)

Docling parses PDF, Office, HTML, EPUB, audio, video and image inputs into Markdown, HTML or lossless JSON with layout, reading order and table structure preserved. Its extractor goes further, returning the fields a user defines in a dictionary or Pydantic template, such as an invoice's bill number and total, from PDFs and images.

• https://docling-project.github.io/docling/_generated/examples/extraction/ recorded 2026-09-29

  The Information extraction example states "Docling provides the capability of extracting information, i.e. structured data, from unstructured documents." and that the user supplies a template "either as a dictionary or as a Pydantic model, and Docling will return" the extracted data; its "Using a dict template" example returns a bill number and a total of "3949.75" from an invoice.

• https://github.com/docling-project/docling recorded 2026-08-13

  Feature list - PDF, DOCX, PPTX, XLSX, HTML, EPUB, WAV, MP3, WebVTT, Box Notes, EML/MSG, images, LaTeX, DocLang and plain text input; "Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification"; export to Markdown, HTML, WebVTT, DocLang, DocTags and lossless JSON; "Extensive OCR support for scanned PDFs and images"; VLM support; "Audio support with Automatic Speech Recognition (ASR) models"; "Connect to any agent using the MCP server"; video parsing under What's new.

• https://raw.githubusercontent.com/docling-project/docling/main/docling/document_extractor.py recorded 2026-09-29

  The package source defines the extractor as a "Standalone extractor class." whose public API is "`extract(...) -> ExtractionResult`" and which imports "from docling.pipeline.extraction_vlm_pipeline import ExtractionVlmPipeline".

• https://raw.githubusercontent.com/docling-project/docling/main/README.md recorded 2026-09-29

  The raw README feature list: "Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more", export to "Markdown, HTML, WebVTT, DocLang", "Extensive OCR support for scanned PDFs and images", "Audio support with Automatic Speech Recognition (ASR) models", "Parsing of video files (MP4, AVI, MOV, MKV, and WebM)", "Parsing of ODF (OpenDocument Format) files" and "Chart understanding (Barchart, Piechart, LinePlot)".