## 1. Project Overview & Quickstart (docling-project/docling) ## File: README.md # Docling [](https://arxiv.org/abs/2408.09869) [](https://docling-project.github.io/docling/) [](https://pypi.org/project/docling/) [](https://pypi.org/project/docling/) [](https://github.com/astral-sh/uv) [](https://github.com/astral-sh/ruff) [](https://pydantic.dev) [](https://pypi.org/project/prek/) [](https://opensource.org/licenses/MIT) [](https://pepy.tech/projects/docling) [](https://apify.com/vancura/docling) [](https://app.dosu.dev/097760a8-135e-4789-8234-90c8837d7f1c/ask?utm_source=github) [](https://docling.ai/discord) [](https://www.bestpractices.dev/projects/10101) [](https://lfaidata.foundation/projects/) ## What is Docling ? Docling simplifies document processing by parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the generative AI ecosystem. ## Features - 🗂️ Parsing of [multiple document formats][supported_formats] including PDF, DOCX, PPTX, XLSX, HTML, EPUB, WAV, MP3, WebVTT, Box Notes, email formats (EML, MSG), images (PNG, TIFF, JPEG, ...), LaTeX, DocLang, plain text, and more - 📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more - 🧬 A unified, expressive [DoclingDocument][docling_document] representation format - ↪️ Various [export formats][supported_formats] and options, including Markdown, HTML, WebVTT, DocLang, [DocTags](https://arxiv.org/abs/2503.11576) and lossless JSON - 📜 Support for several application-specific XML schemas including [DocLang](https://doclang.ai), [USPTO](https://www.uspto.gov/patents) patents, [JATS](https://jats.nlm.nih.gov/) articles, and [XBRL](https://www.xbrl.org/) financial reports. - 🔒 Local execution capabilities for sensitive data and air-gapped environments - 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI - 🔍 Extensive OCR support for scanned PDFs and images - 👓 Support for several Visual Language Models, such as ([GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M)) - 🎙️ Audio support with Automatic Speech Recognition (ASR) models - 🔌 Connect to any agent using the [MCP server](https://docling-project.github.io/docling/usage/mcp/) - 🌐 Run Docling as a service with the [API server](https://docling-project.github.io/docling/usage/api_server/) (docling-serve) - 💻 Simple and convenient CLI ### What's new - 🎬 Parsing of video files (MP4, AVI, MOV, MKV, and WebM) with an ASR transcript and representative keyframes - 📄 Parsing of ODF (OpenDocument Format) files for text documents (`.odt`), spreadsheets (`.ods`), and presentations (`.odp`) - 💼 Parsing of XBRL (eXtensible Business Reporting Language) documents for financial reports - 📧 Parsing of email files (`.eml`, `.msg`) - 📚 Parsing of EPUB (Electronic Publication) files for e-books - 📝 Parsing of plain-text files (`.txt`, `.text`) and Markdown supersets (`.qmd`, `.Rmd`) - 📊 Chart understanding (Barchart, Piechart, LinePlot): convert them into tables or code and add detailed descriptions ### Coming soon - 📝 Metadata extraction, including title, authors, references & language - 📝 Complex chemistry understanding (Molecular structures) ## Quickstart ### 1. Install ```bash pip install docling ``` > **Note:** Python 3.9 support was dropped in docling version 2.70.0. Please use Python 3.10 or higher. Works on macOS, Linux and Windows environments for both x86_64 and arm64 architectures. More [detailed installation instructions](https://docling-project.github.io/docling/getting_started/installation/) are available in the docs. ## 2. Convert a document (CLI) ```bash docling https://arxiv.org/pdf/2206.01062 ``` This generates a .md file in the current directory containing structured document content. You can also use 🥚[GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M) and other VLMs via Docling CLI: ```bash docling --pipeline vlm --vlm-model granite_docling https://arxiv.org/pdf/2206.01062 ``` ## 3. Python usage (recommended) ```python from docling.document_converter import DocumentConverter source = "https://arxiv.org/pdf/2408.09869" # a document via a local path or URL converter = DocumentConverter() result = converter.convert(source) print(result.document.export_to_markdown()) # output: "## Docling Technical Report[...]" ``` More advanced [usage](https://docling-project.github.io/docling/usage/) and [configuration](https://docling-project.github.io/docling/getting_started/installation/) options. ## Documentation Check out Docling's [documentation](https://docling-project.github.io/docling/) for details on installation, usage, concepts, recipes, extensions, and more. ## Examples Go hands-on with our [examples](https://docling-project.github.io/docling/examples/), demonstrating how to address different application use cases with Docling. ## Integrations To further accelerate your AI application development, check out Docling's native [integrations](https://docling-project.github.io/docling/integrations/) with popular frameworks and tools. ## Get help and support Please feel free to connect with us using the [discussion section](https://github.com/docling-project/docling/discussions). ## Technical report For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869). ## Contributing Please read [Contributing to Docling](https://github.com/docling-project/docling/blob/main/CONTRIBUTING.md) for details. ## References If you use Docling in your projects, please consider citing the following: ```bib @techreport{Docling, author = {Deep Search Team}, month = {8}, title = {Docling Technical Report}, url = {https://arxiv.org/abs/2408.09869}, eprint = {2408.09869}, doi = {10.48550/arXiv.2408.09869}, version = {1.0.0}, year = {2024} } ``` ## License The Docling codebase is under MIT license. For individual model usage, please refer to the model licenses found in the original packages. ## LF AI & Data Docling is hosted as a project in the [LF AI & Data Foundation](https://lfaidata.foundation/projects/). ### IBM ❤️ Open Source AI The project was started by the AI for knowledge team at IBM Research Zurich. [supported_formats]: https://docling-project.github.io/docling/usage/supported_formats/ [docling_document]: https://docling-project.github.io/docling/concepts/docling_document/ [integrations]: https://docling-project.github.io/docling/integrations/ [extraction]: https://docling-project.github.io/docling/_generated/examples/extraction/ --- ## File: docs/index.md [](https://arxiv.org/abs/2408.09869) [](https://pypi.org/project/docling/) [](https://pypi.org/project/docling/) [](https://github.com/astral-sh/uv) [](https://github.com/astral-sh/ruff) [](https://pydantic.dev) [](https://pypi.org/project/prek/) [](https://opensource.org/licenses/MIT) [](https://pepy.tech/projects/docling) [](https://apify.com/vancura/docling) [](https://app.dosu.dev/097760a8-135e-4789-8234-90c8837d7f1c/ask?utm_source=github) [](https://docling.ai/discord) [](https://www.bestpractices.dev/projects/10101) [](https://lfaidata.foundation/projects/) Docling simplifies document processing by parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the generative AI ecosystem. ## Getting started 🐣 Ready to kick off your Docling journey? Let's dive right into it! [**⬇️ Installation**Quickly install Docling in your environment](../docling/getting_started/installation/) [**▶️ Quickstart**Get a jumpstart on basic Docling usage](../docling/getting_started/quickstart/) [**🧩 Concepts**Learn Docling fundamentals and get a glimpse under the hood](../docling/concepts/) [**🧑🏽‍🍳 Examples**Try out recipes for various use cases, including conversion, RAG, and more](../docling/examples/) [**🤖 Integrations**Check out integrations with popular AI tools and frameworks](../docling/integrations/) [**📖 Reference**See more API details](../docling/reference/document_converter/) ## Features - 🗂️ Parsing of [multiple document formats][supported_formats] including PDF, DOCX, PPTX, XLSX, HTML, EPUB, WAV, MP3, WebVTT, Box Notes, email formats (EML, MSG), images (PNG, TIFF, JPEG, ...), LaTeX, DocLang, plain text, and more - 📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more - 🧬 A unified, expressive [DoclingDocument][docling_document] representation format - ↪️ Various [export formats][supported_formats] and options, including Markdown, HTML, WebVTT, DocLang, [DocTags](https://arxiv.org/abs/2503.11576) and lossless JSON - 📜 Support for several application-specific XML schemas including [DocLang](https://doclang.ai), [USPTO](https://www.uspto.gov/patents) patents, [JATS](https://jats.nlm.nih.gov/) articles, and [XBRL](https://www.xbrl.org/) financial reports. - 🔒 Local execution capabilities for sensitive data and air-gapped environments - 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI - 🔍 Extensive [OCR support][ocr_engines] for scanned PDFs and images - 👓 Support for several Visual Language Models, such as ([GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M)) - 🎙️ Audio support with Automatic Speech Recognition (ASR) models - 🔌 Connect to any agent using the [MCP server](https://docling-project.github.io/docling/usage/mcp/) - 🌐 Run Docling as a service with the [API server](https://docling-project.github.io/docling/usage/api_server/) (docling-serve) - 💻 Simple and convenient CLI ### What's new - 🎬 Parsing of video files (MP4, AVI, MOV, MKV, and WebM) with an ASR transcript and representative keyframes - 📄 Parsing of ODF (OpenDocument Format) files for text documents (`.odt`), spreadsheets (`.ods`), and presentations (`.odp`) - 💼 Parsing of XBRL (eXtensible Business Reporting Language) documents for financial reports - 📧 Parsing of email files (`.eml`, `.msg`) - 📚 Parsing of EPUB (Electronic Publication) files for e-books - 📝 Parsing of plain-text files (`.txt`, `.text`) and Markdown supersets (`.qmd`, `.Rmd`) - 📊 Chart understanding (Barchart, Piechart, LinePlot): convert them into tables or code and add detailed descriptions ### Coming soon * 📝 Metadata extraction, including title, authors, references & language * 📝 Complex chemistry understanding (Molecular structures) ## What's next 🚀 The journey has just begun! Join us and become a part of the growing Docling community. - [:fontawesome-brands-github: GitHub](https://github.com/docling-project/docling) - [:fontawesome-brands-discord: Discord](https://docling.ai/discord) - [:fontawesome-brands-linkedin: LinkedIn](https://linkedin.com/company/docling/) ## Live assistant Do you want to leverage the power of AI and get live support on Docling? Try out the [Chat with Dosu](https://app.dosu.dev/097760a8-135e-4789-8234-90c8837d7f1c/ask?utm_source=github) functionalities provided by our friends at [Dosu](https://dosu.dev/). [](https://app.dosu.dev/097760a8-135e-4789-8234-90c8837d7f1c/ask?utm_source=github) ## LF AI & Data Docling is hosted as a project in the [LF AI & Data Foundation](https://lfaidata.foundation/projects/). ### IBM ❤️ Open Source AI The project was started by the AI for knowledge team at IBM Research Zurich. [supported_formats]: ./usage/supported_formats.md [docling_document]: ./concepts/docling_document.md [integrations]: ./integrations/index.md [ocr_engines]: ./concepts/OCR.md ## 2. Official Technical Reference & Guides (docling-project/website) # Docling Website This is the official website for [Docling](https://github.com/docling-project/docling). ## Getting Started Install the required dependencies: ```bash uv sync ``` ## Running Locally Start the development server on http://0.0.0.0:5001 ```bash uv run website/main.py ``` When you make changes to your project, the server will automatically reload. ## Building the Static Site The site is fully static — every page is pre-rendered to HTML — so it can be published on GitHub Pages (or any static host). Build it with: ```bash uv run website/build.py ``` This renders all pages and copies the assets into `dist/`. To serve that build locally: ```bash python3 -m http.server 8000 --directory dist # open http://localhost:8000 ``` Any static file server works. Clean URLs such as `/deployments/` resolve because each route is written as `/index.html`. Useful options: - `--out `: output directory (default `dist`). - `--base-path `: URL prefix for root-relative links, needed when the site is served from a sub-path. For the GitHub project page at `docling-project.github.io/website`, build with `--base-path /website` (the repository name). Leave empty for a root/custom-domain deploy. - `--cname `: write a `CNAME` file for a custom domain (e.g. `docling.ai`). To preview a sub-path build locally, build straight into a directory whose name matches the prefix — `--base-path` rewrites the links but does not nest the files: ```bash uv run website/build.py --out /tmp/site/website --base-path /website python3 -m http.server 5055 --directory /tmp/site # open http://localhost:5055/website/ ``` ### Asset URLs in CSS `--base-path` rewrites root-relative `href`/`src` attributes in HTML only, so a root-relative `url()` inside a stylesheet would 404 on a sub-path deploy. Write stylesheet asset URLs relative to the stylesheet instead: ```css src: url("../font/plex.woff2"); /* not url("/font/plex.woff2") */ ``` The build enforces this: it exits with an error naming the file and URL if a root-relative `url()` appears in any stylesheet. ## Site architecture Pages are composed from reusable components; content lives in plain Python data modules so copy can be edited without touching markup. ``` website/ pages/ one module per route — section composition only components/ reusable product components (hero, document demo, ...) data/ site content: navigation, samples, product copy, integrations highlight.py build-time Pygments highlighting (no client-side highlighter) seo.py sitemap.xml and robots.txt, generated from one route list public/ css/ cascade layers: tokens, reset, base, layout, components, pages js/ ES modules, one per concern, loaded via js/main.js font/ self-hosted IBM Plex Sans (variable) and Plex Mono ``` **CSS** uses cascade layers, declared once at the top of `css/tokens.css`: ```css @layer reset, tokens, base, layout, components, pages, utilities; ``` Because the order is declared there, the `` tags can be reordered without changing which rules win. Colour, spacing, typography and motion are all tokens in `tokens.css`; the theme is dark by default with a full light variant under `prefers-color-scheme: light`. **Adding a route** means adding it in three places: a page module under `website/pages/`, a handler in `website/main.py`, and a `_write_page` call in `website/build.py`. Add it to `STATIC_ROUTES` in `website/seo.py` so it reaches the sitemap. **Sample output** shown on the site carries provenance metadata in `website/data/samples.py`, including whether it has been regenerated against a pinned Docling release. Anything not yet reproduced is labelled as such on the page rather than presented as a verified result. ## Deployment Pushes to `main` are built and deployed to GitHub Pages automatically by [`.github/workflows/deploy.yml`](.github/workflows/deploy.yml) and served at [docling.ai](https://docling.ai). The workflow builds at the root (`BASE_PATH=/`) and writes a `CNAME` for the custom domain. Requires, once: **Settings → Pages → Build and deployment → Source: GitHub Actions**, and the custom domain configured under **Settings → Pages → Custom domain**. ### Serving from the GitHub project sub-path instead To serve from `docling-project.github.io/website` rather than the custom domain, override the defaults via repository variables under **Settings → Secrets and variables → Actions → Variables**: - `BASE_PATH` = `/website` - `CNAME` = *(empty)* ## Contributing This website is part of the [Docling project](https://github.com/docling-project/docling). Your feedback and contributions are welcome! **Writing a Blog Post** ### Blog Post Structure Blog posts follow a structured format with timestamped folders and organized assets: ``` blog/ └── YYYYMMDD_HH_post-title/ ├── post.md └── images/ ├── thumbnail.jpg └── other-images.jpg ``` ### Creating a New Blog Post 1. **Create the folder** using the naming convention `YYYYMMDD_HH_`: ```bash mkdir -p blog/20260306_14_my-awesome-post/images ``` 2. **Create `post.md`** with metadata and content: ```markdown --- title: My Awesome Post date: 06-03-2026 summary: A brief description that appears in the blog listing thumbnail: images/thumbnail.jpg --- Your blog content starts here... ## Section Heading You can use all standard Markdown features, code blocks, images, etc. ``` 3. **Add images** to the `images/` folder: - Thumbnail: `images/thumbnail.jpg` (recommended size: 1200x630px) - Other images: Reference them in your post as `images/your-image.jpg` 4. **Restart the server** to see your changes (due to caching): ```bash uv run website/main.py ``` ### Metadata Fields - `title`: The post title (displayed as H1) - `date`: Publication date in `DD-MM-YYYY` format - `summary`: Brief description shown in blog listing - `thumbnail`: Path to thumbnail image (optional, relative to post folder) - `category`: Post category for filtering (default: `technical`) - `technical` - Technical guides, tutorials, and deep dives - `event` - Announcements about events, conferences, or community gatherings - `new-feature-alert` - Announcements of new features or releases ### Markdown Support The blog supports extended Markdown features including: - Code syntax highlighting - Tables - Footnotes - Emoji - Admonitions/callouts - And more (see `blog/template/post.md` for examples) ### Tips - Use the template at `blog/template/post.md` as a reference - Posts are sorted by date (newest first) - The folder name's timestamp helps with organization but doesn't affect display - Images are served from `/blog//images/` ## License This project is part of the Docling ecosystem. See the main [Docling repository](https://github.com/docling-project/docling) for license information.