{"slug": "doclang-project-doclang", "title": "Doclang-Project/Doclang", "summary": "The DocLang Project has released DocLang, an AI-native markup format for unstructured content that maps to LLM tokens while preserving structure, semantics, layout, and geometry. The repository hosts the normative specification and reference validator, available via PyPI, with the project supported by the LF AI & Data Foundation under the Apache License 2.0. This standard aims to provide a single, unambiguous representation for documents and images used with large language models and vision-language models.", "body_md": "** DocLang is the AI-native markup format for unstructured content** — including documents, images, and more. It maps cleanly to LLM tokens while preserving structure, semantics, layout, and geometry in a single, unambiguous representation.\n\nThis repository is the home of the normative specification and the reference validator for DocLang. If you build with LLMs and VLMs on real-world content, this is where the standard lives.\n\nThe source of the specification is available in [spec.md](https://github.com/doclang-project/doclang/blob/main/spec.md)\nand exports to different formats can be found in the [exports/](https://github.com/doclang-project/doclang/tree/main/exports)\ndirectory.\n\nYou can install the validator from PyPI:\n\n```\npip install doclang\n```\n\nYou can then validate a DocLang document as follows:\n\n```\ndoclang validate -n my_document.dclg.xml\n```\n\nFor more details, see the [doclang/README.md](https://github.com/doclang-project/doclang/blob/main/doclang/README.md).\n\nIf you use DocLang in academic or technical work, please cite the specification:\n\n```\n@misc{doclang_2026,\n  title        = {DocLang: Universal AI Document Format},\n  author       = {{DocLang Project}},\n  year         = {2026},\n  version      = {main},\n  howpublished = {\\url{https://github.com/doclang-project/doclang}},\n}\n```\n\nTo work on this repository — setup, tests, reference generation, releases — see [CONTRIBUTING.md](https://github.com/doclang-project/doclang/blob/main/CONTRIBUTING.md).\n\nDocLang is developed in the open and supported by the [LF AI & Data Foundation](https://lfaidata.foundation/projects/). Learn more about the project at [doclang-project](https://github.com/doclang-project).\n\nDocLang is licensed under the Apache License 2.0. See [LICENSE](https://github.com/doclang-project/doclang/blob/main/LICENSE) for details.", "url": "https://wpnews.pro/news/doclang-project-doclang", "canonical_source": "https://github.com/doclang-project/doclang", "published_at": "2026-06-12 06:26:55+00:00", "updated_at": "2026-06-12 06:48:30.314237+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "ai-infrastructure", "artificial-intelligence", "generative-ai"], "entities": ["DocLang", "DocLang Project", "PyPI"], "alternates": {"html": "https://wpnews.pro/news/doclang-project-doclang", "markdown": "https://wpnews.pro/news/doclang-project-doclang.md", "text": "https://wpnews.pro/news/doclang-project-doclang.txt", "jsonld": "https://wpnews.pro/news/doclang-project-doclang.jsonld"}}