{"id":26275205,"url":"https://github.com/docling-project/docling","last_synced_at":"2026-04-13T16:01:06.569Z","repository":{"id":248472621,"uuid":"826168160","full_name":"docling-project/docling","owner":"docling-project","description":"Get your documents ready for gen AI","archived":false,"fork":false,"pushed_at":"2026-04-12T07:07:43.000Z","size":271603,"stargazers_count":57622,"open_issues_count":877,"forks_count":3931,"subscribers_count":208,"default_branch":"main","last_synced_at":"2026-04-12T07:18:05.270Z","etag":null,"topics":["ai","convert","document-parser","document-parsing","documents","docx","html","markdown","pdf","pdf-converter","pdf-to-json","pdf-to-text","pptx","tables","xlsx"],"latest_commit_sha":null,"homepage":"https://docling-project.github.io/docling","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/docling-project.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":"CITATION.cff","codeowners":null,"security":".github/SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":"MAINTAINERS.md","copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2024-07-09T07:50:26.000Z","updated_at":"2026-04-12T07:14:18.000Z","dependencies_parsed_at":"2024-08-20T10:50:17.283Z","dependency_job_id":"6098385f-cb78-423d-8fc9-0acabeb7b012","html_url":"https://github.com/docling-project/docling","commit_stats":{"total_commits":251,"total_committers":26,"mean_commits":9.653846153846153,"dds":0.7171314741035857,"last_synced_commit":"eb7ffcdd1cda1caa8ec8ba2fc313ff1e7d9acd4f"},"previous_names":["ds4sd/docling","docling-project/docling"],"tags_count":165,"template":false,"template_full_name":null,"purl":"pkg:github/docling-project/docling","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/docling-project%2Fdocling","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/docling-project%2Fdocling/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/docling-project%2Fdocling/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/docling-project%2Fdocling/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/docling-project","download_url":"https://codeload.github.com/docling-project/docling/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/docling-project%2Fdocling/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31750574,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-13T09:16:15.125Z","status":"ssl_error","status_checked_at":"2026-04-13T09:16:05.023Z","response_time":93,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","convert","document-parser","document-parsing","documents","docx","html","markdown","pdf","pdf-converter","pdf-to-json","pdf-to-text","pptx","tables","xlsx"],"created_at":"2025-03-14T10:01:46.626Z","updated_at":"2026-04-13T16:01:06.563Z","avatar_url":"https://github.com/docling-project.png","language":"Python","funding_links":[],"categories":["Table of Contents","🤖 AI-Powered Scraping","Python","Retrieval-Augmented Generation","\u003cimg src=\"./assets/satellite.svg\" width=\"16\" height=\"16\" style=\"vertical-align: middle;\"\u003e Satellites","Recently Updated","HarmonyOS","RAG (Retrieval Augmented Generation）","Everything to Markdown to LLMs","开源工具","Document Processing and OCR","🛠 Build","5. Retrieval-Augmented Generation (RAG) \u0026 Knowledge","Librerías para usar NLP en español","Data Analysis","\u003ca name=\"Python\"\u003e\u003c/a\u003ePython","SDKs \u0026 CLI Tools","📊 Structured Output \u0026 Data Extraction","🤖 AI \u0026 Machine Learning","Data Ingestion \u0026 Parsing"],"sub_categories":["Information Processing","[Mar 14, 2025](/content/2025/03/14/README.md)","Windows Manager","Document Parser","Contribute to our Repository","预处理","Economic Data Sources","Frameworks","Preprocesamiento (de pdf u otro a markdown/json)"],"readme":"\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/docling-project/docling\"\u003e\n    \u003cimg loading=\"lazy\" alt=\"Docling\" src=\"https://github.com/docling-project/docling/raw/main/docs/assets/docling_processing.png\" width=\"100%\"/\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n# Docling\n\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://trendshift.io/repositories/12132\" target=\"_blank\"\u003e\u003cimg src=\"https://trendshift.io/api/badge/repositories/12132\" alt=\"DS4SD%2Fdocling | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n[![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)\n[![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://docling-project.github.io/docling/)\n[![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)\n[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)\n[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)\n[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)\n[![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)\n[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit\u0026logoColor=white)](https://github.com/pre-commit/pre-commit)\n[![License MIT](https://img.shields.io/github/license/docling-project/docling)](https://opensource.org/licenses/MIT)\n[![PyPI Downloads](https://static.pepy.tech/badge/docling/month)](https://pepy.tech/projects/docling)\n[![Docling Actor](https://apify.com/actor-badge?actor=vancura/docling?fpr=docling)](https://apify.com/vancura/docling)\n[![Chat with Dosu](https://dosu.dev/dosu-chat-badge.svg)](https://app.dosu.dev/097760a8-135e-4789-8234-90c8837d7f1c/ask?utm_source=github)\n[![Discord](https://img.shields.io/discord/1399788921306746971?color=6A7EC2\u0026logo=discord\u0026logoColor=ffffff)](https://docling.ai/discord)\n[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/10101/badge)](https://www.bestpractices.dev/projects/10101)\n[![LF AI \u0026 Data](https://img.shields.io/badge/LF%20AI%20%26%20Data-003778?logo=linuxfoundation\u0026logoColor=fff\u0026color=0094ff\u0026labelColor=003778)](https://lfaidata.foundation/projects/)\n\nDocling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem.\n\n## Features\n\n* 🗂️ Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, WebVTT, images (PNG, TIFF, JPEG, ...), LaTeX, plain text, and more\n* 📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more\n* 🧬 Unified, expressive [DoclingDocument][docling_document] representation format\n* ↪️ Various [export formats][supported_formats] and options, including Markdown, HTML, WebVTT, [DocTags](https://arxiv.org/abs/2503.11576) and lossless JSON\n* 📜 Support of several application-specifc XML schemas incl. [USPTO](https://www.uspto.gov/patents) patents, [JATS](https://jats.nlm.nih.gov/) articles, and [XBRL](https://www.xbrl.org/) financial reports.\n* 🔒 Local execution capabilities for sensitive data and air-gapped environments\n* 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI \u0026 Haystack for agentic AI\n* 🔍 Extensive OCR support for scanned PDFs and images\n* 👓 Support of several Visual Language Models ([GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M))\n* 🎙️ Audio support with Automatic Speech Recognition (ASR) models\n* 🔌 Connect to any agent using the [MCP server](https://docling-project.github.io/docling/usage/mcp/)\n* 💻 Simple and convenient CLI\n\n### What's new\n* 📤 Structured [information extraction][extraction] \\[🧪 beta\\]\n* 📑 New layout model (**Heron**) by default, for faster PDF parsing\n* 🔌 [MCP server](https://docling-project.github.io/docling/usage/mcp/) for agentic applications\n* 💼 Parsing of XBRL (eXtensible Business Reporting Language) documents for financial reports\n* 💬 Parsing of WebVTT (Web Video Text Tracks) files and export to WebVTT format\n* 💬 Parsing of LaTeX files\n* 📝 Parsing of plain-text files (`.txt`, `.text`) and Markdown supersets (`.qmd`, `.Rmd`)\n\n### Coming soon\n\n* 📝 Metadata extraction, including title, authors, references \u0026 language\n* 📝 Chart understanding (Barchart, Piechart, LinePlot, etc)\n* 📝 Complex chemistry understanding (Molecular structures)\n\n## Installation\n\nTo use Docling, simply install `docling` from your package manager, e.g. pip:\n```bash\npip install docling\n```\n\n\u003e **Note:** Python 3.9 support was dropped in docling version 2.70.0. Please use Python 3.10 or higher.\n\nWorks on macOS, Linux and Windows environments. Both x86_64 and arm64 architectures.\n\nMore [detailed installation instructions](https://docling-project.github.io/docling/installation/) are available in the docs.\n\n## Getting started\n\nTo convert individual documents with python, use `convert()`, for example:\n\n```python\nfrom docling.document_converter import DocumentConverter\n\nsource = \"https://arxiv.org/pdf/2408.09869\"  # document per local path or URL\nconverter = DocumentConverter()\nresult = converter.convert(source)\nprint(result.document.export_to_markdown())  # output: \"## Docling Technical Report[...]\"\n```\n\nMore [advanced usage options](https://docling-project.github.io/docling/usage/advanced_options/) are available in\nthe docs.\n\n## CLI\n\nDocling has a built-in CLI to run conversions.\n\n```bash\ndocling https://arxiv.org/pdf/2206.01062\n```\n\nYou can also use 🥚[GraniteDocling](https://huggingface.co/ibm-granite/granite-docling-258M) and other VLMs via Docling CLI:\n```bash\ndocling --pipeline vlm --vlm-model granite_docling https://arxiv.org/pdf/2206.01062\n```\nThis will use MLX acceleration on supported Apple Silicon hardware.\n\nRead more [here](https://docling-project.github.io/docling/usage/)\n\n## Documentation\n\nCheck out Docling's [documentation](https://docling-project.github.io/docling/), for details on\ninstallation, usage, concepts, recipes, extensions, and more.\n\n## Examples\n\nGo hands-on with our [examples](https://docling-project.github.io/docling/examples/),\ndemonstrating how to address different application use cases with Docling.\n\n## Integrations\n\nTo further accelerate your AI application development, check out Docling's native\n[integrations](https://docling-project.github.io/docling/integrations/) with popular frameworks\nand tools.\n\n## Get help and support\n\nPlease feel free to connect with us using the [discussion section](https://github.com/docling-project/docling/discussions).\n\n## Technical report\n\nFor more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).\n\n## Contributing\n\nPlease read [Contributing to Docling](https://github.com/docling-project/docling/blob/main/CONTRIBUTING.md) for details.\n\n## References\n\nIf you use Docling in your projects, please consider citing the following:\n\n```bib\n@techreport{Docling,\n  author = {Deep Search Team},\n  month = {8},\n  title = {Docling Technical Report},\n  url = {https://arxiv.org/abs/2408.09869},\n  eprint = {2408.09869},\n  doi = {10.48550/arXiv.2408.09869},\n  version = {1.0.0},\n  year = {2024}\n}\n```\n\n## License\n\nThe Docling codebase is under MIT license.\nFor individual model usage, please refer to the model licenses found in the original packages.\n\n## LF AI \u0026 Data\n\nDocling is hosted as a project in the [LF AI \u0026 Data Foundation](https://lfaidata.foundation/projects/).\n\n### IBM ❤️ Open Source AI\n\nThe project was started by the AI for knowledge team at IBM Research Zurich.\n\n[supported_formats]: https://docling-project.github.io/docling/usage/supported_formats/\n[docling_document]: https://docling-project.github.io/docling/concepts/docling_document/\n[integrations]: https://docling-project.github.io/docling/integrations/\n[extraction]: https://docling-project.github.io/docling/examples/extraction/\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdocling-project%2Fdocling","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdocling-project%2Fdocling","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdocling-project%2Fdocling/lists"}