Docling
Converts PDFs, Office files and scans into one structured representation, without sending them anywhere
What is Docling?
The difference from a text extractor is that structure survives: page layout, reading order, table cells, code blocks and formulas come through as parts of a single document representation rather than as a flattened string, which is what decides whether a table in a report is still a table by the time an agent reads it. Everything can run locally, including in air-gapped environments. The cost of that fidelity is compute — machine-learning models run over each page, so this is a pipeline to budget for, not a fast converter to call inline.
What can you do with Docling?
- One representation for every input — Whatever went in, what comes out is a single document format, so downstream code does not branch on whether the source was a PDF, a spreadsheet or an email.
- Keep the structure a text dump destroys — Page layout, reading order, table structure, code blocks, formulas and image classification are all recovered, and charts are converted into tables or code with a description attached.
- Read the awkward formats too — Beyond PDF and Office there is HTML, EPUB, images, LaTeX, email, audio via speech recognition, and specialised schemas such as XBRL financial filings and USPTO patents.
- Handle scans without an external service — OCR for scanned PDFs and images is included, along with support for vision-language models, so pages that are pictures of text are not simply skipped.
- Hand the result straight to a RAG stack — Plug-in integrations exist for LangChain, LlamaIndex, CrewAI and Haystack, and an API server mode is available when conversion should be a service rather than a library call.
Before you choose Docling
- Machine-learning models for layout and table structure run over each page, so conversion throughput is a capacity question — this is a pipeline to schedule, not a fast extractor to call in a request path.
Star history
21 Aug to 28 Aug · +335
Frequently asked questions
Is Docling free for commercial use?
Docling is released under the MIT licence — OSI-approved open source, which permits commercial use.
How can Docling be deployed?
Docling is available as Runs locally / Self-hosted.
Documentation
Reproduced from the docling-project/docling README, published under MIT. Read the original ↗
Docling
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 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 representation format
- ↪️ Various export formats and options, including Markdown, HTML, WebVTT, DocLang, DocTags and lossless JSON
- 📜 Support for several application-specific XML schemas including DocLang, USPTO patents, JATS articles, and XBRL financial reports.
- 🔒 Local execution capabilities for sensitive data and air-gapped environments
- 🤖 Plug-and-play 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)
- 🎙️ Audio support with Automatic Speech Recognition (ASR) models
- 🔌 Connect to any agent using the MCP server
- 🌐 Run Docling as a service with the 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
pip install doclingNote: 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 are available in the docs.
2. Convert a document (CLI)
docling https://arxiv.org/pdf/2206.01062This generates a .md file in the current directory containing structured document content.
You can also use 🥚GraniteDocling and other VLMs via Docling CLI:
docling --pipeline vlm --vlm-model granite_docling https://arxiv.org/pdf/2206.010623. Python usage (recommended)
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 and configuration options.
Documentation
Check out Docling’s documentation for details on installation, usage, concepts, recipes, extensions, and more.
Examples
Go hands-on with our 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 with popular frameworks and tools.
Get help and support
Please feel free to connect with us using the discussion section.
Technical report
For more details on Docling’s inner workings, check out the Docling Technical Report.
References
If you use Docling in your projects, please consider citing the following:
@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}
}LF AI & Data
Docling is hosted as a project in the LF AI & Data Foundation.
IBM ❤️ Open Source AI
The project was started by the AI for knowledge team at IBM Research Zurich.
Other options in Data & Ingestion
FirecrawlDataRenders JavaScript, follows links and strips the navigation and boilerplate that otherwise poison a retrieval corpus. Solves the unglamorous half of RAG properly. AGPL-licensed, so check the terms if you plan to expose it as a service.
ragflowRAG & RetrievalRAGFlow is a server you run rather than a library you import: documents go into a dataset, it splits them into chunks, and you can read every chunk on screen and hand-correct the ones that came out wrong before any of it reaches a model, with chat answers citing the chunk they came from. Around that sit an agent canvas and an ingestion pipeline you can rebuild yourself, so retrieval, tools and MCP servers can be wired together without writing code. The optical character recognition, table-structure and layout models that make sense of scans run on PDFs and images only — Word, Excel and PowerPoint files are read structurally, and the docs tell you to convert a DOCX to PDF if you want the visual parser on it. The price of all this is weight: a Docker Compose stack with Elasticsearch, MySQL, MinIO and Redis behind it, 4 cores and 16 GB of RAM as the stated minimum, and parsing that the project's own FAQ concedes is slower than LangChain's. If your documents are already clean text and you want retrieval inside your own Python application, LlamaIndex or Haystack will fit better.
PaddleOCRDataRetrieval over your own documents usually fails long before the model does, at the point where a scanned table or a two-column PDF becomes an unreadable wall of text. PaddleOCR is the layer that stops that. It recognises text in more than a hundred languages, and its document pipeline preserves what the layout meant — headings stay headings, a table comes out as a table with its cell positions, formulas and seals are handled — emitting Markdown or JSON. The models are deliberately small enough to run on a CPU or at the edge, which is what makes processing a large archive affordable. The cost is the framework underneath: this is a PaddlePaddle project, and installing it means installing that.