Docling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem.
Go to file
Christoph Auer a00c937e19
Ensure all models work only on valid pages (#158)
Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
2024-10-18 08:54:06 +02:00
.github docs: add use docling (#150) 2024-10-17 18:14:48 +02:00
docling Ensure all models work only on valid pages (#158) 2024-10-18 08:54:06 +02:00
docs Ensure all models work only on valid pages (#158) 2024-10-18 08:54:06 +02:00
tests feat!: Docling v2 (#117) 2024-10-16 21:02:03 +02:00
.gitignore ci: Add Github Actions (#4) 2024-07-16 13:05:04 +02:00
.pre-commit-config.yaml feat!: Docling v2 (#117) 2024-10-16 21:02:03 +02:00
CHANGELOG.md chore: bump version to 2.0.0 [skip ci] 2024-10-16 19:48:06 +00:00
CODE_OF_CONDUCT.md Initial commit 2024-07-15 09:42:42 +02:00
CONTRIBUTING.md Initial commit 2024-07-15 09:42:42 +02:00
Dockerfile feat: Support tableformer model choice (#90) 2024-09-26 21:37:08 +02:00
LICENSE chore: fix placeholders in license (#63) 2024-09-06 17:10:07 +02:00
MAINTAINERS.md docs: Update MAINTAINERS.md (#59) 2024-09-02 12:34:38 +02:00
mkdocs.yml docs: add use docling (#150) 2024-10-17 18:14:48 +02:00
poetry.lock docs: add use docling (#150) 2024-10-17 18:14:48 +02:00
pyproject.toml docs: add use docling (#150) 2024-10-17 18:14:48 +02:00
README.md docs: add graphical band in readme (#154) 2024-10-17 18:15:40 +02:00

Docling

Docling

arXiv Docs PyPI version Python Poetry Code style: black Imports: isort Pydantic v2 pre-commit License MIT

Docling parses documents and exports them to the desired format with ease and speed.

Features

  • 🗂️ Multi-format support for input (PDF, DOCX etc.) & output (Markdown, JSON etc.)
  • 📑 Advanced PDF document understanding incl. page layout, reading order & table structures
  • 📝 Metadata extraction, including title, authors, references & language
  • 🤖 Seamless LlamaIndex 🦙 & LangChain 🦜🔗 integration for powerful RAG / QA applications
  • 🔍 OCR support for scanned PDFs
  • 💻 Simple and convenient CLI

Explore the documentation to discover plenty examples and unlock the full power of Docling!

Installation

To use Docling, simply install docling from your package manager, e.g. pip:

pip install docling

Works on macOS, Linux and Windows environments. Both x86_64 and arm64 architectures.

More detailed installation instructions are available in the docs.

Getting started

To convert invidual documents, use convert(), for example:

from docling.document_converter import DocumentConverter

source = "https://arxiv.org/pdf/2408.09869"  # PDF path or URL
converter = DocumentConverter()
result = converter.convert(source)
print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"

Check out Getting started. You will find lots of tuning options to leverage all the advanced capabilities.

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.

Contributing

Please read Contributing to Docling for details.

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}
}

License

The Docling codebase is under MIT license. For individual model usage, please refer to the model licenses found in the original packages.