docling 1.1.2__tar.gz → 2.64.1__tar.gz

{docling-1.1.2 → docling-2.64.1}/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) [year] [fullname]
+Copyright (c) 2024 International Business Machines
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

docling-2.64.1/PKG-INFO

@@ -0,0 +1,237 @@
+Metadata-Version: 2.4
+Name: docling
+Version: 2.64.1
+Summary: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
+Author-email: Christoph Auer <cau@zurich.ibm.com>, Michele Dolfi <dol@zurich.ibm.com>, Maxim Lysak <mly@zurich.ibm.com>, Nikos Livathinos <nli@zurich.ibm.com>, Ahmed Nassar <ahn@zurich.ibm.com>, Panos Vagenas <pva@zurich.ibm.com>, Peter Staar <taa@zurich.ibm.com>
+License-Expression: MIT
+Project-URL: homepage, https://github.com/docling-project/docling
+Project-URL: repository, https://github.com/docling-project/docling
+Project-URL: issues, https://github.com/docling-project/docling/issues
+Project-URL: changelog, https://github.com/docling-project/docling/blob/main/CHANGELOG.md
+Keywords: docling,convert,document,pdf,docx,html,markdown,layout model,segmentation,table structure,table former
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: Microsoft :: Windows
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: <4.0,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic<3.0.0,>=2.0.0
+Requires-Dist: docling-core[chunking]<3.0.0,>=2.50.1
+Requires-Dist: docling-parse<5.0.0,>=4.7.0
+Requires-Dist: docling-ibm-models<4,>=3.9.1
+Requires-Dist: filetype<2.0.0,>=1.2.0
+Requires-Dist: pypdfium2!=4.30.1,<5.0.0,>=4.30.0
+Requires-Dist: pydantic-settings<3.0.0,>=2.3.0
+Requires-Dist: huggingface_hub<1,>=0.23
+Requires-Dist: requests<3.0.0,>=2.32.2
+Requires-Dist: ocrmac<2.0.0,>=1.0.0; sys_platform == "darwin"
+Requires-Dist: rapidocr<4.0.0,>=3.3
+Requires-Dist: certifi>=2024.7.4
+Requires-Dist: rtree<2.0.0,>=1.3.0
+Requires-Dist: typer<0.20.0,>=0.12.5
+Requires-Dist: python-docx<2.0.0,>=1.1.2
+Requires-Dist: python-pptx<2.0.0,>=1.0.2
+Requires-Dist: beautifulsoup4<5.0.0,>=4.12.3
+Requires-Dist: pandas<3.0.0,>=2.1.4
+Requires-Dist: marko<3.0.0,>=2.1.2
+Requires-Dist: openpyxl<4.0.0,>=3.1.5
+Requires-Dist: lxml<7.0.0,>=4.0.0
+Requires-Dist: pillow<12.0.0,>=10.0.0
+Requires-Dist: tqdm<5.0.0,>=4.65.0
+Requires-Dist: pluggy<2.0.0,>=1.0.0
+Requires-Dist: pylatexenc<3.0,>=2.10
+Requires-Dist: scipy<2.0.0,>=1.6.0
+Requires-Dist: accelerate<2,>=1.0.0
+Requires-Dist: polyfactory>=2.22.2
+Provides-Extra: easyocr
+Requires-Dist: easyocr<2.0,>=1.7; extra == "easyocr"
+Provides-Extra: tesserocr
+Requires-Dist: tesserocr<3.0.0,>=2.7.1; extra == "tesserocr"
+Provides-Extra: ocrmac
+Requires-Dist: ocrmac<2.0.0,>=1.0.0; sys_platform == "darwin" and extra == "ocrmac"
+Provides-Extra: vlm
+Requires-Dist: transformers<5.0.0,>=4.46.0; extra == "vlm"
+Requires-Dist: accelerate<2.0.0,>=1.2.1; extra == "vlm"
+Requires-Dist: mlx-vlm<1.0.0,>=0.3.0; (python_version >= "3.10" and python_version < "3.14" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "vlm"
+Requires-Dist: vllm<1.0.0,>=0.10.0; (python_version >= "3.10" and python_version < "3.14" and sys_platform == "linux" and platform_machine == "x86_64") and extra == "vlm"
+Requires-Dist: qwen-vl-utils>=0.0.11; extra == "vlm"
+Provides-Extra: rapidocr
+Requires-Dist: rapidocr<4.0.0,>=3.3; extra == "rapidocr"
+Requires-Dist: onnxruntime<2.0.0,>=1.7.0; python_version < "3.14" and extra == "rapidocr"
+Provides-Extra: asr
+Requires-Dist: mlx-whisper>=0.4.3; (python_version >= "3.10" and python_version < "3.14" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "asr"
+Requires-Dist: openai-whisper>=20250625; python_version < "3.14" and extra == "asr"
+Dynamic: license-file
+
+<p align="center">
+  <a href="https://github.com/docling-project/docling">
+    <img loading="lazy" alt="Docling" src="https://github.com/docling-project/docling/raw/main/docs/assets/docling_processing.png" width="100%"/>
+  </a>
+</p>
+
+# Docling
+
+<p align="center">
+  <a href="https://trendshift.io/repositories/12132" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12132" alt="DS4SD%2Fdocling | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</p>
+
+[![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)
+[![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://docling-project.github.io/docling/)
+[![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)
+[![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)
+[![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)
+[![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
+[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
+[![License MIT](https://img.shields.io/github/license/docling-project/docling)](https://opensource.org/licenses/MIT)
+[![PyPI Downloads](https://static.pepy.tech/badge/docling/month)](https://pepy.tech/projects/docling)
+[![Docling Actor](https://apify.com/actor-badge?actor=vancura/docling?fpr=docling)](https://apify.com/vancura/docling)
+[![Chat with Dosu](https://dosu.dev/dosu-chat-badge.svg)](https://app.dosu.dev/097760a8-135e-4789-8234-90c8837d7f1c/ask?utm_source=github)
+[![Discord](https://img.shields.io/discord/1399788921306746971?color=6A7EC2&logo=discord&logoColor=ffffff)](https://docling.ai/discord)
+[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/10101/badge)](https://www.bestpractices.dev/projects/10101)
+[![LF AI & Data](https://img.shields.io/badge/LF%20AI%20%26%20Data-003778?logo=linuxfoundation&logoColor=fff&color=0094ff&labelColor=003778)](https://lfaidata.foundation/projects/)
+
+Docling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem.
+
+## Features
+
+* 🗂️ Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, VTT, images (PNG, TIFF, JPEG, ...), and more
+* 📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more
+* 🧬 Unified, expressive [DoclingDocument][docling_document] representation format
+* ↪️ Various [export formats][supported_formats] and options, including Markdown, HTML, [DocTags](https://arxiv.org/abs/2503.11576) and lossless JSON
+* 🔒 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 of several Visual Language Models ([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/)
+* 💻 Simple and convenient CLI
+
+### What's new
+* 📤 Structured [information extraction][extraction] \[🧪 beta\]
+* 📑 New layout model (**Heron**) by default, for faster PDF parsing
+* 🔌 [MCP server](https://docling-project.github.io/docling/usage/mcp/) for agentic applications
+* 💬 Parsing of Web Video Text Tracks (WebVTT) files
+
+### Coming soon
+
+* 📝 Metadata extraction, including title, authors, references & language
+* 📝 Chart understanding (Barchart, Piechart, LinePlot, etc)
+* 📝 Complex chemistry understanding (Molecular structures)
+
+## Installation
+
+To use Docling, simply install `docling` from your package manager, e.g. pip:
+```bash
+pip install docling
+```
+
+Works on macOS, Linux and Windows environments. Both x86_64 and arm64 architectures.
+
+More [detailed installation instructions](https://docling-project.github.io/docling/installation/) are available in the docs.
+
+## Getting started
+
+To convert individual documents with python, use `convert()`, for example:
+
+```python
+from docling.document_converter import DocumentConverter
+
+source = "https://arxiv.org/pdf/2408.09869"  # document per local path or URL
+converter = DocumentConverter()
+result = converter.convert(source)
+print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"
+```
+
+More [advanced usage options](https://docling-project.github.io/docling/usage/advanced_options/) are available in
+the docs.
+
+## CLI
+
+Docling has a built-in CLI to run conversions.
+
+```bash
+docling https://arxiv.org/pdf/2206.01062
+```
+
+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
+```
+This will use MLX acceleration on supported Apple Silicon hardware.
+
+Read more [here](https://docling-project.github.io/docling/usage/)
+
+## 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/examples/extraction/

docling-2.64.1/README.md

@@ -0,0 +1,161 @@
+<p align="center">
+  <a href="https://github.com/docling-project/docling">
+    <img loading="lazy" alt="Docling" src="https://github.com/docling-project/docling/raw/main/docs/assets/docling_processing.png" width="100%"/>
+  </a>
+</p>
+
+# Docling
+
+<p align="center">
+  <a href="https://trendshift.io/repositories/12132" target="_blank"><img src="https://trendshift.io/api/badge/repositories/12132" alt="DS4SD%2Fdocling | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
+</p>
+
+[![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)
+[![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://docling-project.github.io/docling/)
+[![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
+[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)
+[![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)
+[![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)
+[![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
+[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
+[![License MIT](https://img.shields.io/github/license/docling-project/docling)](https://opensource.org/licenses/MIT)
+[![PyPI Downloads](https://static.pepy.tech/badge/docling/month)](https://pepy.tech/projects/docling)
+[![Docling Actor](https://apify.com/actor-badge?actor=vancura/docling?fpr=docling)](https://apify.com/vancura/docling)
+[![Chat with Dosu](https://dosu.dev/dosu-chat-badge.svg)](https://app.dosu.dev/097760a8-135e-4789-8234-90c8837d7f1c/ask?utm_source=github)
+[![Discord](https://img.shields.io/discord/1399788921306746971?color=6A7EC2&logo=discord&logoColor=ffffff)](https://docling.ai/discord)
+[![OpenSSF Best Practices](https://www.bestpractices.dev/projects/10101/badge)](https://www.bestpractices.dev/projects/10101)
+[![LF AI & Data](https://img.shields.io/badge/LF%20AI%20%26%20Data-003778?logo=linuxfoundation&logoColor=fff&color=0094ff&labelColor=003778)](https://lfaidata.foundation/projects/)
+
+Docling simplifies document processing, parsing diverse formats — including advanced PDF understanding — and providing seamless integrations with the gen AI ecosystem.
+
+## Features
+
+* 🗂️ Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, VTT, images (PNG, TIFF, JPEG, ...), and more
+* 📑 Advanced PDF understanding incl. page layout, reading order, table structure, code, formulas, image classification, and more
+* 🧬 Unified, expressive [DoclingDocument][docling_document] representation format
+* ↪️ Various [export formats][supported_formats] and options, including Markdown, HTML, [DocTags](https://arxiv.org/abs/2503.11576) and lossless JSON
+* 🔒 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 of several Visual Language Models ([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/)
+* 💻 Simple and convenient CLI
+
+### What's new
+* 📤 Structured [information extraction][extraction] \[🧪 beta\]
+* 📑 New layout model (**Heron**) by default, for faster PDF parsing
+* 🔌 [MCP server](https://docling-project.github.io/docling/usage/mcp/) for agentic applications
+* 💬 Parsing of Web Video Text Tracks (WebVTT) files
+
+### Coming soon
+
+* 📝 Metadata extraction, including title, authors, references & language
+* 📝 Chart understanding (Barchart, Piechart, LinePlot, etc)
+* 📝 Complex chemistry understanding (Molecular structures)
+
+## Installation
+
+To use Docling, simply install `docling` from your package manager, e.g. pip:
+```bash
+pip install docling
+```
+
+Works on macOS, Linux and Windows environments. Both x86_64 and arm64 architectures.
+
+More [detailed installation instructions](https://docling-project.github.io/docling/installation/) are available in the docs.
+
+## Getting started
+
+To convert individual documents with python, use `convert()`, for example:
+
+```python
+from docling.document_converter import DocumentConverter
+
+source = "https://arxiv.org/pdf/2408.09869"  # document per local path or URL
+converter = DocumentConverter()
+result = converter.convert(source)
+print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"
+```
+
+More [advanced usage options](https://docling-project.github.io/docling/usage/advanced_options/) are available in
+the docs.
+
+## CLI
+
+Docling has a built-in CLI to run conversions.
+
+```bash
+docling https://arxiv.org/pdf/2206.01062
+```
+
+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
+```
+This will use MLX acceleration on supported Apple Silicon hardware.
+
+Read more [here](https://docling-project.github.io/docling/usage/)
+
+## 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/examples/extraction/

docling-2.64.1/docling/backend/abstract_backend.py

@@ -0,0 +1,84 @@
+from abc import ABC, abstractmethod
+from io import BytesIO
+from pathlib import Path
+from typing import TYPE_CHECKING, Union
+
+from docling_core.types.doc import DoclingDocument
+
+from docling.datamodel.backend_options import (
+    BackendOptions,
+    BaseBackendOptions,
+    DeclarativeBackendOptions,
+)
+
+if TYPE_CHECKING:
+    from docling.datamodel.base_models import InputFormat
+    from docling.datamodel.document import InputDocument
+
+
+class AbstractDocumentBackend(ABC):
+    @abstractmethod
+    def __init__(
+        self,
+        in_doc: "InputDocument",
+        path_or_stream: Union[BytesIO, Path],
+        options: BaseBackendOptions = BaseBackendOptions(),
+    ):
+        self.file = in_doc.file
+        self.path_or_stream = path_or_stream
+        self.document_hash = in_doc.document_hash
+        self.input_format = in_doc.format
+        self.options = options
+
+    @abstractmethod
+    def is_valid(self) -> bool:
+        pass
+
+    @classmethod
+    @abstractmethod
+    def supports_pagination(cls) -> bool:
+        pass
+
+    def unload(self):
+        if isinstance(self.path_or_stream, BytesIO):
+            self.path_or_stream.close()
+
+        self.path_or_stream = None
+
+    @classmethod
+    @abstractmethod
+    def supported_formats(cls) -> set["InputFormat"]:
+        pass
+
+
+class PaginatedDocumentBackend(AbstractDocumentBackend):
+    """DeclarativeDocumentBackend.
+
+    A declarative document backend is a backend that can transform to DoclingDocument
+    straight without a recognition pipeline.
+    """
+
+    @abstractmethod
+    def page_count(self) -> int:
+        pass
+
+
+class DeclarativeDocumentBackend(AbstractDocumentBackend):
+    """DeclarativeDocumentBackend.
+
+    A declarative document backend is a backend that can transform to DoclingDocument
+    straight without a recognition pipeline.
+    """
+
+    @abstractmethod
+    def __init__(
+        self,
+        in_doc: "InputDocument",
+        path_or_stream: Union[BytesIO, Path],
+        options: BackendOptions = DeclarativeBackendOptions(),
+    ) -> None:
+        super().__init__(in_doc, path_or_stream, options)
+
+    @abstractmethod
+    def convert(self) -> DoclingDocument:
+        pass