docling 1.20.0__tar.gz → 2.0.0__tar.gz

docling-2.0.0/PKG-INFO

@@ -0,0 +1,149 @@
+Metadata-Version: 2.1
+Name: docling
+Version: 2.0.0
+Summary: Docling PDF conversion package
+Home-page: https://github.com/DS4SD/docling
+License: MIT
+Keywords: docling,convert,document,pdf,layout model,segmentation,table structure,table former
+Author: Christoph Auer
+Author-email: cau@zurich.ibm.com
+Requires-Python: >=3.10,<4.0
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Provides-Extra: tesserocr
+Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
+Requires-Dist: certifi (>=2024.7.4)
+Requires-Dist: deepsearch-glm (>=0.25.0,<0.26.0)
+Requires-Dist: docling-core (>=2.0.0,<3.0.0)
+Requires-Dist: docling-ibm-models (>=2.0.1,<3.0.0)
+Requires-Dist: docling-parse (>=1.6.0,<2.0.0)
+Requires-Dist: easyocr (>=1.7,<2.0)
+Requires-Dist: filetype (>=1.2.0,<2.0.0)
+Requires-Dist: huggingface_hub (>=0.23,<1)
+Requires-Dist: pandas (>=2.1.4,<3.0.0)
+Requires-Dist: pyarrow (>=16.1.0,<17.0.0)
+Requires-Dist: pydantic (>=2.0.0,<3.0.0)
+Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
+Requires-Dist: pypdfium2 (>=4.30.0,<5.0.0)
+Requires-Dist: python-docx (>=1.1.2,<2.0.0)
+Requires-Dist: python-pptx (>=1.0.2,<2.0.0)
+Requires-Dist: requests (>=2.32.3,<3.0.0)
+Requires-Dist: rtree (>=1.3.0,<2.0.0)
+Requires-Dist: scipy (>=1.14.1,<2.0.0)
+Requires-Dist: tesserocr (>=2.7.1,<3.0.0) ; extra == "tesserocr"
+Requires-Dist: torch (>=2.2.2,<2.3.0) ; sys_platform == "darwin" and platform_machine == "x86_64"
+Requires-Dist: torch (>=2.2.2,<3.0.0) ; sys_platform != "darwin" or platform_machine != "x86_64"
+Requires-Dist: torchvision (>=0,<1) ; sys_platform != "darwin" or platform_machine != "x86_64"
+Requires-Dist: torchvision (>=0.17.2,<0.18.0) ; sys_platform == "darwin" and platform_machine == "x86_64"
+Requires-Dist: typer (>=0.12.5,<0.13.0)
+Project-URL: Repository, https://github.com/DS4SD/docling
+Description-Content-Type: text/markdown
+
+<p align="center">
+  <a href="https://github.com/ds4sd/docling">
+    <img loading="lazy" alt="Docling" src="https://github.com/DS4SD/docling/raw/main/docs/assets/logo.png" width="150" />
+  </a>
+</p>
+
+# Docling
+
+[![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://ds4sd.github.io/docling/)
+[![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
+![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)
+[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![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/DS4SD/docling)](https://opensource.org/licenses/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](https://ds4sd.github.io/docling/) 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:
+```bash
+pip install docling
+```
+
+Works on macOS, Linux and Windows environments. Both x86_64 and arm64 architectures.
+
+More [detailed installation instructions](https://ds4sd.github.io/docling/installation/) are available in the docs.
+
+## Getting started
+
+To convert invidual documents, use `convert()`, for example:
+
+```python
+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[...]"
+print(result.document.export_to_document_tokens())  # output: "<document><title><page_1><loc_20>..."
+```
+
+
+Check out [Getting started](https://ds4sd.github.io/docling/).
+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](https://github.com/DS4SD/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/DS4SD/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.
+

docling-2.0.0/README.md

@@ -0,0 +1,98 @@
+<p align="center">
+  <a href="https://github.com/ds4sd/docling">
+    <img loading="lazy" alt="Docling" src="https://github.com/DS4SD/docling/raw/main/docs/assets/logo.png" width="150" />
+  </a>
+</p>
+
+# Docling
+
+[![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://ds4sd.github.io/docling/)
+[![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
+![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)
+[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
+[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
+[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![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/DS4SD/docling)](https://opensource.org/licenses/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](https://ds4sd.github.io/docling/) 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:
+```bash
+pip install docling
+```
+
+Works on macOS, Linux and Windows environments. Both x86_64 and arm64 architectures.
+
+More [detailed installation instructions](https://ds4sd.github.io/docling/installation/) are available in the docs.
+
+## Getting started
+
+To convert invidual documents, use `convert()`, for example:
+
+```python
+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[...]"
+print(result.document.export_to_document_tokens())  # output: "<document><title><page_1><loc_20>..."
+```
+
+
+Check out [Getting started](https://ds4sd.github.io/docling/).
+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](https://github.com/DS4SD/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/DS4SD/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.

docling-2.0.0/docling/backend/abstract_backend.py

@@ -0,0 +1,63 @@
+from abc import ABC, abstractmethod
+from io import BytesIO
+from pathlib import Path
+from typing import TYPE_CHECKING, Set, Union
+
+from docling_core.types.doc import DoclingDocument
+
+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]):
+        self.path_or_stream = path_or_stream
+        self.document_hash = in_doc.document_hash
+        self.input_format = in_doc.format
+
+    @abstractmethod
+    def is_valid(self) -> bool:
+        pass
+
+    @classmethod
+    @abstractmethod
+    def supports_pagination(cls) -> bool:
+        pass
+
+    @abstractmethod
+    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 convert(self) -> DoclingDocument:
+        pass

{docling-1.20.0 → docling-2.0.0}/docling/backend/docling_parse_backend.py

@@ -5,12 +5,14 @@ from pathlib import Path
 from typing import Iterable, List, Optional, Union
 
 import pypdfium2 as pdfium
+from docling_core.types.doc import BoundingBox, CoordOrigin, Size
 from docling_parse.docling_parse import pdf_parser
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage
 
-from docling.backend.abstract_backend import PdfDocumentBackend, PdfPageBackend
-from docling.datamodel.base_models import BoundingBox, Cell, CoordOrigin, PageSize
+from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
+from docling.datamodel.base_models import Cell
+from docling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 
@@ -177,8 +179,8 @@ class DoclingParsePageBackend(PdfPageBackend):
 
         return image
 
-    def get_size(self) -> PageSize:
-        return PageSize(width=self._ppage.get_width(), height=self._ppage.get_height())
+    def get_size(self) -> Size:
+        return Size(width=self._ppage.get_width(), height=self._ppage.get_height())
 
     def unload(self):
         self._ppage = None
@@ -186,23 +188,25 @@ class DoclingParsePageBackend(PdfPageBackend):
 
 
 class DoclingParseDocumentBackend(PdfDocumentBackend):
-    def __init__(self, path_or_stream: Union[BytesIO, Path], document_hash: str):
-        super().__init__(path_or_stream, document_hash)
+    def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
+        super().__init__(in_doc, path_or_stream)
 
-        self._pdoc = pdfium.PdfDocument(path_or_stream)
+        self._pdoc = pdfium.PdfDocument(self.path_or_stream)
         self.parser = pdf_parser()
 
         success = False
-        if isinstance(path_or_stream, BytesIO):
+        if isinstance(self.path_or_stream, BytesIO):
             success = self.parser.load_document_from_bytesio(
-                document_hash, path_or_stream
+                self.document_hash, self.path_or_stream
+            )
+        elif isinstance(self.path_or_stream, Path):
+            success = self.parser.load_document(
+                self.document_hash, str(self.path_or_stream)
             )
-        elif isinstance(path_or_stream, Path):
-            success = self.parser.load_document(document_hash, str(path_or_stream))
 
         if not success:
             raise RuntimeError(
-                f"docling-parse could not load document {document_hash}."
+                f"docling-parse could not load document with hash {self.document_hash}."
             )
 
     def page_count(self) -> int:

{docling-1.20.0 → docling-2.0.0}/docling/backend/docling_parse_v2_backend.py

@@ -2,15 +2,19 @@ import logging
 import random
 from io import BytesIO
 from pathlib import Path
-from typing import Iterable, List, Optional, Union
+from typing import TYPE_CHECKING, Iterable, List, Optional, Union
 
 import pypdfium2 as pdfium
+from docling_core.types.doc import BoundingBox, CoordOrigin
 from docling_parse.docling_parse import pdf_parser_v2
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage
 
-from docling.backend.abstract_backend import PdfDocumentBackend, PdfPageBackend
-from docling.datamodel.base_models import BoundingBox, Cell, CoordOrigin, PageSize
+from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
+from docling.datamodel.base_models import Cell, Size
+
+if TYPE_CHECKING:
+    from docling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
 
@@ -190,8 +194,8 @@ class DoclingParseV2PageBackend(PdfPageBackend):
 
         return image
 
-    def get_size(self) -> PageSize:
-        return PageSize(width=self._ppage.get_width(), height=self._ppage.get_height())
+    def get_size(self) -> Size:
+        return Size(width=self._ppage.get_width(), height=self._ppage.get_height())
 
     def unload(self):
         self._ppage = None
@@ -199,23 +203,23 @@ class DoclingParseV2PageBackend(PdfPageBackend):
 
 
 class DoclingParseV2DocumentBackend(PdfDocumentBackend):
-    def __init__(self, path_or_stream: Union[BytesIO, Path], document_hash: str):
-        super().__init__(path_or_stream, document_hash)
+    def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
+        super().__init__(in_doc, path_or_stream)
 
-        self._pdoc = pdfium.PdfDocument(path_or_stream)
+        self._pdoc = pdfium.PdfDocument(self.path_or_stream)
         self.parser = pdf_parser_v2("fatal")
 
         success = False
         if isinstance(path_or_stream, BytesIO):
             success = self.parser.load_document_from_bytesio(
-                document_hash, path_or_stream
+                self.document_hash, path_or_stream
             )
         elif isinstance(path_or_stream, Path):
-            success = self.parser.load_document(document_hash, str(path_or_stream))
+            success = self.parser.load_document(self.document_hash, str(path_or_stream))
 
         if not success:
             raise RuntimeError(
-                f"docling-parse could not load document {document_hash}."
+                f"docling-parse v2 could not load document {self.document_hash}."
             )
 
     def page_count(self) -> int: