docling 2.26.0__tar.gz → 2.28.0__tar.gz

{docling-2.26.0 → docling-2.28.0}/PKG-INFO

@@ -1,8 +1,8 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.26.0
+Version: 2.28.0
 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.
-Home-page: https://github.com/DS4SD/docling
+Home-page: https://github.com/docling-project/docling
 License: MIT
 Keywords: docling,convert,document,pdf,docx,html,markdown,layout model,segmentation,table structure,table former
 Author: Christoph Auer
@@ -28,9 +28,9 @@ Provides-Extra: vlm
 Requires-Dist: accelerate (>=1.2.1,<2.0.0) ; (sys_platform != "darwin" or platform_machine != "x86_64") and (extra == "vlm")
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
-Requires-Dist: docling-core[chunking] (>=2.19.0,<3.0.0)
+Requires-Dist: docling-core[chunking] (>=2.23.1,<3.0.0)
 Requires-Dist: docling-ibm-models (>=3.4.0,<4.0.0)
-Requires-Dist: docling-parse (>=3.3.0,<4.0.0)
+Requires-Dist: docling-parse (>=4.0.0,<5.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -42,8 +42,10 @@ Requires-Dist: onnxruntime (>=1.7.0,<2.0.0) ; (python_version >= "3.10") and (ex
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: pandas (>=2.1.4,<3.0.0)
 Requires-Dist: pillow (>=10.0.0,<12.0.0)
+Requires-Dist: pluggy (>=1.0.0,<2.0.0)
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
 Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
+Requires-Dist: pylatexenc (>=2.10,<3.0)
 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)
@@ -57,12 +59,12 @@ Requires-Dist: tqdm (>=4.65.0,<5.0.0)
 Requires-Dist: transformers (>=4.42.0,<4.43.0) ; (sys_platform == "darwin" and platform_machine == "x86_64") and (extra == "vlm")
 Requires-Dist: transformers (>=4.46.0,<5.0.0) ; (sys_platform != "darwin" or platform_machine != "x86_64") and (extra == "vlm")
 Requires-Dist: typer (>=0.12.5,<0.13.0)
-Project-URL: Repository, https://github.com/DS4SD/docling
+Project-URL: Repository, https://github.com/docling-project/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/docling_processing.png" width="100%"/>
+  <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>
 
@@ -73,7 +75,7 @@ Description-Content-Type: text/markdown
 </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://ds4sd.github.io/docling/)
+[![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/)
 [![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
@@ -81,8 +83,10 @@ Description-Content-Type: text/markdown
 [![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)
+[![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)
+[![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.
 
@@ -95,12 +99,12 @@ Docling simplifies document processing, parsing diverse formats — including ad
 * 🔒 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 Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview)) 🆕
 * 💻 Simple and convenient CLI
 
 ### Coming soon
 
 * 📝 Metadata extraction, including title, authors, references & language
-* 📝 Inclusion of Visual Language Models ([SmolDocling](https://huggingface.co/blog/smolervlm#smoldocling))
 * 📝 Chart understanding (Barchart, Piechart, LinePlot, etc)
 * 📝 Complex chemistry understanding (Molecular structures)
 
@@ -113,11 +117,11 @@ 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.
+More [detailed installation instructions](https://docling-project.github.io/docling/installation/) are available in the docs.
 
 ## Getting started
 
-To convert individual documents, use `convert()`, for example:
+To convert individual documents with python, use `convert()`, for example:
 
 ```python
 from docling.document_converter import DocumentConverter
@@ -128,28 +132,44 @@ result = converter.convert(source)
 print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"
 ```
 
-More [advanced usage options](https://ds4sd.github.io/docling/usage/) are available in
+More [advanced usage options](https://docling-project.github.io/docling/usage/) 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 🥚[SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview) and other VLMs via Docling CLI:
+```bash
+docling --pipeline vlm --vlm-model smoldocling 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://ds4sd.github.io/docling/), for details on
+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://ds4sd.github.io/docling/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://ds4sd.github.io/docling/integrations/) with popular frameworks
+[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/DS4SD/docling/discussions).
+Please feel free to connect with us using the [discussion section](https://github.com/docling-project/docling/discussions).
 
 ## Technical report
 
@@ -157,7 +177,7 @@ For more details on Docling's inner workings, check out the [Docling Technical R
 
 ## Contributing
 
-Please read [Contributing to Docling](https://github.com/DS4SD/docling/blob/main/CONTRIBUTING.md) for details.
+Please read [Contributing to Docling](https://github.com/docling-project/docling/blob/main/CONTRIBUTING.md) for details.
 
 ## References
 
@@ -181,11 +201,15 @@ If you use Docling in your projects, please consider citing the following:
 The Docling codebase is under MIT license.
 For individual model usage, please refer to the model licenses found in the original packages.
 
-## IBM ❤️ Open Source AI
+## LF AI & Data
+
+Docling is hosted as a project in the [LF AI & Data Foundation](https://lfaidata.foundation/projects/).
+
+### IBM ❤️ Open Source AI
 
-Docling has been brought to you by IBM.
+The project was started by the AI for knowledge team at IBM Research Zurich.
 
-[supported_formats]: https://ds4sd.github.io/docling/usage/supported_formats/
-[docling_document]: https://ds4sd.github.io/docling/concepts/docling_document/
-[integrations]: https://ds4sd.github.io/docling/integrations/
+[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/
 

{docling-2.26.0 → docling-2.28.0}/README.md

@@ -1,6 +1,6 @@
 <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/docling_processing.png" width="100%"/>
+  <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>
 
@@ -11,7 +11,7 @@
 </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://ds4sd.github.io/docling/)
+[![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/)
 [![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
@@ -19,8 +19,10 @@
 [![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)
+[![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)
+[![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.
 
@@ -33,12 +35,12 @@ Docling simplifies document processing, parsing diverse formats — including ad
 * 🔒 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 Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview)) 🆕
 * 💻 Simple and convenient CLI
 
 ### Coming soon
 
 * 📝 Metadata extraction, including title, authors, references & language
-* 📝 Inclusion of Visual Language Models ([SmolDocling](https://huggingface.co/blog/smolervlm#smoldocling))
 * 📝 Chart understanding (Barchart, Piechart, LinePlot, etc)
 * 📝 Complex chemistry understanding (Molecular structures)
 
@@ -51,11 +53,11 @@ 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.
+More [detailed installation instructions](https://docling-project.github.io/docling/installation/) are available in the docs.
 
 ## Getting started
 
-To convert individual documents, use `convert()`, for example:
+To convert individual documents with python, use `convert()`, for example:
 
 ```python
 from docling.document_converter import DocumentConverter
@@ -66,28 +68,44 @@ result = converter.convert(source)
 print(result.document.export_to_markdown())  # output: "## Docling Technical Report[...]"
 ```
 
-More [advanced usage options](https://ds4sd.github.io/docling/usage/) are available in
+More [advanced usage options](https://docling-project.github.io/docling/usage/) 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 🥚[SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview) and other VLMs via Docling CLI:
+```bash
+docling --pipeline vlm --vlm-model smoldocling 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://ds4sd.github.io/docling/), for details on
+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://ds4sd.github.io/docling/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://ds4sd.github.io/docling/integrations/) with popular frameworks
+[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/DS4SD/docling/discussions).
+Please feel free to connect with us using the [discussion section](https://github.com/docling-project/docling/discussions).
 
 ## Technical report
 
@@ -95,7 +113,7 @@ For more details on Docling's inner workings, check out the [Docling Technical R
 
 ## Contributing
 
-Please read [Contributing to Docling](https://github.com/DS4SD/docling/blob/main/CONTRIBUTING.md) for details.
+Please read [Contributing to Docling](https://github.com/docling-project/docling/blob/main/CONTRIBUTING.md) for details.
 
 ## References
 
@@ -119,10 +137,14 @@ If you use Docling in your projects, please consider citing the following:
 The Docling codebase is under MIT license.
 For individual model usage, please refer to the model licenses found in the original packages.
 
-## IBM ❤️ Open Source AI
+## LF AI & Data
+
+Docling is hosted as a project in the [LF AI & Data Foundation](https://lfaidata.foundation/projects/).
+
+### IBM ❤️ Open Source AI
 
-Docling has been brought to you by IBM.
+The project was started by the AI for knowledge team at IBM Research Zurich.
 
-[supported_formats]: https://ds4sd.github.io/docling/usage/supported_formats/
-[docling_document]: https://ds4sd.github.io/docling/concepts/docling_document/
-[integrations]: https://ds4sd.github.io/docling/integrations/
+[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/

{docling-2.26.0 → docling-2.28.0}/docling/backend/asciidoc_backend.py

@@ -380,7 +380,7 @@ class AsciiDocBackend(DeclarativeDocumentBackend):
                     end_row_offset_idx=row_idx + row_span,
                     start_col_offset_idx=col_idx,
                     end_col_offset_idx=col_idx + col_span,
-                    col_header=False,
+                    column_header=row_idx == 0,
                     row_header=False,
                 )
                 data.table_cells.append(cell)

{docling-2.26.0 → docling-2.28.0}/docling/backend/csv_backend.py

@@ -111,7 +111,7 @@ class CsvDocumentBackend(DeclarativeDocumentBackend):
                             end_row_offset_idx=row_idx + 1,
                             start_col_offset_idx=col_idx,
                             end_col_offset_idx=col_idx + 1,
-                            col_header=row_idx == 0,  # First row as header
+                            column_header=row_idx == 0,  # First row as header
                             row_header=False,
                         )
                         table_data.table_cells.append(cell)

{docling-2.26.0 → docling-2.28.0}/docling/backend/docling_parse_backend.py

@@ -6,12 +6,12 @@ from typing import Iterable, List, Optional, Union
 
 import pypdfium2 as pdfium
 from docling_core.types.doc import BoundingBox, CoordOrigin, Size
+from docling_core.types.doc.page import BoundingRectangle, SegmentedPdfPage, TextCell
 from docling_parse.pdf_parsers import pdf_parser_v1
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage
 
 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__)
@@ -68,8 +68,11 @@ class DoclingParsePageBackend(PdfPageBackend):
 
         return text_piece
 
-    def get_text_cells(self) -> Iterable[Cell]:
-        cells: List[Cell] = []
+    def get_segmented_page(self) -> Optional[SegmentedPdfPage]:
+        return None
+
+    def get_text_cells(self) -> Iterable[TextCell]:
+        cells: List[TextCell] = []
         cell_counter = 0
 
         if not self.valid:
@@ -91,19 +94,24 @@ class DoclingParsePageBackend(PdfPageBackend):
 
             text_piece = self._dpage["cells"][i]["content"]["rnormalized"]
             cells.append(
-                Cell(
-                    id=cell_counter,
+                TextCell(
+                    index=cell_counter,
                     text=text_piece,
-                    bbox=BoundingBox(
-                        # l=x0, b=y0, r=x1, t=y1,
-                        l=x0 * page_size.width / parser_width,
-                        b=y0 * page_size.height / parser_height,
-                        r=x1 * page_size.width / parser_width,
-                        t=y1 * page_size.height / parser_height,
-                        coord_origin=CoordOrigin.BOTTOMLEFT,
+                    orig=text_piece,
+                    from_ocr=False,
+                    rect=BoundingRectangle.from_bounding_box(
+                        BoundingBox(
+                            # l=x0, b=y0, r=x1, t=y1,
+                            l=x0 * page_size.width / parser_width,
+                            b=y0 * page_size.height / parser_height,
+                            r=x1 * page_size.width / parser_width,
+                            t=y1 * page_size.height / parser_height,
+                            coord_origin=CoordOrigin.BOTTOMLEFT,
+                        )
                     ).to_top_left_origin(page_size.height),
                 )
             )
+
             cell_counter += 1
 
         def draw_clusters_and_cells():
@@ -112,7 +120,7 @@ class DoclingParsePageBackend(PdfPageBackend):
             )  # make new image to avoid drawing on the saved ones
             draw = ImageDraw.Draw(image)
             for c in cells:
-                x0, y0, x1, y1 = c.bbox.as_tuple()
+                x0, y0, x1, y1 = c.rect.to_bounding_box().as_tuple()
                 cell_color = (
                     random.randint(30, 140),
                     random.randint(30, 140),

{docling-2.26.0 → docling-2.28.0}/docling/backend/docling_parse_v2_backend.py

@@ -6,12 +6,13 @@ from typing import TYPE_CHECKING, Iterable, List, Optional, Union
 
 import pypdfium2 as pdfium
 from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle, SegmentedPdfPage, TextCell
 from docling_parse.pdf_parsers import pdf_parser_v2
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage
 
 from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
-from docling.datamodel.base_models import Cell, Size
+from docling.datamodel.base_models import Size
 from docling.utils.locks import pypdfium2_lock
 
 if TYPE_CHECKING:
@@ -78,8 +79,11 @@ class DoclingParseV2PageBackend(PdfPageBackend):
 
         return text_piece
 
-    def get_text_cells(self) -> Iterable[Cell]:
-        cells: List[Cell] = []
+    def get_segmented_page(self) -> Optional[SegmentedPdfPage]:
+        return None
+
+    def get_text_cells(self) -> Iterable[TextCell]:
+        cells: List[TextCell] = []
         cell_counter = 0
 
         if not self.valid:
@@ -106,16 +110,20 @@ class DoclingParseV2PageBackend(PdfPageBackend):
 
             text_piece = cell_data[cells_header.index("text")]
             cells.append(
-                Cell(
-                    id=cell_counter,
+                TextCell(
+                    index=cell_counter,
                     text=text_piece,
-                    bbox=BoundingBox(
-                        # l=x0, b=y0, r=x1, t=y1,
-                        l=x0 * page_size.width / parser_width,
-                        b=y0 * page_size.height / parser_height,
-                        r=x1 * page_size.width / parser_width,
-                        t=y1 * page_size.height / parser_height,
-                        coord_origin=CoordOrigin.BOTTOMLEFT,
+                    orig=text_piece,
+                    from_ocr=False,
+                    rect=BoundingRectangle.from_bounding_box(
+                        BoundingBox(
+                            # l=x0, b=y0, r=x1, t=y1,
+                            l=x0 * page_size.width / parser_width,
+                            b=y0 * page_size.height / parser_height,
+                            r=x1 * page_size.width / parser_width,
+                            t=y1 * page_size.height / parser_height,
+                            coord_origin=CoordOrigin.BOTTOMLEFT,
+                        )
                     ).to_top_left_origin(page_size.height),
                 )
             )

docling-2.28.0/docling/backend/docling_parse_v4_backend.py

@@ -0,0 +1,192 @@
+import logging
+import random
+from io import BytesIO
+from pathlib import Path
+from typing import TYPE_CHECKING, Iterable, List, Optional, Union
+
+import pypdfium2 as pdfium
+from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import SegmentedPdfPage, TextCell
+from docling_parse.pdf_parser import DoclingPdfParser, PdfDocument
+from PIL import Image, ImageDraw
+from pypdfium2 import PdfPage
+
+from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
+from docling.datamodel.base_models import Size
+from docling.utils.locks import pypdfium2_lock
+
+if TYPE_CHECKING:
+    from docling.datamodel.document import InputDocument
+
+_log = logging.getLogger(__name__)
+
+
+class DoclingParseV4PageBackend(PdfPageBackend):
+    def __init__(self, parsed_page: SegmentedPdfPage, page_obj: PdfPage):
+        self._ppage = page_obj
+        self._dpage = parsed_page
+        self.valid = parsed_page is not None
+
+    def is_valid(self) -> bool:
+        return self.valid
+
+    def get_text_in_rect(self, bbox: BoundingBox) -> str:
+        # Find intersecting cells on the page
+        text_piece = ""
+        page_size = self.get_size()
+
+        scale = (
+            1  # FIX - Replace with param in get_text_in_rect across backends (optional)
+        )
+
+        for i, cell in enumerate(self._dpage.textline_cells):
+            cell_bbox = (
+                cell.rect.to_bounding_box()
+                .to_top_left_origin(page_height=page_size.height)
+                .scaled(scale)
+            )
+
+            overlap_frac = cell_bbox.intersection_area_with(bbox) / cell_bbox.area()
+
+            if overlap_frac > 0.5:
+                if len(text_piece) > 0:
+                    text_piece += " "
+                text_piece += cell.text
+
+        return text_piece
+
+    def get_segmented_page(self) -> Optional[SegmentedPdfPage]:
+        return self._dpage
+
+    def get_text_cells(self) -> Iterable[TextCell]:
+        page_size = self.get_size()
+
+        [tc.to_top_left_origin(page_size.height) for tc in self._dpage.textline_cells]
+
+        # for cell in self._dpage.textline_cells:
+        #     rect = cell.rect
+        #
+        #     assert (
+        #         rect.to_bounding_box().l <= rect.to_bounding_box().r
+        #     ), f"left is > right on bounding box {rect.to_bounding_box()} of rect {rect}"
+        #     assert (
+        #         rect.to_bounding_box().t <= rect.to_bounding_box().b
+        #     ), f"top is > bottom on bounding box {rect.to_bounding_box()} of rect {rect}"
+
+        return self._dpage.textline_cells
+
+    def get_bitmap_rects(self, scale: float = 1) -> Iterable[BoundingBox]:
+        AREA_THRESHOLD = 0  # 32 * 32
+
+        images = self._dpage.bitmap_resources
+
+        for img in images:
+            cropbox = img.rect.to_bounding_box().to_top_left_origin(
+                self.get_size().height
+            )
+
+            if cropbox.area() > AREA_THRESHOLD:
+                cropbox = cropbox.scaled(scale=scale)
+
+                yield cropbox
+
+    def get_page_image(
+        self, scale: float = 1, cropbox: Optional[BoundingBox] = None
+    ) -> Image.Image:
+
+        page_size = self.get_size()
+
+        if not cropbox:
+            cropbox = BoundingBox(
+                l=0,
+                r=page_size.width,
+                t=0,
+                b=page_size.height,
+                coord_origin=CoordOrigin.TOPLEFT,
+            )
+            padbox = BoundingBox(
+                l=0, r=0, t=0, b=0, coord_origin=CoordOrigin.BOTTOMLEFT
+            )
+        else:
+            padbox = cropbox.to_bottom_left_origin(page_size.height).model_copy()
+            padbox.r = page_size.width - padbox.r
+            padbox.t = page_size.height - padbox.t
+
+        with pypdfium2_lock:
+            image = (
+                self._ppage.render(
+                    scale=scale * 1.5,
+                    rotation=0,  # no additional rotation
+                    crop=padbox.as_tuple(),
+                )
+                .to_pil()
+                .resize(
+                    size=(round(cropbox.width * scale), round(cropbox.height * scale))
+                )
+            )  # We resize the image from 1.5x the given scale to make it sharper.
+
+        return image
+
+    def get_size(self) -> Size:
+        with pypdfium2_lock:
+            return Size(width=self._ppage.get_width(), height=self._ppage.get_height())
+
+        # TODO: Take width and height from docling-parse.
+        # return Size(
+        #    width=self._dpage.dimension.width,
+        #    height=self._dpage.dimension.height,
+        # )
+
+    def unload(self):
+        self._ppage = None
+        self._dpage = None
+
+
+class DoclingParseV4DocumentBackend(PdfDocumentBackend):
+    def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
+        super().__init__(in_doc, path_or_stream)
+
+        with pypdfium2_lock:
+            self._pdoc = pdfium.PdfDocument(self.path_or_stream)
+        self.parser = DoclingPdfParser(loglevel="fatal")
+        self.dp_doc: PdfDocument = self.parser.load(path_or_stream=self.path_or_stream)
+        success = self.dp_doc is not None
+
+        if not success:
+            raise RuntimeError(
+                f"docling-parse v4 could not load document {self.document_hash}."
+            )
+
+    def page_count(self) -> int:
+        # return len(self._pdoc)  # To be replaced with docling-parse API
+
+        len_1 = len(self._pdoc)
+        len_2 = self.dp_doc.number_of_pages()
+
+        if len_1 != len_2:
+            _log.error(f"Inconsistent number of pages: {len_1}!={len_2}")
+
+        return len_2
+
+    def load_page(
+        self, page_no: int, create_words: bool = True, create_textlines: bool = True
+    ) -> DoclingParseV4PageBackend:
+        with pypdfium2_lock:
+            return DoclingParseV4PageBackend(
+                self.dp_doc.get_page(
+                    page_no + 1,
+                    create_words=create_words,
+                    create_textlines=create_textlines,
+                ),
+                self._pdoc[page_no],
+            )
+
+    def is_valid(self) -> bool:
+        return self.page_count() > 0
+
+    def unload(self):
+        super().unload()
+        self.dp_doc.unload()
+        with pypdfium2_lock:
+            self._pdoc.close()
+        self._pdoc = None