docling 2.49.0__tar.gz → 2.51.0__tar.gz

{docling-2.49.0 → docling-2.51.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling
-Version: 2.49.0
+Version: 2.51.0
 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.
 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
@@ -27,8 +27,8 @@ 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,>=2.42.0
-Requires-Dist: docling-parse<5.0.0,>=4.2.2
-Requires-Dist: docling-ibm-models<4,>=3.9.0
+Requires-Dist: docling-parse<5.0.0,>=4.4.0
+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
@@ -101,17 +101,20 @@ Docling simplifies document processing, parsing diverse formats — including ad
 
 ## Features
 
-* 🗂️  Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, images (PNG, TIFF, JPEG, ...), and more
+* 🗂️ Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, 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
+* ↪️ 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 ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
-* 🎙️  Support for Audio with Automatic Speech Recognition (ASR) models
+* 🎙️ Audio support with Automatic Speech Recognition (ASR) models
 * 💻 Simple and convenient CLI
 
+### What's new
+* 📤 Structured [information extraction][extraction] \[🧪 beta\]
+
 ### Coming soon
 
 * 📝 Metadata extraction, including title, authors, references & language
@@ -222,3 +225,4 @@ 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-2.49.0 → docling-2.51.0}/README.md

@@ -29,17 +29,20 @@ Docling simplifies document processing, parsing diverse formats — including ad
 
 ## Features
 
-* 🗂️  Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, images (PNG, TIFF, JPEG, ...), and more
+* 🗂️ Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, 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
+* ↪️ 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 ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
-* 🎙️  Support for Audio with Automatic Speech Recognition (ASR) models
+* 🎙️ Audio support with Automatic Speech Recognition (ASR) models
 * 💻 Simple and convenient CLI
 
+### What's new
+* 📤 Structured [information extraction][extraction] \[🧪 beta\]
+
 ### Coming soon
 
 * 📝 Metadata extraction, including title, authors, references & language
@@ -150,3 +153,4 @@ 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-2.49.0 → docling-2.51.0}/docling/backend/docling_parse_v4_backend.py

@@ -30,13 +30,21 @@ class DoclingParseV4PageBackend(PdfPageBackend):
         page_no: int,
         create_words: bool = True,
         create_textlines: bool = True,
+        keep_chars: bool = False,
+        keep_lines: bool = False,
+        keep_images: bool = True,
     ):
         self._ppage = page_obj
         self._dp_doc = dp_doc
         self._page_no = page_no
+
         self._create_words = create_words
         self._create_textlines = create_textlines
 
+        self._keep_chars = keep_chars
+        self._keep_lines = keep_lines
+        self._keep_images = keep_images
+
         self._dpage: Optional[SegmentedPdfPage] = None
         self._unloaded = False
         self.valid = (self._ppage is not None) and (self._dp_doc is not None)
@@ -47,8 +55,12 @@ class DoclingParseV4PageBackend(PdfPageBackend):
 
         seg_page = self._dp_doc.get_page(
             self._page_no + 1,
+            keep_chars=self._keep_chars,
+            keep_lines=self._keep_lines,
+            keep_bitmaps=self._keep_images,
             create_words=self._create_words,
             create_textlines=self._create_textlines,
+            enforce_same_font=True,
         )
 
         # In Docling, all TextCell instances are expected with top-left origin.

{docling-2.49.0 → docling-2.51.0}/docling/backend/html_backend.py

@@ -467,13 +467,14 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
 
     @contextmanager
     def _use_hyperlink(self, tag: Tag):
+        old_hyperlink: Union[AnyUrl, Path, None] = None
+        new_hyperlink: Union[AnyUrl, Path, None] = None
         this_href = tag.get("href")
         if this_href is None:
             yield None
         else:
             if isinstance(this_href, str) and this_href:
-                old_hyperlink: Union[AnyUrl, Path, None] = self.hyperlink
-                new_hyperlink: Union[AnyUrl, Path, None] = None
+                old_hyperlink = self.hyperlink
                 if self.original_url is not None:
                     this_href = urljoin(str(self.original_url), str(this_href))
                 # ugly fix for relative links since pydantic does not support them.

{docling-2.49.0 → docling-2.51.0}/docling/datamodel/pipeline_options.py

@@ -237,7 +237,9 @@ class PdfBackend(str, Enum):
 
 
 # Define an enum for the ocr engines
-@deprecated("Use ocr_factory.registered_enum")
+@deprecated(
+    "Use get_ocr_factory().registered_kind to get a list of registered OCR engines."
+)
 class OcrEngine(str, Enum):
     """Enum of valid OCR engines."""
 
@@ -283,10 +285,10 @@ class LayoutOptions(BaseModel):
     keep_empty_clusters: bool = (
         False  # Whether to keep clusters that contain no text cells
     )
+    model_spec: LayoutModelConfig = DOCLING_LAYOUT_HERON
     skip_cell_assignment: bool = (
         False  # Skip cell-to-cluster assignment for VLM-only processing
     )
-    model_spec: LayoutModelConfig = DOCLING_LAYOUT_V2
 
 
 class AsrPipelineOptions(PipelineOptions):

{docling-2.49.0 → docling-2.51.0}/docling/models/layout_model.py

@@ -91,7 +91,7 @@ class LayoutModel(BasePageModel):
         local_dir: Optional[Path] = None,
         force: bool = False,
         progress: bool = False,
-        layout_model_config: LayoutModelConfig = DOCLING_LAYOUT_V2,
+        layout_model_config: LayoutModelConfig = LayoutOptions().model_spec,  # use default
     ) -> Path:
         return download_hf_model(
             repo_id=layout_model_config.repo_id,
@@ -122,8 +122,8 @@ class LayoutModel(BasePageModel):
         left_clusters = [c for c in clusters if c.label not in exclude_labels]
         right_clusters = [c for c in clusters if c.label in exclude_labels]
         # Create a deep copy of the original image for both sides
-        left_image = copy.deepcopy(page.image)
-        right_image = copy.deepcopy(page.image)
+        left_image = page.image.copy()
+        right_image = page.image.copy()
 
         # Draw clusters on both images
         draw_clusters(left_image, left_clusters, scale_x, scale_y)

{docling-2.49.0 → docling-2.51.0}/docling/models/page_preprocessing_model.py

@@ -90,7 +90,7 @@ class PagePreprocessingModel(BasePageModel):
 
         # DEBUG code:
         def draw_text_boxes(image, cells, show: bool = False):
-            draw = ImageDraw.Draw(image)
+            draw = ImageDraw.Draw(image.copy())
             for c in cells:
                 x0, y0, x1, y1 = (
                     c.to_bounding_box().l,

{docling-2.49.0 → docling-2.51.0}/docling/models/table_structure_model.py

@@ -94,7 +94,7 @@ class TableStructureModel(BasePageModel):
     ) -> Path:
         return download_hf_model(
             repo_id="ds4sd/docling-models",
-            revision="v2.2.0",
+            revision="v2.3.0",
             local_dir=local_dir,
             force=force,
             progress=progress,

{docling-2.49.0 → docling-2.51.0}/docling/utils/model_downloader.py

@@ -4,6 +4,7 @@ from typing import Optional
 
 from docling.datamodel.layout_model_specs import DOCLING_LAYOUT_V2
 from docling.datamodel.pipeline_options import (
+    LayoutOptions,
     granite_picture_description,
     smolvlm_picture_description,
 )
@@ -47,7 +48,7 @@ def download_models(
     if with_layout:
         _log.info("Downloading layout model...")
         LayoutModel.download_models(
-            local_dir=output_dir / DOCLING_LAYOUT_V2.model_repo_folder,
+            local_dir=output_dir / LayoutOptions().model_spec.model_repo_folder,
             force=force,
             progress=progress,
         )

{docling-2.49.0 → docling-2.51.0}/docling.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling
-Version: 2.49.0
+Version: 2.51.0
 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.
 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
@@ -27,8 +27,8 @@ 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,>=2.42.0
-Requires-Dist: docling-parse<5.0.0,>=4.2.2
-Requires-Dist: docling-ibm-models<4,>=3.9.0
+Requires-Dist: docling-parse<5.0.0,>=4.4.0
+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
@@ -101,17 +101,20 @@ Docling simplifies document processing, parsing diverse formats — including ad
 
 ## Features
 
-* 🗂️  Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, images (PNG, TIFF, JPEG, ...), and more
+* 🗂️ Parsing of [multiple document formats][supported_formats] incl. PDF, DOCX, PPTX, XLSX, HTML, WAV, MP3, 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
+* ↪️ 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 ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
-* 🎙️  Support for Audio with Automatic Speech Recognition (ASR) models
+* 🎙️ Audio support with Automatic Speech Recognition (ASR) models
 * 💻 Simple and convenient CLI
 
+### What's new
+* 📤 Structured [information extraction][extraction] \[🧪 beta\]
+
 ### Coming soon
 
 * 📝 Metadata extraction, including title, authors, references & language
@@ -222,3 +225,4 @@ 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-2.49.0 → docling-2.51.0}/docling.egg-info/requires.txt

@@ -1,7 +1,7 @@
 pydantic<3.0.0,>=2.0.0
 docling-core[chunking]<3.0.0,>=2.42.0
-docling-parse<5.0.0,>=4.2.2
-docling-ibm-models<4,>=3.9.0
+docling-parse<5.0.0,>=4.4.0
+docling-ibm-models<4,>=3.9.1
 filetype<2.0.0,>=1.2.0
 pypdfium2!=4.30.1,<5.0.0,>=4.30.0
 pydantic-settings<3.0.0,>=2.3.0

{docling-2.49.0 → docling-2.51.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "docling"
-version = "2.49.0"  # DO NOT EDIT, updated automatically
+version = "2.51.0"  # DO NOT EDIT, updated automatically
 description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
 license = "MIT"
 keywords = [
@@ -45,8 +45,8 @@ requires-python = '>=3.9,<4.0'
 dependencies = [
   'pydantic (>=2.0.0,<3.0.0)',
   'docling-core[chunking] (>=2.42.0,<3.0.0)',
-  'docling-parse (>=4.2.2,<5.0.0)',
-  "docling-ibm-models>=3.9.0,<4",
+  'docling-parse (>=4.4.0,<5.0.0)',
+  "docling-ibm-models>=3.9.1,<4",
   'filetype (>=1.2.0,<2.0.0)',
   'pypdfium2 (>=4.30.0,!=4.30.1,<5.0.0)',
   'pydantic-settings (>=2.3.0,<3.0.0)',

{docling-2.49.0 → docling-2.51.0}/tests/test_e2e_conversion.py

@@ -11,6 +11,8 @@ from .verify_utils import verify_conversion_result_v2
 
 GENERATE_V2 = GEN_TEST_DATA
 
+SKIP_DOCTAGS_COMPARISON = ["2203.01017v2.pdf"]
+
 
 def get_pdf_paths():
     # Define the directory you want to search
@@ -50,6 +52,12 @@ def test_e2e_pdfs_conversions():
 
         doc_result: ConversionResult = converter.convert(pdf_path)
 
+        # Decide if to skip doctags comparison
+        verify_doctags = pdf_path.name not in SKIP_DOCTAGS_COMPARISON
+
         verify_conversion_result_v2(
-            input_path=pdf_path, doc_result=doc_result, generate=GENERATE_V2
+            input_path=pdf_path,
+            doc_result=doc_result,
+            generate=GENERATE_V2,
+            verify_doctags=verify_doctags,
         )