docling 2.49.0__py3-none-any.whl → 2.51.0__py3-none-any.whl

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/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/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/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/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/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/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.dist-info → docling-2.51.0.dist-info}/METADATA

@@ -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.dist-info → docling-2.51.0.dist-info}/RECORD

@@ -9,8 +9,8 @@ docling/backend/asciidoc_backend.py,sha256=RDNLrPJHxROiM7-NQdZn3DdvAyiPAndbSWcZo
 docling/backend/csv_backend.py,sha256=2g9famYG2W-ID9jEdZPxc6O8QGv1vWQfjN8pL-QMBE0,4536
 docling/backend/docling_parse_backend.py,sha256=9rUo1vPxX6QLzGqF-2B2iEYglZg6YQ3Uea00XrLluTg,7918
 docling/backend/docling_parse_v2_backend.py,sha256=3ckTfke8IICjaImlIzc3TRhG7KDuxDDba0AuCEcjA-M,9500
-docling/backend/docling_parse_v4_backend.py,sha256=MbCMxNGmoW4iuev9tX1Vt4jtIeak2kC9Uac3xQSRxeo,7509
-docling/backend/html_backend.py,sha256=MqtU9fA83lcjqb85lFTmGDedOH72WxTmwvj0ZzPur1I,42224
+docling/backend/docling_parse_v4_backend.py,sha256=xCBbaaXjNNrOaod9tmBuCbe5mL_ipmTNG2XOxVbGG3w,7891
+docling/backend/html_backend.py,sha256=7I3BQSmC7P47jpzXHt3OuPNhtVedJiZVEjjLykyx5pY,42245
 docling/backend/md_backend.py,sha256=qCI7SD9hnWWGrkG_drpzQv2Z7DVBG4Tsq3hhTsYV790,22562
 docling/backend/mets_gbs_backend.py,sha256=EA8sY6tbmGiysKGYPPZiNlK-i7Adn8bLTo-7Ym15hTU,12774
 docling/backend/msexcel_backend.py,sha256=5JRbPwOjR1r45AMeIts1rj6InbOgLBf_CtAhvNPVmsQ,19157
@@ -40,7 +40,7 @@ docling/datamodel/base_models.py,sha256=vOt895z0GsFirHkkI3hM23e9oyUuz9RXfcGFtoIN
 docling/datamodel/document.py,sha256=ElY7G6FYJ6Bayyw433_tbnxyE47fnQRoBG_mygvOBrA,17370
 docling/datamodel/extraction.py,sha256=7dgvtK5SuvgfB8LHAwS1FwrW1kcMQJuJG0ol8uAQgoQ,1323
 docling/datamodel/layout_model_specs.py,sha256=GSkJ-Z_0PVgwWGi7C7TsxbzRjlrWS9ZrHJjHumv-Z5U,2339
-docling/datamodel/pipeline_options.py,sha256=0J0xVOSfI3pqRMkXlzX_rtmVBgCTsR2QJz54xugP8sg,10963
+docling/datamodel/pipeline_options.py,sha256=bwBZoQbjk--5vE7Vz7N6KEbew-b93ge0ez1-cDPlUnQ,11019
 docling/datamodel/pipeline_options_asr_model.py,sha256=7X068xl-qpbyPxC7-TwX7Q6tLyZXGT5h1osZ_xLNLM0,1454
 docling/datamodel/pipeline_options_vlm_model.py,sha256=AcqqThSW74hwQ6x7pazzm57LnJiUqB7gQi5wFayGlbk,2628
 docling/datamodel/settings.py,sha256=c0MTw6pO5be_BKxHKYl4SaBJAw_qL-aapxp-g5HHj1A,2084
@@ -52,16 +52,16 @@ docling/models/base_ocr_model.py,sha256=kT8TylASOpPlY60rIG6VL6_eLVsfg5KvEVnZHzDW
 docling/models/code_formula_model.py,sha256=XRugm4EwifLRc-TrAk-glKlktJP-nAPneKh2EOovkJU,11308
 docling/models/document_picture_classifier.py,sha256=9JvoWeH5uQBC7levjM8zptk7UT-b8EQnD-2EnxTjTT4,6202
 docling/models/easyocr_model.py,sha256=ECPBd-48cCw5s935NsPJO_C_1QuK_yAUGloMM77WqIM,7387
-docling/models/layout_model.py,sha256=Nfbo6keMB4vVjGoZdFMqD9CmZcWh-0bE3LkRjJTDJQ0,9146
+docling/models/layout_model.py,sha256=2D7Ey2Mvtzyq9KARIFLaUZKzsR661h7Zggwn0IM9R3c,9154
 docling/models/ocr_mac_model.py,sha256=y-1DSFDbACHpEwNTfQwzN9ab8r5j5rBFNPtQ48BzsrA,5396
 docling/models/page_assemble_model.py,sha256=TvN1naez7dUodLxpUUBzpuMCpqZBTf6YSpewxgjzmrg,6323
-docling/models/page_preprocessing_model.py,sha256=rHNX1uP1ScTjVUlsxZ0eamK2uNUqI94WpnyrP10Pj6k,5277
+docling/models/page_preprocessing_model.py,sha256=EmusNexws5ZmR93js_saVU0BedqZ_HIHQeY7lcf52tI,5284
 docling/models/picture_description_api_model.py,sha256=o3EkV5aHW_6WzE_fdj_VRnNCrS_btclO_ZCLAUqrfl0,2377
 docling/models/picture_description_base_model.py,sha256=kLthLhdlgwhootQ4_xhhcAk6A-vso5-qcsFJ3TcYfO0,2991
 docling/models/picture_description_vlm_model.py,sha256=5BJvaF3PHuL9lCVYqPv9krh3h_7YwNSdKYw1EVEj13k,4156
 docling/models/rapid_ocr_model.py,sha256=7yZC7I1qoC9xC8xJIjTk2c8VFm89RfB6Vr7IDOnr5gs,7102
 docling/models/readingorder_model.py,sha256=bZoXHaSwUsa8niSmJrbCuy784ixCeBXT-RQBUfgHJ4A,14925
-docling/models/table_structure_model.py,sha256=RFXo73f2q4XuKyaSqbxpznh7JVtlLcT0FsOWl9oZbSg,12518
+docling/models/table_structure_model.py,sha256=7vO8LisdoqCTsY8X8lsk9d-oD2hVjUtdaWlkMTQxEg0,12518
 docling/models/tesseract_ocr_cli_model.py,sha256=I3Gn28Y-LD8OfvyCElN9fLiNgpo2sT0uMkVt258253s,12881
 docling/models/tesseract_ocr_model.py,sha256=GdI5Cjfi87qcehVbM3wdKRvKkl_F9A4bwTUbjXZCJYA,10745
 docling/models/factories/__init__.py,sha256=x_EM5dDg_A3HBcBYzOoqwmA2AFLtJ1IzYDPX-R1A-Sg,868
@@ -93,15 +93,15 @@ docling/utils/export.py,sha256=VwVUnYDk3mhGmISDbVm306fwpGNnoojouStBD4UajXI,4673
 docling/utils/glm_utils.py,sha256=TKOWQqWAHsX_w4fvoAA7_2xCi_urhnp1DsmjY8_sk5w,12274
 docling/utils/layout_postprocessor.py,sha256=sE9UR3Nv4iOk26uoIsN3bFioE7ScfAjj0orDBDneLXg,25166
 docling/utils/locks.py,sha256=RzqQtD5UispgV71pGN_nU6GYfeN11BN0Sh_Dq9ycqGo,52
-docling/utils/model_downloader.py,sha256=3vijCsAIVwWqehGBDRxRq7mJ3yRb9-zBsG00iqjqegU,4076
+docling/utils/model_downloader.py,sha256=lAIyevIC6dyv1TS0ElRSAGNylB5n_V8pWs1PhxH8wAQ,4104
 docling/utils/ocr_utils.py,sha256=nmresYyfin0raanpQc_GGeU3WoLsfExf6SEXNIQ7Djg,2325
 docling/utils/orientation.py,sha256=jTyLxyT31FlOodZoBMlADHNQK2lAWKYVs5z7pXd_6Cg,1842
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=kJtIYuzXeOyJHYlxmLAo7dGM5rEsDa1i84qEsUj1nio,1908
 docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
-docling-2.49.0.dist-info/licenses/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.49.0.dist-info/METADATA,sha256=Gn1u-LwLRMCqHamlyu1M4w9a8NvGfk-jfcCh0XjhsfQ,10731
-docling-2.49.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-docling-2.49.0.dist-info/entry_points.txt,sha256=hzVlbeE0aMSTQ9S0-NTYN0Hmgsn6qL_EA2qX4UbkAuY,149
-docling-2.49.0.dist-info/top_level.txt,sha256=vkIywP-USjFyYo1AIRQbWQQaL3xB5jf8vkCYdTIfNic,8
-docling-2.49.0.dist-info/RECORD,,
+docling-2.51.0.dist-info/licenses/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.51.0.dist-info/METADATA,sha256=oVomcZQUJIX-QnMmIFggzyjuhea7jbgVXus9bZZkYDU,10886
+docling-2.51.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+docling-2.51.0.dist-info/entry_points.txt,sha256=hzVlbeE0aMSTQ9S0-NTYN0Hmgsn6qL_EA2qX4UbkAuY,149
+docling-2.51.0.dist-info/top_level.txt,sha256=vkIywP-USjFyYo1AIRQbWQQaL3xB5jf8vkCYdTIfNic,8
+docling-2.51.0.dist-info/RECORD,,