docling 2.50.0__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/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."""
 

{docling-2.50.0.dist-info → docling-2.51.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling
-Version: 2.50.0
+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
@@ -27,7 +27,7 @@ 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-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
@@ -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-2.50.0.dist-info → docling-2.51.0.dist-info}/RECORD

@@ -9,7 +9,7 @@ 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/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
@@ -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=IkbBJGQjZ9nrxN9qN6L0KBLnf1F3BBg3tfCMWPmx0cQ,10966
+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
@@ -99,9 +99,9 @@ docling/utils/orientation.py,sha256=jTyLxyT31FlOodZoBMlADHNQK2lAWKYVs5z7pXd_6Cg,
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=kJtIYuzXeOyJHYlxmLAo7dGM5rEsDa1i84qEsUj1nio,1908
 docling/utils/visualization.py,sha256=tY2ylE2aiQKkmzlSLnFW-HTfFyqUUMguW18ldd1PLfo,2868
-docling-2.50.0.dist-info/licenses/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.50.0.dist-info/METADATA,sha256=w6U8qf-fYMZi6EXxFXFLxs9WOSG3S0Ilblg-klEyK3Y,10731
-docling-2.50.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-docling-2.50.0.dist-info/entry_points.txt,sha256=hzVlbeE0aMSTQ9S0-NTYN0Hmgsn6qL_EA2qX4UbkAuY,149
-docling-2.50.0.dist-info/top_level.txt,sha256=vkIywP-USjFyYo1AIRQbWQQaL3xB5jf8vkCYdTIfNic,8
-docling-2.50.0.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,,