docling 2.48.0__tar.gz → 2.50.0__tar.gz

{docling-2.48.0 → docling-2.50.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: docling
-Version: 2.48.0
+Version: 2.50.0
 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
@@ -28,7 +28,7 @@ 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-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
@@ -51,6 +51,7 @@ Requires-Dist: pluggy<2.0.0,>=1.0.0
 Requires-Dist: pylatexenc<3.0,>=2.10
 Requires-Dist: scipy<2.0.0,>=1.6.0
 Requires-Dist: accelerate<2,>=1.0.0
+Requires-Dist: polyfactory>=2.22.2
 Provides-Extra: tesserocr
 Requires-Dist: tesserocr<3.0.0,>=2.7.1; extra == "tesserocr"
 Provides-Extra: ocrmac
@@ -60,6 +61,7 @@ Requires-Dist: transformers<5.0.0,>=4.46.0; extra == "vlm"
 Requires-Dist: accelerate<2.0.0,>=1.2.1; extra == "vlm"
 Requires-Dist: mlx-vlm<1.0.0,>=0.3.0; (python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "vlm"
 Requires-Dist: vllm<1.0.0,>=0.10.0; (python_version >= "3.10" and sys_platform == "linux" and platform_machine == "x86_64") and extra == "vlm"
+Requires-Dist: qwen-vl-utils>=0.0.11; extra == "vlm"
 Provides-Extra: rapidocr
 Requires-Dist: rapidocr<4.0.0,>=3.3; python_version < "3.14" and extra == "rapidocr"
 Requires-Dist: onnxruntime<2.0.0,>=1.7.0; extra == "rapidocr"

{docling-2.48.0 → docling-2.50.0}/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-2.48.0 → docling-2.50.0}/docling/backend/msexcel_backend.py

@@ -1,10 +1,11 @@
 import logging
 from io import BytesIO
 from pathlib import Path
-from typing import Any, Union, cast
+from typing import Any, Optional, Union, cast
 
 from docling_core.types.doc import (
     BoundingBox,
+    ContentLayer,
     CoordOrigin,
     DocItem,
     DoclingDocument,
@@ -197,6 +198,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentBacken
                     parent=None,
                     label=GroupLabel.SECTION,
                     name=f"sheet: {sheet_name}",
+                    content_layer=self._get_sheet_content_layer(sheet),
                 )
                 doc = self._convert_sheet(doc, sheet)
                 width, height = self._find_page_size(doc, page_no)
@@ -237,6 +239,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentBacken
         """
 
         if self.workbook is not None:
+            content_layer = self._get_sheet_content_layer(sheet)
             tables = self._find_data_tables(sheet)
 
             for excel_table in tables:
@@ -282,6 +285,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentBacken
                             origin=CoordOrigin.TOPLEFT,
                         ),
                     ),
+                    content_layer=content_layer,
                 )
 
         return doc
@@ -486,6 +490,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentBacken
             The updated DoclingDocument.
         """
         if self.workbook is not None:
+            content_layer = self._get_sheet_content_layer(sheet)
             # Iterate over byte images in the sheet
             for item in sheet._images:  # type: ignore[attr-defined]
                 try:
@@ -511,6 +516,7 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentBacken
                                 anchor, origin=CoordOrigin.TOPLEFT
                             ),
                         ),
+                        content_layer=content_layer,
                     )
                 except Exception:
                     _log.error("could not extract the image from excel sheets")
@@ -536,3 +542,11 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend, PaginatedDocumentBacken
                 bottom = max(bottom, bbox.b) if bottom != -1 else bbox.b
 
         return (right - left, bottom - top)
+
+    @staticmethod
+    def _get_sheet_content_layer(sheet: Worksheet) -> Optional[ContentLayer]:
+        return (
+            None
+            if sheet.sheet_state == Worksheet.SHEETSTATE_VISIBLE
+            else ContentLayer.INVISIBLE
+        )

{docling-2.48.0 → docling-2.50.0}/docling/backend/pypdfium2_backend.py

@@ -254,16 +254,38 @@ class PyPdfiumPageBackend(PdfPageBackend):
     def get_bitmap_rects(self, scale: float = 1) -> Iterable[BoundingBox]:
         AREA_THRESHOLD = 0  # 32 * 32
         page_size = self.get_size()
+        rotation = self._ppage.get_rotation()
+
         with pypdfium2_lock:
             for obj in self._ppage.get_objects(filter=[pdfium_c.FPDF_PAGEOBJ_IMAGE]):
                 pos = obj.get_pos()
+                if rotation == 90:
+                    pos = (
+                        pos[1],
+                        page_size.height - pos[2],
+                        pos[3],
+                        page_size.height - pos[0],
+                    )
+                elif rotation == 180:
+                    pos = (
+                        page_size.width - pos[2],
+                        page_size.height - pos[3],
+                        page_size.width - pos[0],
+                        page_size.height - pos[1],
+                    )
+                elif rotation == 270:
+                    pos = (
+                        page_size.width - pos[3],
+                        pos[0],
+                        page_size.width - pos[1],
+                        pos[2],
+                    )
+
                 cropbox = BoundingBox.from_tuple(
                     pos, origin=CoordOrigin.BOTTOMLEFT
                 ).to_top_left_origin(page_height=page_size.height)
-
                 if cropbox.area() > AREA_THRESHOLD:
                     cropbox = cropbox.scaled(scale=scale)
-
                     yield cropbox
 
     def get_text_in_rect(self, bbox: BoundingBox) -> str:

{docling-2.48.0 → docling-2.50.0}/docling/datamodel/base_models.py

@@ -1,7 +1,7 @@
 import math
 from collections import defaultdict
 from enum import Enum
-from typing import TYPE_CHECKING, Dict, List, Optional, Union
+from typing import TYPE_CHECKING, Dict, List, Optional, Type, Union
 
 import numpy as np
 from docling_core.types.doc import (
@@ -32,6 +32,18 @@ from pydantic import (
 if TYPE_CHECKING:
     from docling.backend.pdf_backend import PdfPageBackend
 
+from docling.backend.abstract_backend import AbstractDocumentBackend
+from docling.datamodel.pipeline_options import PipelineOptions
+
+
+class BaseFormatOption(BaseModel):
+    """Base class for format options used by _DocumentConversionInput."""
+
+    pipeline_options: Optional[PipelineOptions] = None
+    backend: Type[AbstractDocumentBackend]
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
 
 class ConversionStatus(str, Enum):
     PENDING = "pending"

{docling-2.48.0 → docling-2.50.0}/docling/datamodel/document.py

@@ -2,12 +2,13 @@ import csv
 import logging
 import re
 import tarfile
-from collections.abc import Iterable
+from collections.abc import Iterable, Mapping
 from enum import Enum
 from io import BytesIO
 from pathlib import Path, PurePath
 from typing import (
     TYPE_CHECKING,
+    Any,
     Dict,
     List,
     Literal,
@@ -72,7 +73,7 @@ from docling.utils.profiling import ProfilingItem
 from docling.utils.utils import create_file_hash
 
 if TYPE_CHECKING:
-    from docling.document_converter import FormatOption
+    from docling.datamodel.base_models import BaseFormatOption
 
 _log = logging.getLogger(__name__)
 
@@ -238,7 +239,8 @@ class _DocumentConversionInput(BaseModel):
     limits: Optional[DocumentLimits] = DocumentLimits()
 
     def docs(
-        self, format_options: Dict[InputFormat, "FormatOption"]
+        self,
+        format_options: Mapping[InputFormat, "BaseFormatOption"],
     ) -> Iterable[InputDocument]:
         for item in self.path_or_stream_iterator:
             obj = (

docling-2.50.0/docling/datamodel/extraction.py

@@ -0,0 +1,39 @@
+"""Data models for document extraction functionality."""
+
+from typing import Any, Dict, List, Optional, Type, Union
+
+from pydantic import BaseModel, Field
+
+from docling.datamodel.base_models import ConversionStatus, ErrorItem
+from docling.datamodel.document import InputDocument
+
+
+class ExtractedPageData(BaseModel):
+    """Data model for extracted content from a single page."""
+
+    page_no: int = Field(..., description="1-indexed page number")
+    extracted_data: Optional[Dict[str, Any]] = Field(
+        None, description="Extracted structured data from the page"
+    )
+    raw_text: Optional[str] = Field(None, description="Raw extracted text")
+    errors: List[str] = Field(
+        default_factory=list,
+        description="Any errors encountered during extraction for this page",
+    )
+
+
+class ExtractionResult(BaseModel):
+    """Result of document extraction."""
+
+    input: InputDocument
+    status: ConversionStatus = ConversionStatus.PENDING
+    errors: List[ErrorItem] = []
+
+    # Pages field - always a list for consistency
+    pages: List[ExtractedPageData] = Field(
+        default_factory=list, description="Extracted data from each page"
+    )
+
+
+# Type alias for template parameters that can be string, dict, or BaseModel
+ExtractionTemplateType = Union[str, Dict[str, Any], BaseModel, Type[BaseModel]]

{docling-2.48.0 → docling-2.50.0}/docling/datamodel/pipeline_options.py

@@ -37,6 +37,7 @@ from docling.datamodel.pipeline_options_vlm_model import (
 from docling.datamodel.vlm_model_specs import (
     GRANITE_VISION_OLLAMA as granite_vision_vlm_ollama_conversion_options,
     GRANITE_VISION_TRANSFORMERS as granite_vision_vlm_conversion_options,
+    NU_EXTRACT_2B_TRANSFORMERS,
     SMOLDOCLING_MLX as smoldocling_vlm_mlx_conversion_options,
     SMOLDOCLING_TRANSFORMERS as smoldocling_vlm_conversion_options,
     VlmModelType,
@@ -113,6 +114,7 @@ class RapidOcrOptions(OcrOptions):
     cls_model_path: Optional[str] = None  # same default as rapidocr
     rec_model_path: Optional[str] = None  # same default as rapidocr
     rec_keys_path: Optional[str] = None  # same default as rapidocr
+    rec_font_path: Optional[str] = None  # same default as rapidocr
 
     model_config = ConfigDict(
         extra="forbid",
@@ -246,12 +248,9 @@ class OcrEngine(str, Enum):
     RAPIDOCR = "rapidocr"
 
 
-class PipelineOptions(BaseModel):
+class PipelineOptions(BaseOptions):
     """Base pipeline options."""
 
-    create_legacy_output: bool = (
-        True  # This default will be set to False on a future version of docling
-    )
     document_timeout: Optional[float] = None
     accelerator_options: AcceleratorOptions = AcceleratorOptions()
     enable_remote_services: bool = False
@@ -284,10 +283,10 @@ 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):
@@ -295,6 +294,13 @@ class AsrPipelineOptions(PipelineOptions):
     artifacts_path: Optional[Union[Path, str]] = None
 
 
+class VlmExtractionPipelineOptions(PipelineOptions):
+    """Options for extraction pipeline."""
+
+    artifacts_path: Optional[Union[Path, str]] = None
+    vlm_options: Union[InlineVlmOptions] = NU_EXTRACT_2B_TRANSFORMERS
+
+
 class PdfPipelineOptions(PaginatedPipelineOptions):
     """Options for the PDF pipeline."""
 

{docling-2.48.0 → docling-2.50.0}/docling/datamodel/vlm_model_specs.py

@@ -247,6 +247,23 @@ DOLPHIN_TRANSFORMERS = InlineVlmOptions(
     temperature=0.0,
 )
 
+# NuExtract
+NU_EXTRACT_2B_TRANSFORMERS = InlineVlmOptions(
+    repo_id="numind/NuExtract-2.0-2B",
+    prompt="",  # This won't be used, template is passed separately
+    torch_dtype="bfloat16",
+    inference_framework=InferenceFramework.TRANSFORMERS,
+    transformers_model_type=TransformersModelType.AUTOMODEL_IMAGETEXTTOTEXT,
+    response_format=ResponseFormat.PLAINTEXT,
+    supported_devices=[
+        AcceleratorDevice.CPU,
+        AcceleratorDevice.CUDA,
+        AcceleratorDevice.MPS,
+    ],
+    scale=2.0,
+    temperature=0.0,
+)
+
 
 class VlmModelType(str, Enum):
     SMOLDOCLING = "smoldocling"

{docling-2.48.0 → docling-2.50.0}/docling/document_converter.py

@@ -28,6 +28,7 @@ from docling.backend.noop_backend import NoOpBackend
 from docling.backend.xml.jats_backend import JatsDocumentBackend
 from docling.backend.xml.uspto_backend import PatentUsptoDocumentBackend
 from docling.datamodel.base_models import (
+    BaseFormatOption,
     ConversionStatus,
     DoclingComponentType,
     DocumentStream,
@@ -57,12 +58,8 @@ _log = logging.getLogger(__name__)
 _PIPELINE_CACHE_LOCK = threading.Lock()
 
 
-class FormatOption(BaseModel):
+class FormatOption(BaseFormatOption):
     pipeline_cls: Type[BasePipeline]
-    pipeline_options: Optional[PipelineOptions] = None
-    backend: Type[AbstractDocumentBackend]
-
-    model_config = ConfigDict(arbitrary_types_allowed=True)
 
     @model_validator(mode="after")
     def set_optional_field_default(self) -> "FormatOption":
@@ -191,7 +188,7 @@ class DocumentConverter:
         self.allowed_formats = (
             allowed_formats if allowed_formats is not None else list(InputFormat)
         )
-        self.format_to_options = {
+        self.format_to_options: Dict[InputFormat, FormatOption] = {
             format: (
                 _get_default_option(format=format)
                 if (custom_option := (format_options or {}).get(format)) is None