docling 2.15.0__tar.gz → 2.16.0__tar.gz

{docling-2.15.0 → docling-2.16.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.15.0
+Version: 2.16.0
 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
 License: MIT
@@ -26,9 +26,9 @@ Provides-Extra: tesserocr
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=1.0.0,<2.0.0)
-Requires-Dist: docling-core[chunking] (>=2.13.1,<3.0.0)
-Requires-Dist: docling-ibm-models (>=3.1.0,<4.0.0)
-Requires-Dist: docling-parse (>=3.0.0,<4.0.0)
+Requires-Dist: docling-core[chunking] (>=2.15.1,<3.0.0)
+Requires-Dist: docling-ibm-models (>=3.3.0,<4.0.0)
+Requires-Dist: docling-parse (>=3.1.0,<4.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -39,13 +39,14 @@ Requires-Dist: onnxruntime (>=1.7.0,<1.20.0) ; (python_version < "3.10") and (ex
 Requires-Dist: onnxruntime (>=1.7.0,<2.0.0) ; (python_version >= "3.10") and (extra == "rapidocr")
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: pandas (>=2.1.4,<3.0.0)
+Requires-Dist: pillow (>=10.0.0,<11.0.0)
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
 Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
 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)
 Requires-Dist: rapidocr-onnxruntime (>=1.4.0,<2.0.0) ; (python_version < "3.13") and (extra == "rapidocr")
-Requires-Dist: requests (>=2.32.3,<3.0.0)
+Requires-Dist: requests (>=2.32.2,<3.0.0)
 Requires-Dist: rtree (>=1.3.0,<2.0.0)
 Requires-Dist: scipy (>=1.6.0,<2.0.0)
 Requires-Dist: tesserocr (>=2.7.1,<3.0.0) ; extra == "tesserocr"
@@ -84,7 +85,7 @@ Docling parses documents and exports them to the desired format with ease and sp
 * 🗂️ Reads popular document formats (PDF, DOCX, PPTX, XLSX, Images, HTML, AsciiDoc & Markdown) and exports to HTML, Markdown and JSON (with embedded and referenced images)
 * 📑 Advanced PDF document understanding including page layout, reading order & table structures
 * 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
-* 🤖 Easy integration with 🦙 LlamaIndex & 🦜🔗 LangChain for powerful RAG / QA applications
+* 🤖 Plug-and-play [integrations](https://ds4sd.github.io/docling/integrations/) incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
 * 🔍 OCR support for scanned PDFs
 * 💻 Simple and convenient CLI
 
@@ -94,7 +95,6 @@ Explore the [documentation](https://ds4sd.github.io/docling/) to discover plenty
 
 * ♾️ Equation & code extraction
 * 📝 Metadata extraction, including title, authors, references & language
-* 🦜🔗 Native LangChain extension
 
 ## Installation
 

{docling-2.15.0 → docling-2.16.0}/README.md

@@ -29,7 +29,7 @@ Docling parses documents and exports them to the desired format with ease and sp
 * 🗂️ Reads popular document formats (PDF, DOCX, PPTX, XLSX, Images, HTML, AsciiDoc & Markdown) and exports to HTML, Markdown and JSON (with embedded and referenced images)
 * 📑 Advanced PDF document understanding including page layout, reading order & table structures
 * 🧩 Unified, expressive [DoclingDocument](https://ds4sd.github.io/docling/concepts/docling_document/) representation format
-* 🤖 Easy integration with 🦙 LlamaIndex & 🦜🔗 LangChain for powerful RAG / QA applications
+* 🤖 Plug-and-play [integrations](https://ds4sd.github.io/docling/integrations/) incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
 * 🔍 OCR support for scanned PDFs
 * 💻 Simple and convenient CLI
 
@@ -39,7 +39,6 @@ Explore the [documentation](https://ds4sd.github.io/docling/) to discover plenty
 
 * ♾️ Equation & code extraction
 * 📝 Metadata extraction, including title, authors, references & language
-* 🦜🔗 Native LangChain extension
 
 ## Installation
 

{docling-2.15.0 → docling-2.16.0}/docling/backend/abstract_backend.py

@@ -27,7 +27,6 @@ class AbstractDocumentBackend(ABC):
     def supports_pagination(cls) -> bool:
         pass
 
-    @abstractmethod
     def unload(self):
         if isinstance(self.path_or_stream, BytesIO):
             self.path_or_stream.close()

{docling-2.15.0 → docling-2.16.0}/docling/backend/asciidoc_backend.py

@@ -24,7 +24,6 @@ _log = logging.getLogger(__name__)
 
 
 class AsciiDocBackend(DeclarativeDocumentBackend):
-
     def __init__(self, in_doc: InputDocument, path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
 

{docling-2.15.0 → docling-2.16.0}/docling/backend/docling_parse_backend.py

@@ -132,7 +132,7 @@ class DoclingParsePageBackend(PdfPageBackend):
         return cells
 
     def get_bitmap_rects(self, scale: float = 1) -> Iterable[BoundingBox]:
-        AREA_THRESHOLD = 32 * 32
+        AREA_THRESHOLD = 0  # 32 * 32
 
         for i in range(len(self._dpage["images"])):
             bitmap = self._dpage["images"][i]
@@ -163,7 +163,7 @@ class DoclingParsePageBackend(PdfPageBackend):
                 l=0, r=0, t=0, b=0, coord_origin=CoordOrigin.BOTTOMLEFT
             )
         else:
-            padbox = cropbox.to_bottom_left_origin(page_size.height)
+            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
 

{docling-2.15.0 → docling-2.16.0}/docling/backend/docling_parse_v2_backend.py

@@ -140,7 +140,7 @@ class DoclingParseV2PageBackend(PdfPageBackend):
         return cells
 
     def get_bitmap_rects(self, scale: float = 1) -> Iterable[BoundingBox]:
-        AREA_THRESHOLD = 32 * 32
+        AREA_THRESHOLD = 0  # 32 * 32
 
         images = self._dpage["sanitized"]["images"]["data"]
         images_header = self._dpage["sanitized"]["images"]["header"]
@@ -178,7 +178,7 @@ class DoclingParseV2PageBackend(PdfPageBackend):
                 l=0, r=0, t=0, b=0, coord_origin=CoordOrigin.BOTTOMLEFT
             )
         else:
-            padbox = cropbox.to_bottom_left_origin(page_size.height)
+            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
 

{docling-2.15.0 → docling-2.16.0}/docling/backend/html_backend.py

@@ -215,7 +215,7 @@ class HTMLDocumentBackend(DeclarativeDocumentBackend):
         label = DocItemLabel.CODE
         if len(text) == 0:
             return
-        doc.add_text(parent=self.parents[self.level], label=label, text=text)
+        doc.add_code(parent=self.parents[self.level], label=label, text=text)
 
     def handle_paragraph(self, element, idx, doc):
         """Handles paragraph tags (p)."""

docling-2.16.0/docling/backend/json/docling_json_backend.py

@@ -0,0 +1,58 @@
+from io import BytesIO
+from pathlib import Path
+from typing import Union
+
+from docling_core.types.doc import DoclingDocument
+from typing_extensions import override
+
+from docling.backend.abstract_backend import DeclarativeDocumentBackend
+from docling.datamodel.base_models import InputFormat
+from docling.datamodel.document import InputDocument
+
+
+class DoclingJSONBackend(DeclarativeDocumentBackend):
+    @override
+    def __init__(
+        self, in_doc: InputDocument, path_or_stream: Union[BytesIO, Path]
+    ) -> None:
+        super().__init__(in_doc, path_or_stream)
+
+        # given we need to store any actual conversion exception for raising it from
+        # convert(), this captures the successful result or the actual error in a
+        # mutually exclusive way:
+        self._doc_or_err = self._get_doc_or_err()
+
+    @override
+    def is_valid(self) -> bool:
+        return isinstance(self._doc_or_err, DoclingDocument)
+
+    @classmethod
+    @override
+    def supports_pagination(cls) -> bool:
+        return False
+
+    @classmethod
+    @override
+    def supported_formats(cls) -> set[InputFormat]:
+        return {InputFormat.JSON_DOCLING}
+
+    def _get_doc_or_err(self) -> Union[DoclingDocument, Exception]:
+        try:
+            json_data: Union[str, bytes]
+            if isinstance(self.path_or_stream, Path):
+                with open(self.path_or_stream, encoding="utf-8") as f:
+                    json_data = f.read()
+            elif isinstance(self.path_or_stream, BytesIO):
+                json_data = self.path_or_stream.getvalue()
+            else:
+                raise RuntimeError(f"Unexpected: {type(self.path_or_stream)=}")
+            return DoclingDocument.model_validate_json(json_data=json_data)
+        except Exception as e:
+            return e
+
+    @override
+    def convert(self) -> DoclingDocument:
+        if isinstance(self._doc_or_err, DoclingDocument):
+            return self._doc_or_err
+        else:
+            raise self._doc_or_err

{docling-2.15.0 → docling-2.16.0}/docling/backend/md_backend.py

@@ -3,19 +3,22 @@ import re
 import warnings
 from io import BytesIO
 from pathlib import Path
-from typing import Set, Union
+from typing import List, Optional, Set, Union
 
 import marko
 import marko.ext
 import marko.ext.gfm
 import marko.inline
 from docling_core.types.doc import (
+    DocItem,
     DocItemLabel,
     DoclingDocument,
     DocumentOrigin,
     GroupLabel,
+    NodeItem,
     TableCell,
     TableData,
+    TextItem,
 )
 from marko import Markdown
 
@@ -27,8 +30,7 @@ _log = logging.getLogger(__name__)
 
 
 class MarkdownDocumentBackend(DeclarativeDocumentBackend):
-
-    def shorten_underscore_sequences(self, markdown_text, max_length=10):
+    def shorten_underscore_sequences(self, markdown_text: str, max_length: int = 10):
         # This regex will match any sequence of underscores
         pattern = r"_+"
 
@@ -90,13 +92,13 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             ) from e
         return
 
-    def close_table(self, doc=None):
+    def close_table(self, doc: DoclingDocument):
         if self.in_table:
             _log.debug("=== TABLE START ===")
             for md_table_row in self.md_table_buffer:
                 _log.debug(md_table_row)
             _log.debug("=== TABLE END ===")
-            tcells = []
+            tcells: List[TableCell] = []
             result_table = []
             for n, md_table_row in enumerate(self.md_table_buffer):
                 data = []
@@ -137,15 +139,19 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             self.in_table = False
             self.md_table_buffer = []  # clean table markdown buffer
             # Initialize Docling TableData
-            data = TableData(num_rows=num_rows, num_cols=num_cols, table_cells=tcells)
+            table_data = TableData(
+                num_rows=num_rows, num_cols=num_cols, table_cells=tcells
+            )
             # Populate
             for tcell in tcells:
-                data.table_cells.append(tcell)
+                table_data.table_cells.append(tcell)
             if len(tcells) > 0:
-                doc.add_table(data=data)
+                doc.add_table(data=table_data)
         return
 
-    def process_inline_text(self, parent_element, doc=None):
+    def process_inline_text(
+        self, parent_element: Optional[NodeItem], doc: DoclingDocument
+    ):
         # self.inline_text_buffer += str(text_in)
         txt = self.inline_text_buffer.strip()
         if len(txt) > 0:
@@ -156,14 +162,20 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             )
         self.inline_text_buffer = ""
 
-    def iterate_elements(self, element, depth=0, doc=None, parent_element=None):
+    def iterate_elements(
+        self,
+        element: marko.block.Element,
+        depth: int,
+        doc: DoclingDocument,
+        parent_element: Optional[NodeItem] = None,
+    ):
         # Iterates over all elements in the AST
         # Check for different element types and process relevant details
         if isinstance(element, marko.block.Heading):
             self.close_table(doc)
             self.process_inline_text(parent_element, doc)
             _log.debug(
-                f" - Heading level {element.level}, content: {element.children[0].children}"
+                f" - Heading level {element.level}, content: {element.children[0].children}"  # type: ignore
             )
             if element.level == 1:
                 doc_label = DocItemLabel.TITLE
@@ -172,10 +184,10 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
 
             # Header could have arbitrary inclusion of bold, italic or emphasis,
             # hence we need to traverse the tree to get full text of a header
-            strings = []
+            strings: List[str] = []
 
             # Define a recursive function to traverse the tree
-            def traverse(node):
+            def traverse(node: marko.block.BlockElement):
                 # Check if the node has a "children" attribute
                 if hasattr(node, "children"):
                     # If "children" is a list, continue traversal
@@ -209,9 +221,13 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             self.process_inline_text(parent_element, doc)
             _log.debug(" - List item")
 
-            snippet_text = str(element.children[0].children[0].children)
+            snippet_text = str(element.children[0].children[0].children)  # type: ignore
             is_numbered = False
-            if parent_element.label == GroupLabel.ORDERED_LIST:
+            if (
+                parent_element is not None
+                and isinstance(parent_element, DocItem)
+                and parent_element.label == GroupLabel.ORDERED_LIST
+            ):
                 is_numbered = True
             doc.add_list_item(
                 enumerated=is_numbered, parent=parent_element, text=snippet_text
@@ -221,7 +237,14 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             self.close_table(doc)
             self.process_inline_text(parent_element, doc)
             _log.debug(f" - Image with alt: {element.title}, url: {element.dest}")
-            doc.add_picture(parent=parent_element, caption=element.title)
+
+            fig_caption: Optional[TextItem] = None
+            if element.title is not None and element.title != "":
+                fig_caption = doc.add_text(
+                    label=DocItemLabel.CAPTION, text=element.title
+                )
+
+            doc.add_picture(parent=parent_element, caption=fig_caption)
 
         elif isinstance(element, marko.block.Paragraph):
             self.process_inline_text(parent_element, doc)
@@ -252,27 +275,21 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             self.process_inline_text(parent_element, doc)
             _log.debug(f" - Code Span: {element.children}")
             snippet_text = str(element.children).strip()
-            doc.add_text(
-                label=DocItemLabel.CODE, parent=parent_element, text=snippet_text
-            )
+            doc.add_code(parent=parent_element, text=snippet_text)
 
         elif isinstance(element, marko.block.CodeBlock):
             self.close_table(doc)
             self.process_inline_text(parent_element, doc)
             _log.debug(f" - Code Block: {element.children}")
-            snippet_text = str(element.children[0].children).strip()
-            doc.add_text(
-                label=DocItemLabel.CODE, parent=parent_element, text=snippet_text
-            )
+            snippet_text = str(element.children[0].children).strip()  # type: ignore
+            doc.add_code(parent=parent_element, text=snippet_text)
 
         elif isinstance(element, marko.block.FencedCode):
             self.close_table(doc)
             self.process_inline_text(parent_element, doc)
             _log.debug(f" - Code Block: {element.children}")
-            snippet_text = str(element.children[0].children).strip()
-            doc.add_text(
-                label=DocItemLabel.CODE, parent=parent_element, text=snippet_text
-            )
+            snippet_text = str(element.children[0].children).strip()  # type: ignore
+            doc.add_code(parent=parent_element, text=snippet_text)
 
         elif isinstance(element, marko.inline.LineBreak):
             self.process_inline_text(parent_element, doc)

{docling-2.15.0 → docling-2.16.0}/docling/backend/msexcel_backend.py

@@ -26,6 +26,7 @@ _log = logging.getLogger(__name__)
 
 from typing import Any, List
 
+from PIL import Image as PILImage
 from pydantic import BaseModel
 
 
@@ -44,7 +45,6 @@ class ExcelTable(BaseModel):
 
 
 class MsExcelDocumentBackend(DeclarativeDocumentBackend):
-
     def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
 
@@ -326,49 +326,61 @@ class MsExcelDocumentBackend(DeclarativeDocumentBackend):
         self, doc: DoclingDocument, sheet: Worksheet
     ) -> DoclingDocument:
 
-        # FIXME: mypy does not agree with _images ...
-        """
-        # Iterate over images in the sheet
-        for idx, image in enumerate(sheet._images):  # Access embedded images
+        # Iterate over byte images in the sheet
+        for idx, image in enumerate(sheet._images):  # type: ignore
 
-            image_bytes = BytesIO(image.ref.blob)
-            pil_image = Image.open(image_bytes)
+            try:
+                pil_image = PILImage.open(image.ref)
 
-            doc.add_picture(
-                parent=self.parents[0],
-                image=ImageRef.from_pil(image=pil_image, dpi=72),
-                caption=None,
-            )
-        """
+                doc.add_picture(
+                    parent=self.parents[0],
+                    image=ImageRef.from_pil(image=pil_image, dpi=72),
+                    caption=None,
+                )
+            except:
+                _log.error("could not extract the image from excel sheets")
 
-        # FIXME: mypy does not agree with _charts ...
         """
-        for idx, chart in enumerate(sheet._charts):  # Access embedded charts
-            chart_path = f"chart_{idx + 1}.png"
-            _log.info(
-                f"Chart found, but dynamic rendering is required for: {chart_path}"
-            )
+        for idx, chart in enumerate(sheet._charts):  # type: ignore
+            try:
+                chart_path = f"chart_{idx + 1}.png"
+                _log.info(
+                    f"Chart found, but dynamic rendering is required for: {chart_path}"
+                )
 
-            _log.info(f"Chart {idx + 1}:")
-        
-            # Chart type
-            _log.info(f"Type: {type(chart).__name__}")
-            
-            # Title
-            if chart.title:
-                _log.info(f"Title: {chart.title}")
-            else:
-                _log.info("No title")
-            
-            # Data series
-            for series in chart.series:
-                _log.info(" => series ...")
-                _log.info(f"Data Series: {series.title}")
-                _log.info(f"Values: {series.values}")
-                _log.info(f"Categories: {series.categories}")
+                _log.info(f"Chart {idx + 1}:")
                 
-            # Position
-            # _log.info(f"Anchor Cell: {chart.anchor}")
+                # Chart type
+                # _log.info(f"Type: {type(chart).__name__}")
+                print(f"Type: {type(chart).__name__}")
+
+                # Extract series data
+                for series_idx, series in enumerate(chart.series):
+                    #_log.info(f"Series {series_idx + 1}:")
+                    print(f"Series {series_idx + 1} type: {type(series).__name__}")
+                    #print(f"x-values: {series.xVal}")
+                    #print(f"y-values: {series.yVal}")
+
+                    print(f"xval type: {type(series.xVal).__name__}")
+                    
+                    xvals = []
+                    for _ in series.xVal.numLit.pt:
+                        print(f"xval type: {type(_).__name__}")
+                        if hasattr(_, 'v'):
+                            xvals.append(_.v)
+
+                    print(f"x-values: {xvals}")
+                            
+                    yvals = []
+                    for _ in series.yVal:
+                        if hasattr(_, 'v'):
+                            yvals.append(_.v)
+                            
+                    print(f"y-values: {yvals}")                    
+                    
+            except Exception as exc:
+                print(exc)
+                continue
         """
 
         return doc

{docling-2.15.0 → docling-2.16.0}/docling/backend/msword_backend.py

@@ -26,7 +26,6 @@ _log = logging.getLogger(__name__)
 
 
 class MsWordDocumentBackend(DeclarativeDocumentBackend):
-
     def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
         self.XML_KEY = (

{docling-2.15.0 → docling-2.16.0}/docling/backend/pdf_backend.py

@@ -12,7 +12,6 @@ from docling.datamodel.document import InputDocument
 
 
 class PdfPageBackend(ABC):
-
     @abstractmethod
     def get_text_in_rect(self, bbox: BoundingBox) -> str:
         pass
@@ -45,7 +44,6 @@ class PdfPageBackend(ABC):
 
 
 class PdfDocumentBackend(PaginatedDocumentBackend):
-
     def __init__(self, in_doc: InputDocument, path_or_stream: Union[BytesIO, Path]):
         super().__init__(in_doc, path_or_stream)
 

{docling-2.15.0 → docling-2.16.0}/docling/backend/pypdfium2_backend.py

@@ -39,7 +39,7 @@ class PyPdfiumPageBackend(PdfPageBackend):
         return self.valid
 
     def get_bitmap_rects(self, scale: float = 1) -> Iterable[BoundingBox]:
-        AREA_THRESHOLD = 32 * 32
+        AREA_THRESHOLD = 0  # 32 * 32
         for obj in self._ppage.get_objects(filter=[pdfium_c.FPDF_PAGEOBJ_IMAGE]):
             pos = obj.get_pos()
             cropbox = BoundingBox.from_tuple(
@@ -210,7 +210,7 @@ class PyPdfiumPageBackend(PdfPageBackend):
                 l=0, r=0, t=0, b=0, coord_origin=CoordOrigin.BOTTOMLEFT
             )
         else:
-            padbox = cropbox.to_bottom_left_origin(page_size.height)
+            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
 

{docling-2.15.0 → docling-2.16.0}/docling/datamodel/base_models.py

@@ -4,6 +4,7 @@ from typing import TYPE_CHECKING, Dict, List, Optional, Union
 from docling_core.types.doc import (
     BoundingBox,
     DocItemLabel,
+    NodeItem,
     PictureDataType,
     Size,
     TableCell,
@@ -40,6 +41,7 @@ class InputFormat(str, Enum):
     MD = "md"
     XLSX = "xlsx"
     XML_USPTO = "xml_uspto"
+    JSON_DOCLING = "json_docling"
 
 
 class OutputFormat(str, Enum):
@@ -61,6 +63,7 @@ FormatToExtensions: Dict[InputFormat, List[str]] = {
     InputFormat.ASCIIDOC: ["adoc", "asciidoc", "asc"],
     InputFormat.XLSX: ["xlsx"],
     InputFormat.XML_USPTO: ["xml", "txt"],
+    InputFormat.JSON_DOCLING: ["json"],
 }
 
 FormatToMimeType: Dict[InputFormat, List[str]] = {
@@ -89,6 +92,7 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
         "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
     ],
     InputFormat.XML_USPTO: ["application/xml", "text/plain"],
+    InputFormat.JSON_DOCLING: ["application/json"],
 }
 
 MimeTypeToFormat: dict[str, list[InputFormat]] = {
@@ -201,6 +205,13 @@ class AssembledUnit(BaseModel):
     headers: List[PageElement] = []
 
 
+class ItemAndImageEnrichmentElement(BaseModel):
+    model_config = ConfigDict(arbitrary_types_allowed=True)
+
+    item: NodeItem
+    image: Image
+
+
 class Page(BaseModel):
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
@@ -219,12 +230,28 @@ class Page(BaseModel):
         {}
     )  # Cache of images in different scales. By default it is cleared during assembling.
 
-    def get_image(self, scale: float = 1.0) -> Optional[Image]:
+    def get_image(
+        self, scale: float = 1.0, cropbox: Optional[BoundingBox] = None
+    ) -> Optional[Image]:
         if self._backend is None:
             return self._image_cache.get(scale, None)
+
         if not scale in self._image_cache:
-            self._image_cache[scale] = self._backend.get_page_image(scale=scale)
-        return self._image_cache[scale]
+            if cropbox is None:
+                self._image_cache[scale] = self._backend.get_page_image(scale=scale)
+            else:
+                return self._backend.get_page_image(scale=scale, cropbox=cropbox)
+
+        if cropbox is None:
+            return self._image_cache[scale]
+        else:
+            page_im = self._image_cache[scale]
+            assert self.size is not None
+            return page_im.crop(
+                cropbox.to_top_left_origin(page_height=self.size.height)
+                .scaled(scale=scale)
+                .as_tuple()
+            )
 
     @property
     def image(self) -> Optional[Image]:

{docling-2.15.0 → docling-2.16.0}/docling/datamodel/document.py

@@ -350,6 +350,8 @@ class _DocumentConversionInput(BaseModel):
             mime = FormatToMimeType[InputFormat.HTML][0]
         elif ext in FormatToExtensions[InputFormat.MD]:
             mime = FormatToMimeType[InputFormat.MD][0]
+        elif ext in FormatToExtensions[InputFormat.JSON_DOCLING]:
+            mime = FormatToMimeType[InputFormat.JSON_DOCLING][0]
         return mime
 
     @staticmethod

{docling-2.15.0 → docling-2.16.0}/docling/datamodel/pipeline_options.py

@@ -1,17 +1,11 @@
 import logging
 import os
-import warnings
 from enum import Enum
 from pathlib import Path
-from typing import Annotated, Any, Dict, List, Literal, Optional, Tuple, Type, Union
+from typing import Any, List, Literal, Optional, Union
 
-from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
-from pydantic_settings import (
-    BaseSettings,
-    PydanticBaseSettingsSource,
-    SettingsConfigDict,
-)
-from typing_extensions import deprecated
+from pydantic import BaseModel, ConfigDict, Field, model_validator
+from pydantic_settings import BaseSettings, SettingsConfigDict
 
 _log = logging.getLogger(__name__)
 
@@ -139,7 +133,7 @@ class EasyOcrOptions(OcrOptions):
 
     use_gpu: Optional[bool] = None
 
-    confidence_threshold: float = 0.65
+    confidence_threshold: float = 0.5
 
     model_storage_directory: Optional[str] = None
     recog_network: Optional[str] = "standard"
@@ -225,6 +219,9 @@ class PdfPipelineOptions(PipelineOptions):
     artifacts_path: Optional[Union[Path, str]] = None
     do_table_structure: bool = True  # True: perform table structure extraction
     do_ocr: bool = True  # True: perform OCR, replace programmatic PDF text
+    do_code_enrichment: bool = False  # True: perform code OCR
+    do_formula_enrichment: bool = False  # True: perform formula OCR, return Latex code
+    do_picture_classification: bool = False  # True: classify pictures in documents
 
     table_structure_options: TableStructureOptions = TableStructureOptions()
     ocr_options: Union[