docling 2.18.0__py3-none-any.whl → 2.19.0__py3-none-any.whl

docling/backend/md_backend.py

@@ -36,7 +36,7 @@ _STOP_MARKER = f"#_#_{_MARKER_BODY}_STOP_#_#"
 
 
 class MarkdownDocumentBackend(DeclarativeDocumentBackend):
-    def shorten_underscore_sequences(self, markdown_text: str, max_length: int = 10):
+    def _shorten_underscore_sequences(self, markdown_text: str, max_length: int = 10):
         # This regex will match any sequence of underscores
         pattern = r"_+"
 
@@ -81,7 +81,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                 # very long sequences of underscores will lead to unnecessary long processing times.
                 # In any proper Markdown files, underscores have to be escaped,
                 # otherwise they represent emphasis (bold or italic)
-                self.markdown = self.shorten_underscore_sequences(text_stream)
+                self.markdown = self._shorten_underscore_sequences(text_stream)
             if isinstance(self.path_or_stream, Path):
                 with open(self.path_or_stream, "r", encoding="utf-8") as f:
                     md_content = f.read()
@@ -89,7 +89,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                     # very long sequences of underscores will lead to unnecessary long processing times.
                     # In any proper Markdown files, underscores have to be escaped,
                     # otherwise they represent emphasis (bold or italic)
-                    self.markdown = self.shorten_underscore_sequences(md_content)
+                    self.markdown = self._shorten_underscore_sequences(md_content)
             self.valid = True
 
             _log.debug(self.markdown)
@@ -99,7 +99,7 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             ) from e
         return
 
-    def close_table(self, doc: DoclingDocument):
+    def _close_table(self, doc: DoclingDocument):
         if self.in_table:
             _log.debug("=== TABLE START ===")
             for md_table_row in self.md_table_buffer:
@@ -156,30 +156,35 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                 doc.add_table(data=table_data)
         return
 
-    def process_inline_text(
-        self, parent_element: Optional[NodeItem], doc: DoclingDocument
+    def _process_inline_text(
+        self, parent_item: Optional[NodeItem], doc: DoclingDocument
     ):
         txt = " ".join(self.inline_texts)
         if len(txt) > 0:
             doc.add_text(
                 label=DocItemLabel.PARAGRAPH,
-                parent=parent_element,
+                parent=parent_item,
                 text=txt,
             )
         self.inline_texts = []
 
-    def iterate_elements(
+    def _iterate_elements(
         self,
         element: marko.element.Element,
         depth: int,
         doc: DoclingDocument,
-        parent_element: Optional[NodeItem] = None,
+        visited: Set[marko.element.Element],
+        parent_item: Optional[NodeItem] = None,
     ):
+
+        if element in visited:
+            return
+
         # Iterates over all elements in the AST
         # Check for different element types and process relevant details
         if isinstance(element, marko.block.Heading) and len(element.children) > 0:
-            self.close_table(doc)
-            self.process_inline_text(parent_element, doc)
+            self._close_table(doc)
+            self._process_inline_text(parent_item, doc)
             _log.debug(
                 f" - Heading level {element.level}, content: {element.children[0].children}"  # type: ignore
             )
@@ -207,8 +212,8 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             traverse(element)
             snippet_text = "".join(strings)
             if len(snippet_text) > 0:
-                parent_element = doc.add_text(
-                    label=doc_label, parent=parent_element, text=snippet_text
+                parent_item = doc.add_text(
+                    label=doc_label, parent=parent_item, text=snippet_text
                 )
 
         elif isinstance(element, marko.block.List):
@@ -218,35 +223,37 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                     has_non_empty_list_items = True
                     break
 
-            self.close_table(doc)
-            self.process_inline_text(parent_element, doc)
+            self._close_table(doc)
+            self._process_inline_text(parent_item, doc)
             _log.debug(f" - List {'ordered' if element.ordered else 'unordered'}")
             if has_non_empty_list_items:
                 label = GroupLabel.ORDERED_LIST if element.ordered else GroupLabel.LIST
-                parent_element = doc.add_group(
-                    label=label, name=f"list", parent=parent_element
+                parent_item = doc.add_group(
+                    label=label, name=f"list", parent=parent_item
                 )
 
         elif isinstance(element, marko.block.ListItem) and len(element.children) > 0:
-            self.close_table(doc)
-            self.process_inline_text(parent_element, doc)
+            self._close_table(doc)
+            self._process_inline_text(parent_item, doc)
             _log.debug(" - List item")
 
-            snippet_text = str(element.children[0].children[0].children)  # type: ignore
+            first_child = element.children[0]
+            snippet_text = str(first_child.children[0].children)  # type: ignore
             is_numbered = False
             if (
-                parent_element is not None
-                and isinstance(parent_element, DocItem)
-                and parent_element.label == GroupLabel.ORDERED_LIST
+                parent_item is not None
+                and isinstance(parent_item, DocItem)
+                and parent_item.label == GroupLabel.ORDERED_LIST
             ):
                 is_numbered = True
             doc.add_list_item(
-                enumerated=is_numbered, parent=parent_element, text=snippet_text
+                enumerated=is_numbered, parent=parent_item, text=snippet_text
             )
+            visited.add(first_child)
 
         elif isinstance(element, marko.inline.Image):
-            self.close_table(doc)
-            self.process_inline_text(parent_element, doc)
+            self._close_table(doc)
+            self._process_inline_text(parent_item, doc)
             _log.debug(f" - Image with alt: {element.title}, url: {element.dest}")
 
             fig_caption: Optional[TextItem] = None
@@ -255,10 +262,10 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                     label=DocItemLabel.CAPTION, text=element.title
                 )
 
-            doc.add_picture(parent=parent_element, caption=fig_caption)
+            doc.add_picture(parent=parent_item, caption=fig_caption)
 
         elif isinstance(element, marko.block.Paragraph) and len(element.children) > 0:
-            self.process_inline_text(parent_element, doc)
+            self._process_inline_text(parent_item, doc)
 
         elif isinstance(element, marko.inline.RawText):
             _log.debug(f" - Paragraph (raw text): {element.children}")
@@ -272,17 +279,16 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
                 else:
                     self.md_table_buffer.append(snippet_text)
             else:
-                self.close_table(doc)
-                self.in_table = False
+                self._close_table(doc)
                 # most likely just inline text
                 self.inline_texts.append(str(element.children))
 
         elif isinstance(element, marko.inline.CodeSpan):
-            self.close_table(doc)
-            self.process_inline_text(parent_element, doc)
+            self._close_table(doc)
+            self._process_inline_text(parent_item, doc)
             _log.debug(f" - Code Span: {element.children}")
             snippet_text = str(element.children).strip()
-            doc.add_code(parent=parent_element, text=snippet_text)
+            doc.add_code(parent=parent_item, text=snippet_text)
 
         elif (
             isinstance(element, (marko.block.CodeBlock, marko.block.FencedCode))
@@ -290,10 +296,10 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             and isinstance((first_child := element.children[0]), marko.inline.RawText)
             and len(snippet_text := (first_child.children.strip())) > 0
         ):
-            self.close_table(doc)
-            self.process_inline_text(parent_element, doc)
+            self._close_table(doc)
+            self._process_inline_text(parent_item, doc)
             _log.debug(f" - Code Block: {element.children}")
-            doc.add_code(parent=parent_element, text=snippet_text)
+            doc.add_code(parent=parent_item, text=snippet_text)
 
         elif isinstance(element, marko.inline.LineBreak):
             if self.in_table:
@@ -302,8 +308,8 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
 
         elif isinstance(element, marko.block.HTMLBlock):
             self._html_blocks += 1
-            self.process_inline_text(parent_element, doc)
-            self.close_table(doc)
+            self._process_inline_text(parent_item, doc)
+            self._close_table(doc)
             _log.debug("HTML Block: {}".format(element))
             if (
                 len(element.body) > 0
@@ -312,18 +318,16 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
 
                 # wrap in markers to enable post-processing in convert()
                 text_to_add = f"{_START_MARKER}{html_block}{_STOP_MARKER}"
-                doc.add_code(parent=parent_element, text=text_to_add)
+                doc.add_code(parent=parent_item, text=text_to_add)
         else:
             if not isinstance(element, str):
-                self.close_table(doc)
+                self._close_table(doc)
                 _log.debug("Some other element: {}".format(element))
 
         processed_block_types = (
-            marko.block.ListItem,
             marko.block.Heading,
             marko.block.CodeBlock,
             marko.block.FencedCode,
-            # marko.block.Paragraph,
             marko.inline.RawText,
         )
 
@@ -332,7 +336,13 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             element, processed_block_types
         ):
             for child in element.children:
-                self.iterate_elements(child, depth + 1, doc, parent_element)
+                self._iterate_elements(
+                    element=child,
+                    depth=depth + 1,
+                    doc=doc,
+                    visited=visited,
+                    parent_item=parent_item,
+                )
 
     def is_valid(self) -> bool:
         return self.valid
@@ -366,9 +376,15 @@ class MarkdownDocumentBackend(DeclarativeDocumentBackend):
             marko_parser = Markdown()
             parsed_ast = marko_parser.parse(self.markdown)
             # Start iterating from the root of the AST
-            self.iterate_elements(parsed_ast, 0, doc, None)
-            self.process_inline_text(None, doc)  # handle last hanging inline text
-            self.close_table(doc=doc)  # handle any last hanging table
+            self._iterate_elements(
+                element=parsed_ast,
+                depth=0,
+                doc=doc,
+                parent_item=None,
+                visited=set(),
+            )
+            self._process_inline_text(None, doc)  # handle last hanging inline text
+            self._close_table(doc=doc)  # handle any last hanging table
 
             # if HTML blocks were detected, export to HTML and delegate to HTML backend
             if self._html_blocks > 0:

docling/backend/msword_backend.py

@@ -242,7 +242,7 @@ class MsWordDocumentBackend(DeclarativeDocumentBackend):
             parts = label.split(":")
 
             if len(parts) == 2:
-                return parts[0], int(parts[1])
+                return parts[0], self.str_to_int(parts[1], None)
 
         parts = self.split_text_and_number(label)
 

docling/cli/main.py

@@ -219,6 +219,13 @@ def convert(
         bool,
         typer.Option(..., help="Enable the formula enrichment model in the pipeline."),
     ] = False,
+    enrich_picture_classes: Annotated[
+        bool,
+        typer.Option(
+            ...,
+            help="Enable the picture classification enrichment model in the pipeline.",
+        ),
+    ] = False,
     artifacts_path: Annotated[
         Optional[Path],
         typer.Option(..., help="If provided, the location of the model artifacts."),
@@ -375,6 +382,7 @@ def convert(
             do_table_structure=True,
             do_code_enrichment=enrich_code,
             do_formula_enrichment=enrich_formula,
+            do_picture_classification=enrich_picture_classes,
             document_timeout=document_timeout,
         )
         pipeline_options.table_structure_options.do_cell_matching = (

docling/cli/models.py

@@ -0,0 +1,105 @@
+import logging
+import warnings
+from enum import Enum
+from pathlib import Path
+from typing import Annotated, Optional
+
+import typer
+from rich.console import Console
+from rich.logging import RichHandler
+
+from docling.datamodel.settings import settings
+from docling.utils.model_downloader import download_models
+
+warnings.filterwarnings(action="ignore", category=UserWarning, module="pydantic|torch")
+warnings.filterwarnings(action="ignore", category=FutureWarning, module="easyocr")
+
+console = Console()
+err_console = Console(stderr=True)
+
+
+app = typer.Typer(
+    name="Docling models helper",
+    no_args_is_help=True,
+    add_completion=False,
+    pretty_exceptions_enable=False,
+)
+
+
+class _AvailableModels(str, Enum):
+    LAYOUT = "layout"
+    TABLEFORMER = "tableformer"
+    CODE_FORMULA = "code_formula"
+    PICTURE_CLASSIFIER = "picture_classifier"
+    EASYOCR = "easyocr"
+
+
+@app.command("download")
+def download(
+    output_dir: Annotated[
+        Path,
+        typer.Option(
+            ...,
+            "-o",
+            "--output-dir",
+            help="The directory where all the models are downloaded.",
+        ),
+    ] = (settings.cache_dir / "models"),
+    force: Annotated[
+        bool, typer.Option(..., help="If true, the download will be forced")
+    ] = False,
+    models: Annotated[
+        Optional[list[_AvailableModels]],
+        typer.Argument(
+            help=f"Models to download (default behavior: all will be downloaded)",
+        ),
+    ] = None,
+    quiet: Annotated[
+        bool,
+        typer.Option(
+            ...,
+            "-q",
+            "--quiet",
+            help="No extra output is generated, the CLI prints only the directory with the cached models.",
+        ),
+    ] = False,
+):
+    if not quiet:
+        FORMAT = "%(message)s"
+        logging.basicConfig(
+            level=logging.INFO,
+            format="[blue]%(message)s[/blue]",
+            datefmt="[%X]",
+            handlers=[RichHandler(show_level=False, show_time=False, markup=True)],
+        )
+    to_download = models or [m for m in _AvailableModels]
+    output_dir = download_models(
+        output_dir=output_dir,
+        force=force,
+        progress=(not quiet),
+        with_layout=_AvailableModels.LAYOUT in to_download,
+        with_tableformer=_AvailableModels.TABLEFORMER in to_download,
+        with_code_formula=_AvailableModels.CODE_FORMULA in to_download,
+        with_picture_classifier=_AvailableModels.PICTURE_CLASSIFIER in to_download,
+        with_easyocr=_AvailableModels.EASYOCR in to_download,
+    )
+
+    if quiet:
+        typer.echo(output_dir)
+    else:
+        typer.secho(f"\nModels downloaded into: {output_dir}.", fg="green")
+
+        console.print(
+            "\n",
+            "Docling can now be configured for running offline using the local artifacts.\n\n",
+            "Using the CLI:",
+            f"`docling --artifacts-path={output_dir} FILE`",
+            "\n",
+            "Using Python: see the documentation at <https://ds4sd.github.io/docling/usage>.",
+        )
+
+
+click_app = typer.main.get_command(app)
+
+if __name__ == "__main__":
+    app()

docling/cli/tools.py

@@ -0,0 +1,17 @@
+import typer
+
+from docling.cli.models import app as models_app
+
+app = typer.Typer(
+    name="Docling helpers",
+    no_args_is_help=True,
+    add_completion=False,
+    pretty_exceptions_enable=False,
+)
+
+app.add_typer(models_app, name="models")
+
+click_app = typer.main.get_command(app)
+
+if __name__ == "__main__":
+    app()

docling/datamodel/settings.py

@@ -61,5 +61,7 @@ class AppSettings(BaseSettings):
     perf: BatchConcurrencySettings
     debug: DebugSettings
 
+    cache_dir: Path = Path.home() / ".cache" / "docling"
+
 
 settings = AppSettings(perf=BatchConcurrencySettings(), debug=DebugSettings())

docling/models/base_model.py

@@ -6,6 +6,7 @@ from typing_extensions import TypeVar
 
 from docling.datamodel.base_models import ItemAndImageEnrichmentElement, Page
 from docling.datamodel.document import ConversionResult
+from docling.datamodel.settings import settings
 
 
 class BasePageModel(ABC):
@@ -21,6 +22,8 @@ EnrichElementT = TypeVar("EnrichElementT", default=NodeItem)
 
 class GenericEnrichmentModel(ABC, Generic[EnrichElementT]):
 
+    elements_batch_size: int = settings.perf.elements_batch_size
+
     @abstractmethod
     def is_processable(self, doc: DoclingDocument, element: NodeItem) -> bool:
         pass

docling/models/code_formula_model.py

@@ -2,6 +2,7 @@ import re
 from pathlib import Path
 from typing import Iterable, List, Literal, Optional, Tuple, Union
 
+import numpy as np
 from docling_core.types.doc import (
     CodeItem,
     DocItemLabel,
@@ -61,13 +62,15 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
         Processes the given batch of elements and enriches them with predictions.
     """
 
+    _model_repo_folder = "ds4sd--CodeFormula"
+    elements_batch_size = 5
     images_scale = 1.66  # = 120 dpi, aligned with training data resolution
     expansion_factor = 0.03
 
     def __init__(
         self,
         enabled: bool,
-        artifacts_path: Optional[Union[Path, str]],
+        artifacts_path: Optional[Path],
         options: CodeFormulaModelOptions,
         accelerator_options: AcceleratorOptions,
     ):
@@ -96,29 +99,32 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
             )
 
             if artifacts_path is None:
-                artifacts_path = self.download_models_hf()
+                artifacts_path = self.download_models()
             else:
-                artifacts_path = Path(artifacts_path)
+                artifacts_path = artifacts_path / self._model_repo_folder
 
             self.code_formula_model = CodeFormulaPredictor(
-                artifacts_path=artifacts_path,
+                artifacts_path=str(artifacts_path),
                 device=device,
                 num_threads=accelerator_options.num_threads,
             )
 
     @staticmethod
-    def download_models_hf(
-        local_dir: Optional[Path] = None, force: bool = False
+    def download_models(
+        local_dir: Optional[Path] = None,
+        force: bool = False,
+        progress: bool = False,
     ) -> Path:
         from huggingface_hub import snapshot_download
         from huggingface_hub.utils import disable_progress_bars
 
-        disable_progress_bars()
+        if not progress:
+            disable_progress_bars()
         download_path = snapshot_download(
             repo_id="ds4sd/CodeFormula",
             force_download=force,
             local_dir=local_dir,
-            revision="v1.0.0",
+            revision="v1.0.1",
         )
 
         return Path(download_path)
@@ -226,7 +232,7 @@ class CodeFormulaModel(BaseItemAndImageEnrichmentModel):
             return
 
         labels: List[str] = []
-        images: List[Image.Image] = []
+        images: List[Union[Image.Image, np.ndarray]] = []
         elements: List[TextItem] = []
         for el in element_batch:
             assert isinstance(el.item, TextItem)

docling/models/document_picture_classifier.py

@@ -1,6 +1,7 @@
 from pathlib import Path
 from typing import Iterable, List, Literal, Optional, Tuple, Union
 
+import numpy as np
 from docling_core.types.doc import (
     DoclingDocument,
     NodeItem,
@@ -55,12 +56,13 @@ class DocumentPictureClassifier(BaseEnrichmentModel):
         Processes a batch of elements and adds classification annotations.
     """
 
+    _model_repo_folder = "ds4sd--DocumentFigureClassifier"
     images_scale = 2
 
     def __init__(
         self,
         enabled: bool,
-        artifacts_path: Optional[Union[Path, str]],
+        artifacts_path: Optional[Path],
         options: DocumentPictureClassifierOptions,
         accelerator_options: AcceleratorOptions,
     ):
@@ -88,24 +90,25 @@ class DocumentPictureClassifier(BaseEnrichmentModel):
             )
 
             if artifacts_path is None:
-                artifacts_path = self.download_models_hf()
+                artifacts_path = self.download_models()
             else:
-                artifacts_path = Path(artifacts_path)
+                artifacts_path = artifacts_path / self._model_repo_folder
 
             self.document_picture_classifier = DocumentFigureClassifierPredictor(
-                artifacts_path=artifacts_path,
+                artifacts_path=str(artifacts_path),
                 device=device,
                 num_threads=accelerator_options.num_threads,
             )
 
     @staticmethod
-    def download_models_hf(
-        local_dir: Optional[Path] = None, force: bool = False
+    def download_models(
+        local_dir: Optional[Path] = None, force: bool = False, progress: bool = False
     ) -> Path:
         from huggingface_hub import snapshot_download
         from huggingface_hub.utils import disable_progress_bars
 
-        disable_progress_bars()
+        if not progress:
+            disable_progress_bars()
         download_path = snapshot_download(
             repo_id="ds4sd/DocumentFigureClassifier",
             force_download=force,
@@ -159,7 +162,7 @@ class DocumentPictureClassifier(BaseEnrichmentModel):
                 yield element
             return
 
-        images: List[Image.Image] = []
+        images: List[Union[Image.Image, np.ndarray]] = []
         elements: List[PictureItem] = []
         for el in element_batch:
             assert isinstance(el, PictureItem)

docling/models/easyocr_model.py

@@ -1,7 +1,10 @@
 import logging
 import warnings
-from typing import Iterable
+import zipfile
+from pathlib import Path
+from typing import Iterable, List, Optional
 
+import httpx
 import numpy
 import torch
 from docling_core.types.doc import BoundingBox, CoordOrigin
@@ -17,14 +20,18 @@ from docling.datamodel.settings import settings
 from docling.models.base_ocr_model import BaseOcrModel
 from docling.utils.accelerator_utils import decide_device
 from docling.utils.profiling import TimeRecorder
+from docling.utils.utils import download_url_with_progress
 
 _log = logging.getLogger(__name__)
 
 
 class EasyOcrModel(BaseOcrModel):
+    _model_repo_folder = "EasyOcr"
+
     def __init__(
         self,
         enabled: bool,
+        artifacts_path: Optional[Path],
         options: EasyOcrOptions,
         accelerator_options: AcceleratorOptions,
     ):
@@ -62,15 +69,55 @@ class EasyOcrModel(BaseOcrModel):
                 )
                 use_gpu = self.options.use_gpu
 
+            download_enabled = self.options.download_enabled
+            model_storage_directory = self.options.model_storage_directory
+            if artifacts_path is not None and model_storage_directory is None:
+                download_enabled = False
+                model_storage_directory = str(artifacts_path / self._model_repo_folder)
+
             self.reader = easyocr.Reader(
                 lang_list=self.options.lang,
                 gpu=use_gpu,
-                model_storage_directory=self.options.model_storage_directory,
+                model_storage_directory=model_storage_directory,
                 recog_network=self.options.recog_network,
-                download_enabled=self.options.download_enabled,
+                download_enabled=download_enabled,
                 verbose=False,
             )
 
+    @staticmethod
+    def download_models(
+        detection_models: List[str] = ["craft"],
+        recognition_models: List[str] = ["english_g2", "latin_g2"],
+        local_dir: Optional[Path] = None,
+        force: bool = False,
+        progress: bool = False,
+    ) -> Path:
+        # Models are located in https://github.com/JaidedAI/EasyOCR/blob/master/easyocr/config.py
+        from easyocr.config import detection_models as det_models_dict
+        from easyocr.config import recognition_models as rec_models_dict
+
+        if local_dir is None:
+            local_dir = settings.cache_dir / "models" / EasyOcrModel._model_repo_folder
+
+        local_dir.mkdir(parents=True, exist_ok=True)
+
+        # Collect models to download
+        download_list = []
+        for model_name in detection_models:
+            if model_name in det_models_dict:
+                download_list.append(det_models_dict[model_name])
+        for model_name in recognition_models:
+            if model_name in rec_models_dict["gen2"]:
+                download_list.append(rec_models_dict["gen2"][model_name])
+
+        # Download models
+        for model_details in download_list:
+            buf = download_url_with_progress(model_details["url"], progress=progress)
+            with zipfile.ZipFile(buf, "r") as zip_ref:
+                zip_ref.extractall(local_dir)
+
+        return local_dir
+
     def __call__(
         self, conv_res: ConversionResult, page_batch: Iterable[Page]
     ) -> Iterable[Page]:

docling/models/layout_model.py

@@ -1,7 +1,8 @@
 import copy
 import logging
+import warnings
 from pathlib import Path
-from typing import Iterable
+from typing import Iterable, Optional, Union
 
 from docling_core.types.doc import DocItemLabel
 from docling_ibm_models.layoutmodel.layout_predictor import LayoutPredictor
@@ -21,6 +22,8 @@ _log = logging.getLogger(__name__)
 
 
 class LayoutModel(BasePageModel):
+    _model_repo_folder = "ds4sd--docling-models"
+    _model_path = "model_artifacts/layout"
 
     TEXT_ELEM_LABELS = [
         DocItemLabel.TEXT,
@@ -42,15 +45,56 @@ class LayoutModel(BasePageModel):
     FORMULA_LABEL = DocItemLabel.FORMULA
     CONTAINER_LABELS = [DocItemLabel.FORM, DocItemLabel.KEY_VALUE_REGION]
 
-    def __init__(self, artifacts_path: Path, accelerator_options: AcceleratorOptions):
+    def __init__(
+        self, artifacts_path: Optional[Path], accelerator_options: AcceleratorOptions
+    ):
         device = decide_device(accelerator_options.device)
 
+        if artifacts_path is None:
+            artifacts_path = self.download_models() / self._model_path
+        else:
+            # will become the default in the future
+            if (artifacts_path / self._model_repo_folder).exists():
+                artifacts_path = (
+                    artifacts_path / self._model_repo_folder / self._model_path
+                )
+            elif (artifacts_path / self._model_path).exists():
+                warnings.warn(
+                    "The usage of artifacts_path containing directly "
+                    f"{self._model_path} is deprecated. Please point "
+                    "the artifacts_path to the parent containing "
+                    f"the {self._model_repo_folder} folder.",
+                    DeprecationWarning,
+                    stacklevel=3,
+                )
+                artifacts_path = artifacts_path / self._model_path
+
         self.layout_predictor = LayoutPredictor(
             artifact_path=str(artifacts_path),
             device=device,
             num_threads=accelerator_options.num_threads,
         )
 
+    @staticmethod
+    def download_models(
+        local_dir: Optional[Path] = None,
+        force: bool = False,
+        progress: bool = False,
+    ) -> Path:
+        from huggingface_hub import snapshot_download
+        from huggingface_hub.utils import disable_progress_bars
+
+        if not progress:
+            disable_progress_bars()
+        download_path = snapshot_download(
+            repo_id="ds4sd/docling-models",
+            force_download=force,
+            local_dir=local_dir,
+            revision="v2.1.0",
+        )
+
+        return Path(download_path)
+
     def draw_clusters_and_cells_side_by_side(
         self, conv_res, page, clusters, mode_prefix: str, show: bool = False
     ):
@@ -106,10 +150,12 @@ class LayoutModel(BasePageModel):
             else:
                 with TimeRecorder(conv_res, "layout"):
                     assert page.size is not None
+                    page_image = page.get_image(scale=1.0)
+                    assert page_image is not None
 
                     clusters = []
                     for ix, pred_item in enumerate(
-                        self.layout_predictor.predict(page.get_image(scale=1.0))
+                        self.layout_predictor.predict(page_image)
                     ):
                         label = DocItemLabel(
                             pred_item["label"]

docling/models/table_structure_model.py

@@ -1,6 +1,7 @@
 import copy
+import warnings
 from pathlib import Path
-from typing import Iterable
+from typing import Iterable, Optional, Union
 
 import numpy
 from docling_core.types.doc import BoundingBox, DocItemLabel, TableCell
@@ -22,10 +23,13 @@ from docling.utils.profiling import TimeRecorder
 
 
 class TableStructureModel(BasePageModel):
+    _model_repo_folder = "ds4sd--docling-models"
+    _model_path = "model_artifacts/tableformer"
+
     def __init__(
         self,
         enabled: bool,
-        artifacts_path: Path,
+        artifacts_path: Optional[Path],
         options: TableStructureOptions,
         accelerator_options: AcceleratorOptions,
     ):
@@ -35,6 +39,26 @@ class TableStructureModel(BasePageModel):
 
         self.enabled = enabled
         if self.enabled:
+
+            if artifacts_path is None:
+                artifacts_path = self.download_models() / self._model_path
+            else:
+                # will become the default in the future
+                if (artifacts_path / self._model_repo_folder).exists():
+                    artifacts_path = (
+                        artifacts_path / self._model_repo_folder / self._model_path
+                    )
+                elif (artifacts_path / self._model_path).exists():
+                    warnings.warn(
+                        "The usage of artifacts_path containing directly "
+                        f"{self._model_path} is deprecated. Please point "
+                        "the artifacts_path to the parent containing "
+                        f"the {self._model_repo_folder} folder.",
+                        DeprecationWarning,
+                        stacklevel=3,
+                    )
+                    artifacts_path = artifacts_path / self._model_path
+
             if self.mode == TableFormerMode.ACCURATE:
                 artifacts_path = artifacts_path / "accurate"
             else:
@@ -58,6 +82,24 @@ class TableStructureModel(BasePageModel):
             )
             self.scale = 2.0  # Scale up table input images to 144 dpi
 
+    @staticmethod
+    def download_models(
+        local_dir: Optional[Path] = None, force: bool = False, progress: bool = False
+    ) -> Path:
+        from huggingface_hub import snapshot_download
+        from huggingface_hub.utils import disable_progress_bars
+
+        if not progress:
+            disable_progress_bars()
+        download_path = snapshot_download(
+            repo_id="ds4sd/docling-models",
+            force_download=force,
+            local_dir=local_dir,
+            revision="v2.1.0",
+        )
+
+        return Path(download_path)
+
     def draw_table_and_cells(
         self,
         conv_res: ConversionResult,

docling/pipeline/base_pipeline.py

@@ -79,7 +79,7 @@ class BasePipeline(ABC):
             for model in self.enrichment_pipe:
                 for element_batch in chunkify(
                     _prepare_elements(conv_res, model),
-                    settings.perf.elements_batch_size,
+                    model.elements_batch_size,
                 ):
                     for element in model(
                         doc=conv_res.document, element_batch=element_batch

docling/pipeline/standard_pdf_pipeline.py

@@ -1,5 +1,6 @@
 import logging
 import sys
+import warnings
 from pathlib import Path
 from typing import Optional
 
@@ -17,6 +18,7 @@ from docling.datamodel.pipeline_options import (
     TesseractCliOcrOptions,
     TesseractOcrOptions,
 )
+from docling.datamodel.settings import settings
 from docling.models.base_ocr_model import BaseOcrModel
 from docling.models.code_formula_model import CodeFormulaModel, CodeFormulaModelOptions
 from docling.models.document_picture_classifier import (
@@ -37,23 +39,23 @@ from docling.models.table_structure_model import TableStructureModel
 from docling.models.tesseract_ocr_cli_model import TesseractOcrCliModel
 from docling.models.tesseract_ocr_model import TesseractOcrModel
 from docling.pipeline.base_pipeline import PaginatedPipeline
+from docling.utils.model_downloader import download_models
 from docling.utils.profiling import ProfilingScope, TimeRecorder
 
 _log = logging.getLogger(__name__)
 
 
 class StandardPdfPipeline(PaginatedPipeline):
-    _layout_model_path = "model_artifacts/layout"
-    _table_model_path = "model_artifacts/tableformer"
+    _layout_model_path = LayoutModel._model_path
+    _table_model_path = TableStructureModel._model_path
 
     def __init__(self, pipeline_options: PdfPipelineOptions):
         super().__init__(pipeline_options)
         self.pipeline_options: PdfPipelineOptions
 
-        if pipeline_options.artifacts_path is None:
-            self.artifacts_path = self.download_models_hf()
-        else:
-            self.artifacts_path = Path(pipeline_options.artifacts_path)
+        artifacts_path: Optional[Path] = None
+        if pipeline_options.artifacts_path is not None:
+            artifacts_path = Path(pipeline_options.artifacts_path).expanduser()
 
         self.keep_images = (
             self.pipeline_options.generate_page_images
@@ -63,7 +65,7 @@ class StandardPdfPipeline(PaginatedPipeline):
 
         self.glm_model = GlmModel(options=GlmOptions())
 
-        if (ocr_model := self.get_ocr_model()) is None:
+        if (ocr_model := self.get_ocr_model(artifacts_path=artifacts_path)) is None:
             raise RuntimeError(
                 f"The specified OCR kind is not supported: {pipeline_options.ocr_options.kind}."
             )
@@ -79,15 +81,13 @@ class StandardPdfPipeline(PaginatedPipeline):
             ocr_model,
             # Layout model
             LayoutModel(
-                artifacts_path=self.artifacts_path
-                / StandardPdfPipeline._layout_model_path,
+                artifacts_path=artifacts_path,
                 accelerator_options=pipeline_options.accelerator_options,
             ),
             # Table structure model
             TableStructureModel(
                 enabled=pipeline_options.do_table_structure,
-                artifacts_path=self.artifacts_path
-                / StandardPdfPipeline._table_model_path,
+                artifacts_path=artifacts_path,
                 options=pipeline_options.table_structure_options,
                 accelerator_options=pipeline_options.accelerator_options,
             ),
@@ -101,7 +101,7 @@ class StandardPdfPipeline(PaginatedPipeline):
             CodeFormulaModel(
                 enabled=pipeline_options.do_code_enrichment
                 or pipeline_options.do_formula_enrichment,
-                artifacts_path=pipeline_options.artifacts_path,
+                artifacts_path=artifacts_path,
                 options=CodeFormulaModelOptions(
                     do_code_enrichment=pipeline_options.do_code_enrichment,
                     do_formula_enrichment=pipeline_options.do_formula_enrichment,
@@ -111,7 +111,7 @@ class StandardPdfPipeline(PaginatedPipeline):
             # Document Picture Classifier
             DocumentPictureClassifier(
                 enabled=pipeline_options.do_picture_classification,
-                artifacts_path=pipeline_options.artifacts_path,
+                artifacts_path=artifacts_path,
                 options=DocumentPictureClassifierOptions(),
                 accelerator_options=pipeline_options.accelerator_options,
             ),
@@ -127,23 +127,24 @@ class StandardPdfPipeline(PaginatedPipeline):
     def download_models_hf(
         local_dir: Optional[Path] = None, force: bool = False
     ) -> Path:
-        from huggingface_hub import snapshot_download
-        from huggingface_hub.utils import disable_progress_bars
-
-        disable_progress_bars()
-        download_path = snapshot_download(
-            repo_id="ds4sd/docling-models",
-            force_download=force,
-            local_dir=local_dir,
-            revision="v2.1.0",
+        warnings.warn(
+            "The usage of StandardPdfPipeline.download_models_hf() is deprecated "
+            "use instead the utility `docling-tools models download`, or "
+            "the upstream method docling.utils.models_downloader.download_all()",
+            DeprecationWarning,
+            stacklevel=3,
         )
 
-        return Path(download_path)
+        output_dir = download_models(output_dir=local_dir, force=force, progress=False)
+        return output_dir
 
-    def get_ocr_model(self) -> Optional[BaseOcrModel]:
+    def get_ocr_model(
+        self, artifacts_path: Optional[Path] = None
+    ) -> Optional[BaseOcrModel]:
         if isinstance(self.pipeline_options.ocr_options, EasyOcrOptions):
             return EasyOcrModel(
                 enabled=self.pipeline_options.do_ocr,
+                artifacts_path=artifacts_path,
                 options=self.pipeline_options.ocr_options,
                 accelerator_options=self.pipeline_options.accelerator_options,
             )

docling/utils/model_downloader.py

@@ -0,0 +1,72 @@
+import logging
+from pathlib import Path
+from typing import Optional
+
+from docling.datamodel.settings import settings
+from docling.models.code_formula_model import CodeFormulaModel
+from docling.models.document_picture_classifier import DocumentPictureClassifier
+from docling.models.easyocr_model import EasyOcrModel
+from docling.models.layout_model import LayoutModel
+from docling.models.table_structure_model import TableStructureModel
+
+_log = logging.getLogger(__name__)
+
+
+def download_models(
+    output_dir: Optional[Path] = None,
+    *,
+    force: bool = False,
+    progress: bool = False,
+    with_layout: bool = True,
+    with_tableformer: bool = True,
+    with_code_formula: bool = True,
+    with_picture_classifier: bool = True,
+    with_easyocr: bool = True,
+):
+    if output_dir is None:
+        output_dir = settings.cache_dir / "models"
+
+    # Make sure the folder exists
+    output_dir.mkdir(exist_ok=True, parents=True)
+
+    if with_layout:
+        _log.info(f"Downloading layout model...")
+        LayoutModel.download_models(
+            local_dir=output_dir / LayoutModel._model_repo_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_tableformer:
+        _log.info(f"Downloading tableformer model...")
+        TableStructureModel.download_models(
+            local_dir=output_dir / TableStructureModel._model_repo_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_picture_classifier:
+        _log.info(f"Downloading picture classifier model...")
+        DocumentPictureClassifier.download_models(
+            local_dir=output_dir / DocumentPictureClassifier._model_repo_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_code_formula:
+        _log.info(f"Downloading code formula model...")
+        CodeFormulaModel.download_models(
+            local_dir=output_dir / CodeFormulaModel._model_repo_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_easyocr:
+        _log.info(f"Downloading easyocr models...")
+        EasyOcrModel.download_models(
+            local_dir=output_dir / EasyOcrModel._model_repo_folder,
+            force=force,
+            progress=progress,
+        )
+
+    return output_dir

docling/utils/utils.py

@@ -4,6 +4,9 @@ from itertools import islice
 from pathlib import Path
 from typing import List, Union
 
+import requests
+from tqdm import tqdm
+
 
 def chunkify(iterator, chunk_size):
     """Yield successive chunks of chunk_size from the iterable."""
@@ -39,3 +42,24 @@ def create_hash(string: str):
     hasher.update(string.encode("utf-8"))
 
     return hasher.hexdigest()
+
+
+def download_url_with_progress(url: str, progress: bool = False) -> BytesIO:
+    buf = BytesIO()
+    with requests.get(url, stream=True, allow_redirects=True) as response:
+        total_size = int(response.headers.get("content-length", 0))
+        progress_bar = tqdm(
+            total=total_size,
+            unit="B",
+            unit_scale=True,
+            unit_divisor=1024,
+            disable=(not progress),
+        )
+
+        for chunk in response.iter_content(10 * 1024):
+            buf.write(chunk)
+            progress_bar.update(len(chunk))
+        progress_bar.close()
+
+    buf.seek(0)
+    return buf

{docling-2.18.0.dist-info → docling-2.19.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.18.0
+Version: 2.19.0
 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
@@ -24,12 +24,12 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: ocrmac
 Provides-Extra: rapidocr
 Provides-Extra: tesserocr
-Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
+Requires-Dist: beautifulsoup4 (>=4.12.3,<4.13.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=1.0.0,<2.0.0)
-Requires-Dist: docling-core[chunking] (>=2.17.0,<3.0.0)
+Requires-Dist: docling-core[chunking] (>=2.17.2,<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: docling-parse (>=3.3.0,<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)
@@ -52,6 +52,7 @@ Requires-Dist: rtree (>=1.3.0,<2.0.0)
 Requires-Dist: scipy (>=1.6.0,<1.14.0) ; python_version < "3.10"
 Requires-Dist: scipy (>=1.6.0,<2.0.0) ; python_version >= "3.10"
 Requires-Dist: tesserocr (>=2.7.1,<3.0.0) ; extra == "tesserocr"
+Requires-Dist: tqdm (>=4.65.0,<5.0.0)
 Requires-Dist: typer (>=0.12.5,<0.13.0)
 Project-URL: Repository, https://github.com/DS4SD/docling
 Description-Content-Type: text/markdown

{docling-2.18.0.dist-info → docling-2.19.0.dist-info}/RECORD

@@ -7,10 +7,10 @@ docling/backend/docling_parse_v2_backend.py,sha256=IpwrBrtLGwNRl5AYO-o3NjEfNRsAk
 docling/backend/html_backend.py,sha256=YTPLZiEEEuGaP6G62skK3wXJ0KftuqBCl8erNXeJyoE,15893
 docling/backend/json/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/json/docling_json_backend.py,sha256=LlFMVoZrrCfVwbDuRbNN4Xg96Lujh4xxrTBt9jGhY9I,1984
-docling/backend/md_backend.py,sha256=d7XAFHzFO9qhrCJA3raWEmZ8WXSYyy3KOE57oMeqKGc,16502
+docling/backend/md_backend.py,sha256=NaVfcnEH-5bwVovjn76EobF6B6Wm8AhaTZ4E8k0TUPo,16826
 docling/backend/msexcel_backend.py,sha256=lyJc4ShJGAN2ZfNTTuhdYTF-44cZsGyn_8Djstp3IEU,12700
 docling/backend/mspowerpoint_backend.py,sha256=esAyaaQe17BQFweGAGJHvImKETefY0BpvfpUSECC49w,16424
-docling/backend/msword_backend.py,sha256=0iR1l3eLplPv3CPT7iGwQb50LIVf3C32KZFzwAkARrc,20573
+docling/backend/msword_backend.py,sha256=V4miLIcOH8DDlSCm25F_DALBW60Uf9JoSS0TB4yrQBw,20591
 docling/backend/pdf_backend.py,sha256=17Pr8dWsD1C4FYUprrwMM9trDGW-JYLjrcScx1Ul4io,2048
 docling/backend/pypdfium2_backend.py,sha256=QSPfp903ZtSpoNqPmcIek0HmvETrJ1kkwrdxnF5pjS0,9014
 docling/backend/xml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -18,45 +18,48 @@ docling/backend/xml/pubmed_backend.py,sha256=LMnpowjnxa5SydfNC00Ll840BYraL8dCJu-
 docling/backend/xml/uspto_backend.py,sha256=a5GxWLj2SUR5Of8TWJinhef1gKyaQSjHPVXvGiN8yG8,70324
 docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=K5C2yQIoM40_W3YU8a7SmneY-hWbNp_JOFPLk0NPcDI,16098
+docling/cli/main.py,sha256=qShZI1f7WWn5T16YtFTeYY1CUucNjyGefIekCWvkAqc,16366
+docling/cli/models.py,sha256=cjP13QZfgHZWPVJw3kJvSszJdDrRVWx-sJipZRfHEuQ,3102
+docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/datamodel/base_models.py,sha256=vewP1X99qfAwiUsiC2m8CBDGiQPsGyp_WkKJHYPoYn4,7026
 docling/datamodel/document.py,sha256=HkmvQKW3QSx3tAqPTnXiJbD_y1EVwR-WE3n6Gq8g1NY,13428
 docling/datamodel/pipeline_options.py,sha256=f9-VQFgOdahyclGQgH_T8ZYBopkWsF_fbWbxo39ux3g,7888
-docling/datamodel/settings.py,sha256=uN9jeXMwx--tJb-DFU7nr77g0Iou13YAVDzsymTvbHg,1759
+docling/datamodel/settings.py,sha256=pJi9OBqZQhsNi7RwJWQFRDKGhm3u679iN76psA3VtsY,1817
 docling/document_converter.py,sha256=qaldb7Thqk59RdE-RTGtj1M7l5UzaBdnxIvGoQ7lTeo,12876
 docling/exceptions.py,sha256=-FoP46rFJgz_jn5uDv2V052udEEg8gckk6uhoItchXc,85
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/models/base_model.py,sha256=H5X-exVaAN-XMTzxpgUc-rwH-D8Uk7-VuZtq2soNGXI,2567
+docling/models/base_model.py,sha256=IIf_PA933bdwHst3g_MOC4oiYQcSCIVOnxnCnN1NxEQ,2681
 docling/models/base_ocr_model.py,sha256=YiUMvdjnHw9SHjnfJKT5INrPMoIGEf_Z2OApfl_VRTE,6919
-docling/models/code_formula_model.py,sha256=bOIKJvckZ0QpnDZ-CDiYv-CvuGvaGzJgp2PiYAidKBQ,8422
-docling/models/document_picture_classifier.py,sha256=RLB80ueqWZ86hdXtTKmSynCU13nT-T10vUp2sky9110,6078
+docling/models/code_formula_model.py,sha256=6grbRPWaLljadheT5s4omdT6hmXfin4gJU17csWvhjY,8611
+docling/models/document_picture_classifier.py,sha256=6I_j6fG5fnhIV6rqN31LYikNTZyg5isXrVs0GIqHDaY,6235
 docling/models/ds_glm_model.py,sha256=CkhsP0cEWwm4wb1g3cLFriVGpVtELiUK3REDMkPwAMw,13028
-docling/models/easyocr_model.py,sha256=Kakb20ioBxDmNsIqoGvSSs_vbqAWN3QQNHYtEi-eErg,4990
-docling/models/layout_model.py,sha256=3Fw7OM6g0j7NgItKsQOgFOCd1q6lp1DacN_db7f6QCw,6090
+docling/models/easyocr_model.py,sha256=dDy0iaR4KUrq7eFIQclMqUYap1B06PG4nC6RMlGYhSw,6886
+docling/models/layout_model.py,sha256=7fQWipGV1HDrvbP4uOKa9QAicQl89jp7lailQmbFL3w,7804
 docling/models/ocr_mac_model.py,sha256=bLP14UUmZcSzjDe-HLj-mtksTuBmsCTg2C1wCxUpan0,4502
 docling/models/page_assemble_model.py,sha256=c5KLKwkUIdW0JcDHizWsqrpb5x_3DK28x82Q8o-3VJM,5968
 docling/models/page_preprocessing_model.py,sha256=1gVrZjObKxAvXkkKvXnIFApPOggzgiTFPtt1CGbMbSs,2763
 docling/models/rapid_ocr_model.py,sha256=2HXmurNRPP6qyqn7U5h9NQIs8zi0TMHf56CpcKQk0fU,5038
-docling/models/table_structure_model.py,sha256=qZgoBrBh7H-RJGCTtaRGcj79g2WzZiUBTPnHqJZ-bLA,9557
+docling/models/table_structure_model.py,sha256=UIqWlw_9JNfGsO86c00rPb4GCg-yNliKEwyhCqlsZbM,11225
 docling/models/tesseract_ocr_cli_model.py,sha256=b2Is5x2gZLS6mQWnKe0y7p6UU6hRTHDfoH4D2RQ5mx0,9310
 docling/models/tesseract_ocr_model.py,sha256=BN85u-4a-xzUY7Iw21Ib8L8kx4mgbDGiUtxBelLiJm8,8513
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/pipeline/base_pipeline.py,sha256=lK8PQiydWJ9M16kIVL7U1A2iryTRFrN5WSucVo2ohFQ,8757
+docling/pipeline/base_pipeline.py,sha256=9ABK-Cr235bxE5vweoIA5rgBZV_EF8qFxAqLI27H_Pg,8749
 docling/pipeline/simple_pipeline.py,sha256=mZqANqUtAOFAyqQEShErQnAUz6tJFOl6zVoazEDJ_wE,2254
-docling/pipeline/standard_pdf_pipeline.py,sha256=Qefg1JSiFwipypi8TZPJ50WgXTLjwkC0wvYAl02RM2o,10480
+docling/pipeline/standard_pdf_pipeline.py,sha256=xVGLYmh677hKBSRCoHYAVn7drmowba2QGI8f-eEC5gs,10624
 docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/utils/accelerator_utils.py,sha256=ZjULCn-qhxqx3frF-rJmAlWdzqgUMxH5utLHbSPev80,1367
 docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
 docling/utils/glm_utils.py,sha256=uyCoFTX9FbS1Ke0aSlkdzGLUt08dZfkgriWadkyLiiA,11856
 docling/utils/layout_postprocessor.py,sha256=urRzeF9PrKiMBvA6DdHHwyLxG06CMhelgJeV5B1l6l0,24258
+docling/utils/model_downloader.py,sha256=5jChSE88byGj7LvGNnB01qBw6n9ODJjnAS66PobRSJc,2267
 docling/utils/ocr_utils.py,sha256=F7iOOjqolUcImUzir4qjDQd4QWSO3s6JC4WRn3U7uY4,263
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
-docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
+docling/utils/utils.py,sha256=0ozCk7zUkYzxRVmYoIB2zA1lqjQOuaQzxfGuf1wmKW4,1866
 docling/utils/visualization.py,sha256=4pn-80fVuE04ken7hUg5Ar47ndRSL9MWBgdHM-1g1zU,2735
-docling-2.18.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.18.0.dist-info/METADATA,sha256=rBP1Z7m0HMpC-HjR360i2JNuIA9lqknRPjUab1mtVic,8403
-docling-2.18.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-docling-2.18.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.18.0.dist-info/RECORD,,
+docling-2.19.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.19.0.dist-info/METADATA,sha256=deXdwXb0i_n3pyEDbVGNQNw4APYoUVtXnkHmC-frXWI,8442
+docling-2.19.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+docling-2.19.0.dist-info/entry_points.txt,sha256=cFrINXsORijdm2EWJzf1m9_rDxH9G9W1fP385-9atY4,84
+docling-2.19.0.dist-info/RECORD,,

{docling-2.18.0.dist-info → docling-2.19.0.dist-info}/entry_points.txt

@@ -1,3 +1,4 @@
 [console_scripts]
 docling=docling.cli.main:app
+docling-tools=docling.cli.tools:app