docling 2.34.0__tar.gz → 2.36.0__tar.gz

{docling-2.34.0 → docling-2.36.0}/PKG-INFO

@@ -1,67 +1,68 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: docling
-Version: 2.34.0
+Version: 2.36.0
 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/docling-project/docling
-License: MIT
+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
+Project-URL: homepage, https://github.com/docling-project/docling
+Project-URL: repository, https://github.com/docling-project/docling
+Project-URL: issues, https://github.com/docling-project/docling/issues
+Project-URL: changelog, https://github.com/docling-project/docling/blob/main/CHANGELOG.md
 Keywords: docling,convert,document,pdf,docx,html,markdown,layout model,segmentation,table structure,table former
-Author: Christoph Auer
-Author-email: cau@zurich.ibm.com
-Requires-Python: >=3.9,<4.0
+Classifier: Operating System :: MacOS :: MacOS X
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Operating System :: Microsoft :: Windows
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: MacOS :: MacOS X
-Classifier: Operating System :: POSIX :: Linux
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
-Provides-Extra: ocrmac
-Provides-Extra: rapidocr
+Requires-Python: <4.0,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pydantic<3.0.0,>=2.0.0
+Requires-Dist: docling-core[chunking]<3.0.0,>=2.29.0
+Requires-Dist: docling-ibm-models<4.0.0,>=3.4.4
+Requires-Dist: docling-parse<5.0.0,>=4.0.0
+Requires-Dist: filetype<2.0.0,>=1.2.0
+Requires-Dist: pypdfium2<5.0.0,>=4.30.0
+Requires-Dist: pydantic-settings<3.0.0,>=2.3.0
+Requires-Dist: huggingface_hub<1,>=0.23
+Requires-Dist: requests<3.0.0,>=2.32.2
+Requires-Dist: easyocr<2.0,>=1.7
+Requires-Dist: certifi>=2024.7.4
+Requires-Dist: rtree<2.0.0,>=1.3.0
+Requires-Dist: typer<0.16.0,>=0.12.5
+Requires-Dist: python-docx<2.0.0,>=1.1.2
+Requires-Dist: python-pptx<2.0.0,>=1.0.2
+Requires-Dist: beautifulsoup4<5.0.0,>=4.12.3
+Requires-Dist: pandas<3.0.0,>=2.1.4
+Requires-Dist: marko<3.0.0,>=2.1.2
+Requires-Dist: openpyxl<4.0.0,>=3.1.5
+Requires-Dist: lxml<6.0.0,>=4.0.0
+Requires-Dist: pillow<12.0.0,>=10.0.0
+Requires-Dist: tqdm<5.0.0,>=4.65.0
+Requires-Dist: pluggy<2.0.0,>=1.0.0
+Requires-Dist: pylatexenc<3.0,>=2.10
+Requires-Dist: click<8.2.0
+Requires-Dist: scipy<2.0.0,>=1.6.0
 Provides-Extra: tesserocr
+Requires-Dist: tesserocr<3.0.0,>=2.7.1; extra == "tesserocr"
+Provides-Extra: ocrmac
+Requires-Dist: ocrmac<2.0.0,>=1.0.0; sys_platform == "darwin" and extra == "ocrmac"
 Provides-Extra: vlm
-Requires-Dist: accelerate (>=1.2.1,<2.0.0) ; (sys_platform != "darwin" or platform_machine != "x86_64") and (extra == "vlm")
-Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
-Requires-Dist: certifi (>=2024.7.4)
-Requires-Dist: click (<8.2.0)
-Requires-Dist: docling-core[chunking] (>=2.29.0,<3.0.0)
-Requires-Dist: docling-ibm-models (>=3.4.0,<4.0.0)
-Requires-Dist: docling-parse (>=4.0.0,<5.0.0)
-Requires-Dist: easyocr (>=1.7,<2.0)
-Requires-Dist: filetype (>=1.2.0,<2.0.0)
-Requires-Dist: huggingface_hub (>=0.23,<1)
-Requires-Dist: lxml (>=4.0.0,<6.0.0)
-Requires-Dist: marko (>=2.1.2,<3.0.0)
-Requires-Dist: ocrmac (>=1.0.0,<2.0.0) ; (sys_platform == "darwin") and (extra == "ocrmac")
-Requires-Dist: onnxruntime (>=1.7.0,<1.20.0) ; (python_version < "3.10") and (extra == "rapidocr")
-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,<12.0.0)
-Requires-Dist: pluggy (>=1.0.0,<2.0.0)
-Requires-Dist: pydantic (>=2.0.0,<3.0.0)
-Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
-Requires-Dist: pylatexenc (>=2.10,<3.0)
-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 (>=2.32.2,<3.0.0)
-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: transformers (>=4.42.0,<4.43.0) ; (sys_platform == "darwin" and platform_machine == "x86_64") and (extra == "vlm")
-Requires-Dist: transformers (>=4.46.0,<5.0.0) ; (sys_platform != "darwin" or platform_machine != "x86_64") and (extra == "vlm")
-Requires-Dist: typer (>=0.12.5,<0.16.0)
-Project-URL: Repository, https://github.com/docling-project/docling
-Description-Content-Type: text/markdown
+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>=0.1.22; (python_version >= "3.10" and sys_platform == "darwin" and platform_machine == "arm64") and extra == "vlm"
+Provides-Extra: rapidocr
+Requires-Dist: rapidocr-onnxruntime<2.0.0,>=1.4.0; python_version < "3.13" and extra == "rapidocr"
+Requires-Dist: onnxruntime<2.0.0,>=1.7.0; extra == "rapidocr"
+Dynamic: license-file
 
 <p align="center">
   <a href="https://github.com/docling-project/docling">
@@ -79,9 +80,8 @@ Description-Content-Type: text/markdown
 [![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://docling-project.github.io/docling/)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)
-[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
-[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
 [![License MIT](https://img.shields.io/github/license/docling-project/docling)](https://opensource.org/licenses/MIT)
@@ -101,7 +101,7 @@ Docling simplifies document processing, parsing diverse formats — including ad
 * 🔒 Local execution capabilities for sensitive data and air-gapped environments
 * 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
 * 🔍 Extensive OCR support for scanned PDFs and images
-* 🥚 Support of Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview)) 🆕
+* 🥚 Support of several Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
 * 💻 Simple and convenient CLI
 
 ### Coming soon
@@ -214,4 +214,3 @@ The project was started by the AI for knowledge team at IBM Research Zurich.
 [supported_formats]: https://docling-project.github.io/docling/usage/supported_formats/
 [docling_document]: https://docling-project.github.io/docling/concepts/docling_document/
 [integrations]: https://docling-project.github.io/docling/integrations/
-

{docling-2.34.0 → docling-2.36.0}/README.md

@@ -14,9 +14,8 @@
 [![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://docling-project.github.io/docling/)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/docling)](https://pypi.org/project/docling/)
-[![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
-[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)
-[![Imports: isort](https://img.shields.io/badge/%20imports-isort-%231674b1?style=flat&labelColor=ef8336)](https://pycqa.github.io/isort/)
+[![uv](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/uv/main/assets/badge/v0.json)](https://github.com/astral-sh/uv)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 [![Pydantic v2](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/pydantic/pydantic/main/docs/badge/v2.json)](https://pydantic.dev)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit&logoColor=white)](https://github.com/pre-commit/pre-commit)
 [![License MIT](https://img.shields.io/github/license/docling-project/docling)](https://opensource.org/licenses/MIT)
@@ -36,7 +35,7 @@ Docling simplifies document processing, parsing diverse formats — including ad
 * 🔒 Local execution capabilities for sensitive data and air-gapped environments
 * 🤖 Plug-and-play [integrations][integrations] incl. LangChain, LlamaIndex, Crew AI & Haystack for agentic AI
 * 🔍 Extensive OCR support for scanned PDFs and images
-* 🥚 Support of Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview)) 🆕
+* 🥚 Support of several Visual Language Models ([SmolDocling](https://huggingface.co/ds4sd/SmolDocling-256M-preview))
 * 💻 Simple and convenient CLI
 
 ### Coming soon

{docling-2.34.0 → docling-2.36.0}/docling/cli/main.py

@@ -12,6 +12,12 @@ from typing import Annotated, Dict, List, Optional, Type
 
 import rich.table
 import typer
+from docling_core.transforms.serializer.html import (
+    HTMLDocSerializer,
+    HTMLOutputStyle,
+    HTMLParams,
+)
+from docling_core.transforms.visualizer.layout_visualizer import LayoutVisualizer
 from docling_core.types.doc import ImageRefMode
 from docling_core.utils.file import resolve_source_to_path
 from pydantic import TypeAdapter
@@ -22,6 +28,7 @@ from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBacke
 from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
 from docling.backend.pdf_backend import PdfDocumentBackend
 from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
+from docling.datamodel.accelerator_options import AcceleratorDevice, AcceleratorOptions
 from docling.datamodel.base_models import (
     ConversionStatus,
     FormatToExtensions,
@@ -30,8 +37,6 @@ from docling.datamodel.base_models import (
 )
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
-    AcceleratorDevice,
-    AcceleratorOptions,
     EasyOcrOptions,
     OcrOptions,
     PaginatedPipelineOptions,
@@ -39,14 +44,16 @@ from docling.datamodel.pipeline_options import (
     PdfPipeline,
     PdfPipelineOptions,
     TableFormerMode,
-    VlmModelType,
     VlmPipelineOptions,
-    granite_vision_vlm_conversion_options,
-    granite_vision_vlm_ollama_conversion_options,
-    smoldocling_vlm_conversion_options,
-    smoldocling_vlm_mlx_conversion_options,
 )
 from docling.datamodel.settings import settings
+from docling.datamodel.vlm_model_specs import (
+    GRANITE_VISION_OLLAMA,
+    GRANITE_VISION_TRANSFORMERS,
+    SMOLDOCLING_MLX,
+    SMOLDOCLING_TRANSFORMERS,
+    VlmModelType,
+)
 from docling.document_converter import DocumentConverter, FormatOption, PdfFormatOption
 from docling.models.factories import get_ocr_factory
 from docling.pipeline.vlm_pipeline import VlmPipeline
@@ -156,6 +163,7 @@ def export_documents(
     export_json: bool,
     export_html: bool,
     export_html_split_page: bool,
+    show_layout: bool,
     export_md: bool,
     export_txt: bool,
     export_doctags: bool,
@@ -189,9 +197,27 @@ def export_documents(
             if export_html_split_page:
                 fname = output_dir / f"{doc_filename}.html"
                 _log.info(f"writing HTML output to {fname}")
-                conv_res.document.save_as_html(
-                    filename=fname, image_mode=image_export_mode, split_page_view=True
-                )
+                if show_layout:
+                    ser = HTMLDocSerializer(
+                        doc=conv_res.document,
+                        params=HTMLParams(
+                            image_mode=image_export_mode,
+                            output_style=HTMLOutputStyle.SPLIT_PAGE,
+                        ),
+                    )
+                    visualizer = LayoutVisualizer()
+                    visualizer.params.show_label = False
+                    ser_res = ser.serialize(
+                        visualizer=visualizer,
+                    )
+                    with open(fname, "w") as fw:
+                        fw.write(ser_res.text)
+                else:
+                    conv_res.document.save_as_html(
+                        filename=fname,
+                        image_mode=image_export_mode,
+                        split_page_view=True,
+                    )
 
             # Export Text format:
             if export_txt:
@@ -250,6 +276,13 @@ def convert(  # noqa: C901
     to_formats: List[OutputFormat] = typer.Option(
         None, "--to", help="Specify output formats. Defaults to Markdown."
     ),
+    show_layout: Annotated[
+        bool,
+        typer.Option(
+            ...,
+            help="If enabled, the page images will show the bounding-boxes of the items.",
+        ),
+    ] = False,
     headers: str = typer.Option(
         None,
         "--headers",
@@ -547,20 +580,16 @@ def convert(  # noqa: C901
             )
 
             if vlm_model == VlmModelType.GRANITE_VISION:
-                pipeline_options.vlm_options = granite_vision_vlm_conversion_options
+                pipeline_options.vlm_options = GRANITE_VISION_TRANSFORMERS
             elif vlm_model == VlmModelType.GRANITE_VISION_OLLAMA:
-                pipeline_options.vlm_options = (
-                    granite_vision_vlm_ollama_conversion_options
-                )
+                pipeline_options.vlm_options = GRANITE_VISION_OLLAMA
             elif vlm_model == VlmModelType.SMOLDOCLING:
-                pipeline_options.vlm_options = smoldocling_vlm_conversion_options
+                pipeline_options.vlm_options = SMOLDOCLING_TRANSFORMERS
                 if sys.platform == "darwin":
                     try:
                         import mlx_vlm
 
-                        pipeline_options.vlm_options = (
-                            smoldocling_vlm_mlx_conversion_options
-                        )
+                        pipeline_options.vlm_options = SMOLDOCLING_MLX
                     except ImportError:
                         _log.warning(
                             "To run SmolDocling faster, please install mlx-vlm:\n"
@@ -596,6 +625,7 @@ def convert(  # noqa: C901
             export_json=export_json,
             export_html=export_html,
             export_html_split_page=export_html_split_page,
+            show_layout=show_layout,
             export_md=export_md,
             export_txt=export_txt,
             export_doctags=export_doctags,

docling-2.36.0/docling/datamodel/accelerator_options.py

@@ -0,0 +1,68 @@
+import logging
+import os
+import re
+from enum import Enum
+from typing import Any, Union
+
+from pydantic import field_validator, model_validator
+from pydantic_settings import BaseSettings, SettingsConfigDict
+
+_log = logging.getLogger(__name__)
+
+
+class AcceleratorDevice(str, Enum):
+    """Devices to run model inference"""
+
+    AUTO = "auto"
+    CPU = "cpu"
+    CUDA = "cuda"
+    MPS = "mps"
+
+
+class AcceleratorOptions(BaseSettings):
+    model_config = SettingsConfigDict(
+        env_prefix="DOCLING_", env_nested_delimiter="_", populate_by_name=True
+    )
+
+    num_threads: int = 4
+    device: Union[str, AcceleratorDevice] = "auto"
+    cuda_use_flash_attention2: bool = False
+
+    @field_validator("device")
+    def validate_device(cls, value):
+        # "auto", "cpu", "cuda", "mps", or "cuda:N"
+        if value in {d.value for d in AcceleratorDevice} or re.match(
+            r"^cuda(:\d+)?$", value
+        ):
+            return value
+        raise ValueError(
+            "Invalid device option. Use 'auto', 'cpu', 'mps', 'cuda', or 'cuda:N'."
+        )
+
+    @model_validator(mode="before")
+    @classmethod
+    def check_alternative_envvars(cls, data: Any) -> Any:
+        r"""
+        Set num_threads from the "alternative" envvar OMP_NUM_THREADS.
+        The alternative envvar is used only if it is valid and the regular envvar is not set.
+
+        Notice: The standard pydantic settings mechanism with parameter "aliases" does not provide
+        the same functionality. In case the alias envvar is set and the user tries to override the
+        parameter in settings initialization, Pydantic treats the parameter provided in __init__()
+        as an extra input instead of simply overwriting the evvar value for that parameter.
+        """
+        if isinstance(data, dict):
+            input_num_threads = data.get("num_threads")
+            # Check if to set the num_threads from the alternative envvar
+            if input_num_threads is None:
+                docling_num_threads = os.getenv("DOCLING_NUM_THREADS")
+                omp_num_threads = os.getenv("OMP_NUM_THREADS")
+                if docling_num_threads is None and omp_num_threads is not None:
+                    try:
+                        data["num_threads"] = int(omp_num_threads)
+                    except ValueError:
+                        _log.error(
+                            "Ignoring misformatted envvar OMP_NUM_THREADS '%s'",
+                            omp_num_threads,
+                        )
+        return data

{docling-2.34.0 → docling-2.36.0}/docling/datamodel/base_models.py

@@ -13,11 +13,11 @@ from docling_core.types.doc import (
     TableCell,
 )
 from docling_core.types.doc.page import SegmentedPdfPage, TextCell
-
-# DO NOT REMOVE; explicitly exposed from this location
 from docling_core.types.io import (
     DocumentStream,
 )
+
+# DO NOT REMOVE; explicitly exposed from this location
 from PIL.Image import Image
 from pydantic import BaseModel, ConfigDict, Field, computed_field
 
@@ -131,12 +131,6 @@ class ErrorItem(BaseModel):
     error_message: str
 
 
-# class Cell(BaseModel):
-#    id: int
-#    text: str
-#    bbox: BoundingBox
-
-
 class Cluster(BaseModel):
     id: int
     label: DocItemLabel
@@ -158,8 +152,16 @@ class LayoutPrediction(BaseModel):
     clusters: List[Cluster] = []
 
 
+class VlmPredictionToken(BaseModel):
+    text: str = ""
+    token: int = -1
+    logprob: float = -1
+
+
 class VlmPrediction(BaseModel):
     text: str = ""
+    generated_tokens: list[VlmPredictionToken] = []
+    generation_time: float = -1
 
 
 class ContainerElement(

{docling-2.34.0 → docling-2.36.0}/docling/datamodel/document.py

@@ -334,9 +334,9 @@ class _DocumentConversionInput(BaseModel):
     ) -> Optional[InputFormat]:
         """Guess the input format of a document by checking part of its content."""
         input_format: Optional[InputFormat] = None
-        content_str = content.decode("utf-8")
 
         if mime == "application/xml":
+            content_str = content.decode("utf-8")
             match_doctype = re.search(r"<!DOCTYPE [^>]+>", content_str)
             if match_doctype:
                 xml_doctype = match_doctype.group()
@@ -358,6 +358,7 @@ class _DocumentConversionInput(BaseModel):
                     input_format = InputFormat.XML_JATS
 
         elif mime == "text/plain":
+            content_str = content.decode("utf-8")
             if InputFormat.XML_USPTO in formats and content_str.startswith("PATN\r\n"):
                 input_format = InputFormat.XML_USPTO
 
@@ -411,7 +412,11 @@ class _DocumentConversionInput(BaseModel):
             else:
                 return "application/xml"
 
-        if re.match(r"<!doctype\s+html|<html|<head|<body", content_str):
+        if re.match(
+            r"(<script.*?>.*?</script>\s*)?(<!doctype\s+html|<html|<head|<body)",
+            content_str,
+            re.DOTALL,
+        ):
             return "text/html"
 
         p = re.compile(