syncing with latest commit on original branch

.github/workflows/checks.yml

@@ -6,7 +6,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ['3.10', '3.11', '3.12']
+        python-version: ['3.9', '3.10', '3.11', '3.12']
     steps:
       - uses: actions/checkout@v3
       - name: Install tesseract

CHANGELOG.md

@@ -1,3 +1,14 @@
+## [v2.7.0](https://github.com/DS4SD/docling/releases/tag/v2.7.0) - 2024-11-20
+
+### Feature
+
+* Add support for `ocrmac` OCR engine on macOS ([#276](https://github.com/DS4SD/docling/issues/276)) ([`6efa96c`](https://github.com/DS4SD/docling/commit/6efa96c983fc509b2c7b35a4a25a714284f2f782))
+
+### Fix
+
+* Python3.9 support ([#396](https://github.com/DS4SD/docling/issues/396)) ([`7b013ab`](https://github.com/DS4SD/docling/commit/7b013abcf31ba49e2141dfd408bc8c23e8d87d91))
+* Propagate document limits to converter ([#388](https://github.com/DS4SD/docling/issues/388)) ([`32ebf55`](https://github.com/DS4SD/docling/commit/32ebf55e3338dd22f9a23c55595f15835794d961))
+
 ## [v2.6.0](https://github.com/DS4SD/docling/releases/tag/v2.6.0) - 2024-11-19
 
 ### Feature

README.md

@@ -13,7 +13,7 @@
 [![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)
 [![Docs](https://img.shields.io/badge/docs-live-brightgreen)](https://ds4sd.github.io/docling/)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
-![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)
+[![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/)

docling/cli/main.py

@@ -24,6 +24,7 @@ from docling.datamodel.base_models import (
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
+    OcrMacOptions,
     OcrOptions,
     PdfPipelineOptions,
     TableFormerMode,
@@ -75,6 +76,7 @@ class OcrEngine(str, Enum):
     EASYOCR = "easyocr"
     TESSERACT_CLI = "tesseract_cli"
     TESSERACT = "tesseract"
+    OCRMAC = "ocrmac"
     PADDLEOCR = "paddleocr"
 
 
@@ -254,17 +256,18 @@ def convert(
     export_txt = OutputFormat.TEXT in to_formats
     export_doctags = OutputFormat.DOCTAGS in to_formats
 
-    match ocr_engine:
+    if ocr_engine == OcrEngine.EASYOCR:
-        case OcrEngine.EASYOCR:
+        ocr_options: OcrOptions = EasyOcrOptions(force_full_page_ocr=force_ocr)
-            ocr_options: OcrOptions = EasyOcrOptions(force_full_page_ocr=force_ocr)
+    elif ocr_engine == OcrEngine.TESSERACT_CLI:
-        case OcrEngine.TESSERACT_CLI:
+        ocr_options = TesseractCliOcrOptions(force_full_page_ocr=force_ocr)
-            ocr_options = TesseractCliOcrOptions(force_full_page_ocr=force_ocr)
+    elif ocr_engine == OcrEngine.TESSERACT:
-        case OcrEngine.TESSERACT:
+        ocr_options = TesseractOcrOptions(force_full_page_ocr=force_ocr)
-            ocr_options = TesseractOcrOptions(force_full_page_ocr=force_ocr)
+    elif ocr_engine == OcrEngine.OCRMAC:
-        case OcrEngine.PADDLEOCR:
+        ocr_options = OcrMacOptions(force_full_page_ocr=force_ocr)
-            ocr_options = PaddleOcrOptions(force_full_page_ocr=force_ocr)
+    elif ocr_engine ==  OcrEngine.PADDLEOCR:
-        case _:
+        ocr_options = PaddleOcrOptions(force_full_page_ocr=force_ocr)
-            raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}")
+    else:
+        raise RuntimeError(f"Unexpected OCR engine type {ocr_engine}")
 
     ocr_lang_list = _split_list(ocr_lang)
     if ocr_lang_list is not None:
@@ -281,15 +284,14 @@ def convert(
     if artifacts_path is not None:
         pipeline_options.artifacts_path = artifacts_path
 
-    match pdf_backend:
+    if pdf_backend == PdfBackend.DLPARSE_V1:
-        case PdfBackend.DLPARSE_V1:
+        backend: Type[PdfDocumentBackend] = DoclingParseDocumentBackend
-            backend: Type[PdfDocumentBackend] = DoclingParseDocumentBackend
+    elif pdf_backend == PdfBackend.DLPARSE_V2:
-        case PdfBackend.DLPARSE_V2:
+        backend = DoclingParseV2DocumentBackend
-            backend = DoclingParseV2DocumentBackend
+    elif pdf_backend == PdfBackend.PYPDFIUM2:
-        case PdfBackend.PYPDFIUM2:
+        backend = PyPdfiumDocumentBackend
-            backend = PyPdfiumDocumentBackend
+    else:
-        case _:
+        raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
-            raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
 
     format_options: Dict[InputFormat, FormatOption] = {
         InputFormat.PDF: PdfFormatOption(

docling/datamodel/pipeline_options.py

@@ -1,6 +1,6 @@
 from enum import Enum
 from pathlib import Path
-from typing import List, Literal, Optional, Union
+from typing import List, Literal, Optional, Union, Annotated
 
 from pydantic import BaseModel, ConfigDict, Field
 
@@ -43,7 +43,10 @@ class EasyOcrOptions(OcrOptions):
 
 class PaddleOcrOptions(OcrOptions):
     kind: Literal["paddleocr"] = "paddleocr"
-    lang: str = "en"
+    lang: Annotated[
+        list[str],
+        Field(min_items=1, max_items=1)  # Limits the list length to 0 or 1 items
+    ] = ["en"]
     use_gpu: bool = True  # same default as paddleocr.ocr
     use_angle_cls: bool = True
     show_log: bool = False
@@ -75,6 +78,17 @@ class TesseractOcrOptions(OcrOptions):
     )
 
 
+class OcrMacOptions(OcrOptions):
+    kind: Literal["ocrmac"] = "ocrmac"
+    lang: List[str] = ["fr-FR", "de-DE", "es-ES", "en-US"]
+    recognition: str = "accurate"
+    framework: str = "vision"
+
+    model_config = ConfigDict(
+        extra="forbid",
+    )
+
+
 class PipelineOptions(BaseModel):
     create_legacy_output: bool = (
         True  # This defautl will be set to False on a future version of docling
@@ -87,9 +101,9 @@ class PdfPipelineOptions(PipelineOptions):
     do_ocr: bool = True  # True: perform OCR, replace programmatic PDF text
 
     table_structure_options: TableStructureOptions = TableStructureOptions()
-    ocr_options: Union[EasyOcrOptions, TesseractCliOcrOptions, TesseractOcrOptions, PaddleOcrOptions] = (
+    ocr_options: Union[
-        Field(EasyOcrOptions(), discriminator="kind")
+        EasyOcrOptions, TesseractCliOcrOptions, TesseractOcrOptions, PaddleOcrOptions, OcrMacOptions
-    )
+    ] = Field(EasyOcrOptions(), discriminator="kind")
 
     images_scale: float = 1.0
     generate_page_images: bool = False

docling/document_converter.py

@@ -3,7 +3,7 @@ import sys
 import time
 from functools import partial
 from pathlib import Path
-from typing import Dict, Iterable, Iterator, List, Optional, Type
+from typing import Dict, Iterable, Iterator, List, Optional, Type, Union
 
 from pydantic import BaseModel, ConfigDict, model_validator, validate_call
 
@@ -155,7 +155,7 @@ class DocumentConverter:
     @validate_call(config=ConfigDict(strict=True))
     def convert(
         self,
-        source: Path | str | DocumentStream,  # TODO review naming
+        source: Union[Path, str, DocumentStream],  # TODO review naming
         raises_on_error: bool = True,
         max_num_pages: int = sys.maxsize,
         max_file_size: int = sys.maxsize,
@@ -172,7 +172,7 @@ class DocumentConverter:
     @validate_call(config=ConfigDict(strict=True))
     def convert_all(
         self,
-        source: Iterable[Path | str | DocumentStream],  # TODO review naming
+        source: Iterable[Union[Path, str, DocumentStream]],  # TODO review naming
         raises_on_error: bool = True,  # True: raises on first conversion error; False: does not raise on conv error
         max_num_pages: int = sys.maxsize,
         max_file_size: int = sys.maxsize,

docling/models/ocr_mac_model.py

@@ -0,0 +1,118 @@
+import logging
+import tempfile
+from typing import Iterable, Optional, Tuple
+
+from docling_core.types.doc import BoundingBox, CoordOrigin
+
+from docling.datamodel.base_models import OcrCell, Page
+from docling.datamodel.document import ConversionResult
+from docling.datamodel.pipeline_options import OcrMacOptions
+from docling.datamodel.settings import settings
+from docling.models.base_ocr_model import BaseOcrModel
+from docling.utils.profiling import TimeRecorder
+
+_log = logging.getLogger(__name__)
+
+
+class OcrMacModel(BaseOcrModel):
+    def __init__(self, enabled: bool, options: OcrMacOptions):
+        super().__init__(enabled=enabled, options=options)
+        self.options: OcrMacOptions
+
+        self.scale = 3  # multiplier for 72 dpi == 216 dpi.
+
+        if self.enabled:
+            install_errmsg = (
+                "ocrmac is not correctly installed. "
+                "Please install it via `pip install ocrmac` to use this OCR engine. "
+                "Alternatively, Docling has support for other OCR engines. See the documentation: "
+                "https://ds4sd.github.io/docling/installation/"
+            )
+            try:
+                from ocrmac import ocrmac
+            except ImportError:
+                raise ImportError(install_errmsg)
+
+            self.reader_RIL = ocrmac.OCR
+
+    def __call__(
+        self, conv_res: ConversionResult, page_batch: Iterable[Page]
+    ) -> Iterable[Page]:
+
+        if not self.enabled:
+            yield from page_batch
+            return
+
+        for page in page_batch:
+            assert page._backend is not None
+            if not page._backend.is_valid():
+                yield page
+            else:
+                with TimeRecorder(conv_res, "ocr"):
+
+                    ocr_rects = self.get_ocr_rects(page)
+
+                    all_ocr_cells = []
+                    for ocr_rect in ocr_rects:
+                        # Skip zero area boxes
+                        if ocr_rect.area() == 0:
+                            continue
+                        high_res_image = page._backend.get_page_image(
+                            scale=self.scale, cropbox=ocr_rect
+                        )
+
+                        with tempfile.NamedTemporaryFile(
+                            suffix=".png", mode="w"
+                        ) as image_file:
+                            fname = image_file.name
+                            high_res_image.save(fname)
+
+                            boxes = self.reader_RIL(
+                                fname,
+                                recognition_level=self.options.recognition,
+                                framework=self.options.framework,
+                                language_preference=self.options.lang,
+                            ).recognize()
+
+                        im_width, im_height = high_res_image.size
+                        cells = []
+                        for ix, (text, confidence, box) in enumerate(boxes):
+                            x = float(box[0])
+                            y = float(box[1])
+                            w = float(box[2])
+                            h = float(box[3])
+
+                            x1 = x * im_width
+                            y2 = (1 - y) * im_height
+
+                            x2 = x1 + w * im_width
+                            y1 = y2 - h * im_height
+
+                            left = x1 / self.scale
+                            top = y1 / self.scale
+                            right = x2 / self.scale
+                            bottom = y2 / self.scale
+
+                            cells.append(
+                                OcrCell(
+                                    id=ix,
+                                    text=text,
+                                    confidence=confidence,
+                                    bbox=BoundingBox.from_tuple(
+                                        coord=(left, top, right, bottom),
+                                        origin=CoordOrigin.TOPLEFT,
+                                    ),
+                                )
+                            )
+
+                        # del high_res_image
+                        all_ocr_cells.extend(cells)
+
+                    # Post-process the cells
+                    page.cells = self.post_process_cells(all_ocr_cells, page.cells)
+
+                # DEBUG code:
+                if settings.debug.visualize_ocr:
+                    self.draw_ocr_rects_and_cells(conv_res, page, ocr_rects)
+
+                yield page

docling/models/paddle_ocr_model.py

@@ -4,13 +4,12 @@ from typing import Iterable
 import numpy
 from docling_core.types.doc import BoundingBox, CoordOrigin
 
-from docling.datamodel.base_models import Cell, OcrCell, Page
+from docling.datamodel.base_models import OcrCell, Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import PaddleOcrOptions
 from docling.datamodel.settings import settings
 from docling.models.base_ocr_model import BaseOcrModel
 from docling.utils.profiling import TimeRecorder
-import cv2
 
 _log = logging.getLogger(__name__)
 
@@ -32,7 +31,7 @@ class PaddleOcrModel(BaseOcrModel):
                 )
 
             self.reader = PaddleOCR(
-                lang=self.options.lang,
+                lang=self.options.lang[0],
                 use_gpu=self.options.use_gpu,
                 use_angle_cls=self.options.use_angle_cls, 
                 show_log=self.options.show_log,

docling/pipeline/standard_pdf_pipeline.py

@@ -1,4 +1,5 @@
 import logging
+import sys
 from pathlib import Path
 from typing import Optional
 
@@ -10,6 +11,7 @@ from docling.datamodel.base_models import AssembledUnit, Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
+    OcrMacOptions,
     PdfPipelineOptions,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
@@ -20,6 +22,7 @@ from docling.models.ds_glm_model import GlmModel, GlmOptions
 from docling.models.easyocr_model import EasyOcrModel
 from docling.models.paddle_ocr_model import PaddleOcrModel
 from docling.models.layout_model import LayoutModel
+from docling.models.ocr_mac_model import OcrMacModel
 from docling.models.page_assemble_model import PageAssembleModel, PageAssembleOptions
 from docling.models.page_preprocessing_model import (
     PagePreprocessingModel,
@@ -120,6 +123,15 @@ class StandardPdfPipeline(PaginatedPipeline):
                 enabled=self.pipeline_options.do_ocr,
                 options=self.pipeline_options.ocr_options,
             )
+        elif isinstance(self.pipeline_options.ocr_options, OcrMacOptions):
+            if "darwin" != sys.platform:
+                raise RuntimeError(
+                    f"The specified OCR type is only supported on Mac: {self.pipeline_options.ocr_options.kind}."
+                )
+            return OcrMacModel(
+                enabled=self.pipeline_options.do_ocr,
+                options=self.pipeline_options.ocr_options,
+            )
         elif isinstance(self.pipeline_options.ocr_options, PaddleOcrOptions):
             return PaddleOcrModel(
                 enabled=self.pipeline_options.do_ocr,

docs/examples/custom_convert.py

@@ -7,6 +7,7 @@ from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
 from docling.datamodel.base_models import InputFormat
 from docling.datamodel.pipeline_options import PdfPipelineOptions
 from docling.document_converter import DocumentConverter, PdfFormatOption
+from docling.models.ocr_mac_model import OcrMacOptions
 from docling.models.tesseract_ocr_cli_model import TesseractCliOcrOptions
 from docling.models.tesseract_ocr_model import TesseractOcrOptions
 
@@ -122,6 +123,20 @@ def main():
     #     }
     # )
 
+    # Docling Parse with ocrmac(Mac only)
+    # ----------------------
+    # pipeline_options = PdfPipelineOptions()
+    # pipeline_options.do_ocr = True
+    # pipeline_options.do_table_structure = True
+    # pipeline_options.table_structure_options.do_cell_matching = True
+    # pipeline_options.ocr_options = OcrMacOptions()
+
+    # doc_converter = DocumentConverter(
+    #     format_options={
+    #         InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
+    #     }
+    # )
+
     ###########################################################################
 
     start_time = time.time()

docs/examples/full_page_ocr.py

@@ -4,6 +4,7 @@ from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.datamodel.base_models import InputFormat
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
+    OcrMacOptions,
     PdfPipelineOptions,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
@@ -20,9 +21,10 @@ def main():
     pipeline_options.do_table_structure = True
     pipeline_options.table_structure_options.do_cell_matching = True
 
-    # Any of the OCR options can be used:EasyOcrOptions, TesseractOcrOptions, TesseractCliOcrOptions, PaddleOcrOptions
+    # Any of the OCR options can be used:EasyOcrOptions, TesseractOcrOptions, TesseractCliOcrOptions, OcrMacOptions(Mac only), PaddleOcrOptions
     # ocr_options = EasyOcrOptions(force_full_page_ocr=True)
     # ocr_options = TesseractOcrOptions(force_full_page_ocr=True)
+    # ocr_options = OcrMacOptions(force_full_page_ocr=True)
     # ocr_options = PaddleOcrOptions(force_full_page_ocr=True)
     ocr_options = TesseractCliOcrOptions(force_full_page_ocr=True)
     pipeline_options.ocr_options = ocr_options

docs/installation.md

@@ -30,6 +30,7 @@ Works on macOS, Linux, and Windows, with support for both x86_64 and arm64 archi
     | [EasyOCR](https://github.com/JaidedAI/EasyOCR) | Default in Docling or via `pip install easyocr`. | `EasyOcrOptions` |
     | Tesseract | System dependency. See description for Tesseract and Tesserocr below.  | `TesseractOcrOptions` |
     | Tesseract CLI | System dependency. See description below. | `TesseractCliOcrOptions` |
+    | OcrMac | System dependency. See description below. | `OcrMacOptions` |
     | PaddleOCR | Extra feature not included in Default Docling installation can be installed via `pip install paddlepaddle paddleocr` | `PaddleOcrOptions` |
 
     The Docling `DocumentConverter` allows to choose the OCR engine with the `ocr_options` settings. For example
@@ -92,6 +93,17 @@ Works on macOS, Linux, and Windows, with support for both x86_64 and arm64 archi
     pip install --no-binary :all: tesserocr
     ```
 
+    <h3>ocrmac installation</h3>
+
+    [ocrmac](https://github.com/straussmaximilian/ocrmac) is using
+    Apple's vision(or livetext) framework as OCR backend.
+    For using this engine with Docling, ocrmac must be installed on your system.
+    This only works on macOS systems with newer macOS versions (10.15+).
+
+    ```console
+    pip install ocrmac
+    ```
+
 ## Development setup
 
 To develop Docling features, bugfixes etc., install as follows from your local clone's root dir:

poetry.lock

@@ -898,13 +898,13 @@ tabulate = ">=0.9.0,<0.10.0"
 
 [[package]]
 name = "docling-ibm-models"
-version = "2.0.5"
+version = "2.0.6"
 description = "This package contains the AI models used by the Docling PDF conversion package"
 optional = false
-python-versions = "<4.0,>=3.10"
+python-versions = "<4.0,>=3.9"
 files = [
-    {file = "docling_ibm_models-2.0.5-py3-none-any.whl", hash = "sha256:a939acd6fdd97a4c2422af1e303a059ff8150d125d66875861ee927e6e5da8de"},
+    {file = "docling_ibm_models-2.0.6-py3-none-any.whl", hash = "sha256:1702b413353d18089511cb73fc325606eb3601b1406b1367a7c5070081f44af2"},
-    {file = "docling_ibm_models-2.0.5.tar.gz", hash = "sha256:3157755e206f0fa364094e3b87a2e573b0dd4f1591083d852b6b71c6e3bb7cc9"},
+    {file = "docling_ibm_models-2.0.6.tar.gz", hash = "sha256:b06bb8e426c8d53cb300b17a432120917a335390665302d82f311a3647ee1bca"},
 ]
 
 [package.dependencies]
@@ -922,41 +922,49 @@ tqdm = ">=4.64.0,<5.0.0"
 
 [[package]]
 name = "docling-parse"
-version = "2.0.4"
+version = "2.1.0"
 description = "Simple package to extract text with coordinates from programmatic PDFs"
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "docling_parse-2.0.4-cp310-cp310-macosx_13_0_arm64.whl", hash = "sha256:1ba71aa48538fd118b7f5e872573d384c335d205d3c6bde102067e0bf2b7d6a9"},
+    {file = "docling_parse-2.1.0-cp310-cp310-macosx_13_0_arm64.whl", hash = "sha256:9bcb089b52fe2e8b414b7a6e812d8402c3a7c664c30c71d71fb6293605ea71cc"},
-    {file = "docling_parse-2.0.4-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:156f34124408a1d016e6a3e1c5a82f58e43c96acc8f3896e81bfb2b5ecc127d5"},
+    {file = "docling_parse-2.1.0-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:430471c51ddb44f180a2350955d5f3e6a507449165e062e6d2bf94a77e3a9ce3"},
-    {file = "docling_parse-2.0.4-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:32f6e791bceb3b1cac357878929ec976aeb50c40b395518934f4817bb2530eae"},
+    {file = "docling_parse-2.1.0-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:f6b9d5883af783516861732eacd03cd37920c1ec4e16ad65b8ddeface8df05a3"},
-    {file = "docling_parse-2.0.4-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:580b01b9276845a410d3aa59397cacb06ad3cf4f471bdfd18187ac0dfdcaaafc"},
+    {file = "docling_parse-2.1.0-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:2a851f28cd61ebe1a94ae9f076ae33e228a80f2c216e7fe558540d6aca22a31a"},
-    {file = "docling_parse-2.0.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e4fce1f091aed82e16726658174d06098642c197ce1ded9508571aa2416a2a03"},
+    {file = "docling_parse-2.1.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fdd7e07d836d39f5fc0703ebd39ae83a453f449af8508937da6374c12a237084"},
-    {file = "docling_parse-2.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0d5447cce907ba6725609346f04d38a83671d2e0b13b468d27a0a861d96af144"},
+    {file = "docling_parse-2.1.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6a3b53a03e8b4d693398f826ed4212bb5903dd557f8a33753248f83762130af8"},
-    {file = "docling_parse-2.0.4-cp310-cp310-win_amd64.whl", hash = "sha256:ce2120287efe4fe408795cfeea881a71d6980527a46ee583a69247e8404d4c0b"},
+    {file = "docling_parse-2.1.0-cp310-cp310-win_amd64.whl", hash = "sha256:92e5c66368bd2b316c7f5b8a55a82052037c1e3b182263628e157fea0d8c92ca"},
-    {file = "docling_parse-2.0.4-cp311-cp311-macosx_13_0_arm64.whl", hash = "sha256:52c94fe627382541e13a8e7fbad8242b618636db55eeeeacc6e92dbf88130812"},
+    {file = "docling_parse-2.1.0-cp311-cp311-macosx_13_0_arm64.whl", hash = "sha256:55f720106faf7999d221cc198bd2e22336aa98f46b3456100ec8ea42f6c90e85"},
-    {file = "docling_parse-2.0.4-cp311-cp311-macosx_13_0_x86_64.whl", hash = "sha256:10c7a2e68a124ebb54b1e27ce6c85ef2f4d9da294e391fc131a9b39b1f9ce657"},
+    {file = "docling_parse-2.1.0-cp311-cp311-macosx_13_0_x86_64.whl", hash = "sha256:e0da2c524d2dce0bd5d3e145964e21dc3ab56c58f2c8940e4aa8e62863a393da"},
-    {file = "docling_parse-2.0.4-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:43dc41995310ed0b0015bea6f72df7cb71106a8550d79946f66f30b2ab2c3a29"},
+    {file = "docling_parse-2.1.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:691f4f1753b59c3bb4cca0c2ad87fd26f59223387cdc0ee3a3d8d6d849793625"},
-    {file = "docling_parse-2.0.4-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:f385d97cb0cf0933a5f0eb4da8b0f9fc9d8629bbf93d57b9043b7a51ba0b33c8"},
+    {file = "docling_parse-2.1.0-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:fadda03667fe9e52f3be92ed6f8ce3d8f7209358b755a5950fd0348de79141d0"},
-    {file = "docling_parse-2.0.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:449c449168cada11eaa83a779e2c25ed4e9e9aec63db2012222ee28fa048a020"},
+    {file = "docling_parse-2.1.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ef354a061a7e57f20baf56f8e8d64b94876dae8d098ddd0d941207d81e8b8f80"},
-    {file = "docling_parse-2.0.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:87dbf20715dbbb9b7d5ff49475b65ce88454c43c0b00bb8ec5bda30643c79003"},
+    {file = "docling_parse-2.1.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d5470b110f35a0a30231607bb1a9ca4e2cb3bf2257d67b29608caa71c553b8a4"},
-    {file = "docling_parse-2.0.4-cp311-cp311-win_amd64.whl", hash = "sha256:6e56726829cb82977f5441db4e1f4d9357faf3ed3dfd55bfa135e650d476a8d8"},
+    {file = "docling_parse-2.1.0-cp311-cp311-win_amd64.whl", hash = "sha256:21a97cfa79179c875d451938b775685f382a47be8f468720e743e4acfd13755e"},
-    {file = "docling_parse-2.0.4-cp312-cp312-macosx_13_0_arm64.whl", hash = "sha256:60c560ed7fdfda1748dca23c858d2d5eb0eff5858fef060bfc4851e1f949e915"},
+    {file = "docling_parse-2.1.0-cp312-cp312-macosx_13_0_arm64.whl", hash = "sha256:72633ec66e5391479260b99fd1d2ff8abd029e6dbe9782c5bd7583037cdc8018"},
-    {file = "docling_parse-2.0.4-cp312-cp312-macosx_13_0_x86_64.whl", hash = "sha256:d35c8c3dd8f580820ec8905be48e37a36f8c3fe8cacbe366ba75c7c35e0de938"},
+    {file = "docling_parse-2.1.0-cp312-cp312-macosx_13_0_x86_64.whl", hash = "sha256:4f29321823fdde287b8986ad23b034de4d09948f4dad80a01c4b853dc923091e"},
-    {file = "docling_parse-2.0.4-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:419dabf6aa0f895878d489a95bdd173661d0891674638c6c01a9b5ca8f156839"},
+    {file = "docling_parse-2.1.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:728ef624ebd487d12872af4ace05a8a25ce52a4debd9da1d870b96e5a2defb8a"},
-    {file = "docling_parse-2.0.4-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:ff7fb21829aa2acad6874ac78b87cfaa642b0910ae6d60e90007c2021fe05c73"},
+    {file = "docling_parse-2.1.0-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:738820a424d27409da2b39af705dd3aa5dc4090f980638ff4f49865e5444c958"},
-    {file = "docling_parse-2.0.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:132e7db9042f13141ec089562478737fb8df70fcd33a0cb0161c7e6cfebf5b46"},
+    {file = "docling_parse-2.1.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d7360bdc2aacd463076799984c989669d1711295a643d2f4be8033150c809b33"},
-    {file = "docling_parse-2.0.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b1ccc13bb32b5c5877f9c3f8870a88beb56d1ab3335ce8a81561cdba1054dfb"},
+    {file = "docling_parse-2.1.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a3a0853dd61aeb381560fcc8e8bf8a444992478ad5b9895932627de0dd14000d"},
-    {file = "docling_parse-2.0.4-cp312-cp312-win_amd64.whl", hash = "sha256:ac34fae4e0080dd8719c22a4aa49a013003a13f3f6bf68f5763136ac7626e390"},
+    {file = "docling_parse-2.1.0-cp312-cp312-win_amd64.whl", hash = "sha256:4ce35cc16ff34f23679c50dd3dfb199df10a4803b17e95f91595abd14232c5af"},
-    {file = "docling_parse-2.0.4-cp313-cp313-macosx_13_0_arm64.whl", hash = "sha256:e8cc56e41ae4caf4302ebeaaeb02de2b60edcf5ed4bdcdf13a67eca0c1b9f39a"},
+    {file = "docling_parse-2.1.0-cp313-cp313-macosx_13_0_arm64.whl", hash = "sha256:eb38e62bb4202025d8a5a2154cd383db13259707eb753307c7bf9f446d519364"},
-    {file = "docling_parse-2.0.4-cp313-cp313-macosx_13_0_x86_64.whl", hash = "sha256:bc2efba8183356c6437a62e9802055988f5edc2d907ea1a42a2613737b2fc77e"},
+    {file = "docling_parse-2.1.0-cp313-cp313-macosx_13_0_x86_64.whl", hash = "sha256:d76b5888cbad92410ec92c6deadf1c1a9467f4498c697a3330eacc51e0f6a5c4"},
-    {file = "docling_parse-2.0.4-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:db839a2a7a8742b93a5cab4d91c664938306d248177bc5b716527003c32054a3"},
+    {file = "docling_parse-2.1.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:610f64eba191a0501fb09bcad6b34b46f0d58179d5ef0e7071356ee35bc6b558"},
-    {file = "docling_parse-2.0.4-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:737fb79b6c91a676ac7cdf4ced65c85f687a968b9d1d2ef95b04958fbbc554ff"},
+    {file = "docling_parse-2.1.0-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:f15061e05ebbf15f723e0fedc26b4e473a6399e2890d9475a21a930eb61f1e93"},
-    {file = "docling_parse-2.0.4-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0c02edd935eb5d4d3b4a64564ac92f6a427bb106cb5632f745d853a6ba7b7441"},
+    {file = "docling_parse-2.1.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a2089530a3751dfa71ee0fa37d585fcb9496f1400e642b582d99f85afe79e851"},
-    {file = "docling_parse-2.0.4-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2e84a3c50086380fff7925cfd9e9e4e62b2d2f4b79660520999f39207d478b18"},
+    {file = "docling_parse-2.1.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b1ae020256c3593028011fda0af1de417329c868037698681a58a7d0a1e1a194"},
-    {file = "docling_parse-2.0.4-cp313-cp313-win_amd64.whl", hash = "sha256:99cfb99c1fc65573a45e2c99b98cc6483134451d42a81b9f4cea27e4e858415e"},
+    {file = "docling_parse-2.1.0-cp313-cp313-win_amd64.whl", hash = "sha256:5215ff823fcc2e65bd924731b0de16dbdd507424fce32745e15ac54fe059a045"},
-    {file = "docling_parse-2.0.4-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:2e2dbe4e18b6aa2f2fe8801685846d7b6a9bb355d6eac48b697cd9d1b62501e1"},
+    {file = "docling_parse-2.1.0-cp39-cp39-macosx_13_0_arm64.whl", hash = "sha256:0e002df567f09f0dd982cea0c17f287d55a0b953d2b13ee9bcc51a1c2e306cc0"},
-    {file = "docling_parse-2.0.4.tar.gz", hash = "sha256:bdcdfe070509e137846108056931e3738ad3225fcb31ed1496e9368690c3036d"},
+    {file = "docling_parse-2.1.0-cp39-cp39-macosx_13_0_x86_64.whl", hash = "sha256:9eef2c4c47586410083b6db9210bc2cef12af2eb67f8c88dcd2b46ca5010482b"},
+    {file = "docling_parse-2.1.0-cp39-cp39-macosx_14_0_arm64.whl", hash = "sha256:944cf36e4b9db0b1477e71f891321ea522498c8b9039a2acff52d85feed2f95e"},
+    {file = "docling_parse-2.1.0-cp39-cp39-macosx_14_0_x86_64.whl", hash = "sha256:68c357f66c0899ea1deb95a84ad929aaba10bc68bee2606563b1aae62d448186"},
+    {file = "docling_parse-2.1.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:26e98077db92fce59fe356a411c944525182f3cd8e9b3d228787439eb5429c63"},
+    {file = "docling_parse-2.1.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6dcacc29528f25ab65cf366829fad2584d2f23abbcf792e258a1de4ee0685f09"},
+    {file = "docling_parse-2.1.0-cp39-cp39-win_amd64.whl", hash = "sha256:9c7af4d68ca51ed7fa1170a7715a4ae97271cf30fce8b623bc8cce92aaa253e2"},
+    {file = "docling_parse-2.1.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:2316a5f4fd77ac673dace32cc6011f56fd1815941dc651df244a52cfd0bc70a6"},
+    {file = "docling_parse-2.1.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:540f4b7760addc6bf83358a6fb8853c50048bf9687ea0e89a79d515f75a26ac0"},
+    {file = "docling_parse-2.1.0.tar.gz", hash = "sha256:e8d39286f46842ba0a99f383b28712b7c8198a18be71b69fe2d4cf5105daa7f3"},
 ]
 
 [package.dependencies]
@@ -1648,13 +1656,13 @@ test = ["flaky", "ipyparallel", "pre-commit", "pytest (>=7.0)", "pytest-asyncio
 
 [[package]]
 name = "ipython"
-version = "8.29.0"
+version = "8.18.1"
 description = "IPython: Productive Interactive Computing"
 optional = false
-python-versions = ">=3.10"
+python-versions = ">=3.9"
 files = [
-    {file = "ipython-8.29.0-py3-none-any.whl", hash = "sha256:0188a1bd83267192123ccea7f4a8ed0a78910535dbaa3f37671dca76ebd429c8"},
+    {file = "ipython-8.18.1-py3-none-any.whl", hash = "sha256:e8267419d72d81955ec1177f8a29aaa90ac80ad647499201119e2f05e99aa397"},
-    {file = "ipython-8.29.0.tar.gz", hash = "sha256:40b60e15b22591450eef73e40a027cf77bd652e757523eebc5bd7c7c498290eb"},
+    {file = "ipython-8.18.1.tar.gz", hash = "sha256:ca6f079bb33457c66e233e4580ebfc4128855b4cf6370dddd73842a9563e8a27"},
 ]
 
 [package.dependencies]
@@ -1663,26 +1671,25 @@ decorator = "*"
 exceptiongroup = {version = "*", markers = "python_version < \"3.11\""}
 jedi = ">=0.16"
 matplotlib-inline = "*"
-pexpect = {version = ">4.3", markers = "sys_platform != \"win32\" and sys_platform != \"emscripten\""}
+pexpect = {version = ">4.3", markers = "sys_platform != \"win32\""}
 prompt-toolkit = ">=3.0.41,<3.1.0"
 pygments = ">=2.4.0"
 stack-data = "*"
-traitlets = ">=5.13.0"
+traitlets = ">=5"
-typing-extensions = {version = ">=4.6", markers = "python_version < \"3.12\""}
+typing-extensions = {version = "*", markers = "python_version < \"3.10\""}
 
 [package.extras]
-all = ["ipython[black,doc,kernel,matplotlib,nbconvert,nbformat,notebook,parallel,qtconsole]", "ipython[test,test-extra]"]
+all = ["black", "curio", "docrepr", "exceptiongroup", "ipykernel", "ipyparallel", "ipywidgets", "matplotlib", "matplotlib (!=3.2.0)", "nbconvert", "nbformat", "notebook", "numpy (>=1.22)", "pandas", "pickleshare", "pytest (<7)", "pytest (<7.1)", "pytest-asyncio (<0.22)", "qtconsole", "setuptools (>=18.5)", "sphinx (>=1.3)", "sphinx-rtd-theme", "stack-data", "testpath", "trio", "typing-extensions"]
 black = ["black"]
-doc = ["docrepr", "exceptiongroup", "intersphinx-registry", "ipykernel", "ipython[test]", "matplotlib", "setuptools (>=18.5)", "sphinx (>=1.3)", "sphinx-rtd-theme", "sphinxcontrib-jquery", "tomli", "typing-extensions"]
+doc = ["docrepr", "exceptiongroup", "ipykernel", "matplotlib", "pickleshare", "pytest (<7)", "pytest (<7.1)", "pytest-asyncio (<0.22)", "setuptools (>=18.5)", "sphinx (>=1.3)", "sphinx-rtd-theme", "stack-data", "testpath", "typing-extensions"]
 kernel = ["ipykernel"]
-matplotlib = ["matplotlib"]
 nbconvert = ["nbconvert"]
 nbformat = ["nbformat"]
 notebook = ["ipywidgets", "notebook"]
 parallel = ["ipyparallel"]
 qtconsole = ["qtconsole"]
-test = ["packaging", "pickleshare", "pytest", "pytest-asyncio (<0.22)", "testpath"]
+test = ["pickleshare", "pytest (<7.1)", "pytest-asyncio (<0.22)", "testpath"]
-test-extra = ["curio", "ipython[test]", "matplotlib (!=3.2.0)", "nbformat", "numpy (>=1.23)", "pandas", "trio"]
+test-extra = ["curio", "matplotlib (!=3.2.0)", "nbformat", "numpy (>=1.22)", "pandas", "pickleshare", "pytest (<7.1)", "pytest-asyncio (<0.22)", "testpath", "trio"]
 
 [[package]]
 name = "ipywidgets"
@@ -1936,6 +1943,7 @@ files = [
 ]
 
 [package.dependencies]
+importlib-metadata = {version = ">=4.8.3", markers = "python_version < \"3.10\""}
 jupyter-core = ">=4.12,<5.0.dev0 || >=5.1.dev0"
 python-dateutil = ">=2.8.2"
 pyzmq = ">=23.0"
@@ -2367,6 +2375,9 @@ files = [
     {file = "markdown-3.7.tar.gz", hash = "sha256:2ae2471477cfd02dbbf038d5d9bc226d40def84b4fe2986e49b59b6b472bbed2"},
 ]
 
+[package.dependencies]
+importlib-metadata = {version = ">=4.4", markers = "python_version < \"3.10\""}
+
 [package.extras]
 docs = ["mdx-gh-links (>=0.2)", "mkdocs (>=1.5)", "mkdocs-gen-files", "mkdocs-literate-nav", "mkdocs-nature (>=0.6)", "mkdocs-section-index", "mkdocstrings[python]"]
 testing = ["coverage", "pyyaml"]
@@ -2608,6 +2619,7 @@ files = [
 click = ">=7.0"
 colorama = {version = ">=0.4", markers = "platform_system == \"Windows\""}
 ghp-import = ">=1.0"
+importlib-metadata = {version = ">=4.4", markers = "python_version < \"3.10\""}
 jinja2 = ">=2.11.1"
 markdown = ">=3.3.6"
 markupsafe = ">=2.0.1"
@@ -2650,6 +2662,7 @@ files = [
 ]
 
 [package.dependencies]
+importlib-metadata = {version = ">=4.3", markers = "python_version < \"3.10\""}
 mergedeep = ">=1.3.4"
 platformdirs = ">=2.2.0"
 pyyaml = ">=5.1"
@@ -2970,6 +2983,7 @@ files = [
 beautifulsoup4 = "*"
 bleach = "!=5.0.0"
 defusedxml = "*"
+importlib-metadata = {version = ">=3.6", markers = "python_version < \"3.10\""}
 jinja2 = ">=3.0"
 jupyter-core = ">=4.7"
 jupyterlab-pygments = "*"
@@ -3046,21 +3060,20 @@ files = [
 
 [[package]]
 name = "networkx"
-version = "3.4.2"
+version = "3.2.1"
 description = "Python package for creating and manipulating graphs and networks"
 optional = false
-python-versions = ">=3.10"
+python-versions = ">=3.9"
 files = [
-    {file = "networkx-3.4.2-py3-none-any.whl", hash = "sha256:df5d4365b724cf81b8c6a7312509d0c22386097011ad1abe274afd5e9d3bbc5f"},
+    {file = "networkx-3.2.1-py3-none-any.whl", hash = "sha256:f18c69adc97877c42332c170849c96cefa91881c99a7cb3e95b7c659ebdc1ec2"},
-    {file = "networkx-3.4.2.tar.gz", hash = "sha256:307c3669428c5362aab27c8a1260aa8f47c4e91d3891f48be0141738d8d053e1"},
+    {file = "networkx-3.2.1.tar.gz", hash = "sha256:9f1bb5cf3409bf324e0a722c20bdb4c20ee39bf1c30ce8ae499c8502b0b5e0c6"},
 ]
 
 [package.extras]
-default = ["matplotlib (>=3.7)", "numpy (>=1.24)", "pandas (>=2.0)", "scipy (>=1.10,!=1.11.0,!=1.11.1)"]
+default = ["matplotlib (>=3.5)", "numpy (>=1.22)", "pandas (>=1.4)", "scipy (>=1.9,!=1.11.0,!=1.11.1)"]
-developer = ["changelist (==0.5)", "mypy (>=1.1)", "pre-commit (>=3.2)", "rtoml"]
+developer = ["changelist (==0.4)", "mypy (>=1.1)", "pre-commit (>=3.2)", "rtoml"]
-doc = ["intersphinx-registry", "myst-nb (>=1.1)", "numpydoc (>=1.8.0)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.15)", "sphinx (>=7.3)", "sphinx-gallery (>=0.16)", "texext (>=0.6.7)"]
+doc = ["nb2plots (>=0.7)", "nbconvert (<7.9)", "numpydoc (>=1.6)", "pillow (>=9.4)", "pydata-sphinx-theme (>=0.14)", "sphinx (>=7)", "sphinx-gallery (>=0.14)", "texext (>=0.6.7)"]
-example = ["cairocffi (>=1.7)", "contextily (>=1.6)", "igraph (>=0.11)", "momepy (>=0.7.2)", "osmnx (>=1.9)", "scikit-learn (>=1.5)", "seaborn (>=0.13)"]
+extra = ["lxml (>=4.6)", "pydot (>=1.4.2)", "pygraphviz (>=1.11)", "sympy (>=1.10)"]
-extra = ["lxml (>=4.6)", "pydot (>=3.0.1)", "pygraphviz (>=1.14)", "sympy (>=1.10)"]
 test = ["pytest (>=7.2)", "pytest-cov (>=4.0)"]
 
 [[package]]
@@ -3532,6 +3545,22 @@ files = [
     {file = "nvidia_nvtx_cu12-12.4.127-py3-none-win_amd64.whl", hash = "sha256:641dccaaa1139f3ffb0d3164b4b84f9d253397e38246a4f2f36728b48566d485"},
 ]
 
+[[package]]
+name = "ocrmac"
+version = "1.0.0"
+description = "A python wrapper to extract text from images on a mac system. Uses the vision framework from Apple."
+optional = true
+python-versions = ">=3.6"
+files = [
+    {file = "ocrmac-1.0.0-py2.py3-none-any.whl", hash = "sha256:0b5a072aa23a9ead48132cb2d595b680aa6c3c5a6cb69525155e35ca95610c3a"},
+    {file = "ocrmac-1.0.0.tar.gz", hash = "sha256:5b299e9030c973d1f60f82db000d6c2e5ff271601878c7db0885e850597d1d2e"},
+]
+
+[package.dependencies]
+Click = ">=7.0"
+pillow = "*"
+pyobjc-framework-Vision = "*"
+
 [[package]]
 name = "opencv-python-headless"
 version = "4.10.0.84"
@@ -3551,9 +3580,11 @@ files = [
 [package.dependencies]
 numpy = [
     {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
+    {version = ">=1.21.0", markers = "python_version == \"3.9\" and platform_system == \"Darwin\" and platform_machine == \"arm64\""},
+    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
     {version = ">=1.21.4", markers = "python_version >= \"3.10\" and platform_system == \"Darwin\" and python_version < \"3.11\""},
     {version = ">=1.21.2", markers = "platform_system != \"Darwin\" and python_version >= \"3.10\" and python_version < \"3.11\""},
-    {version = ">=1.23.5", markers = "python_version >= \"3.11\" and python_version < \"3.12\""},
+    {version = ">=1.19.3", markers = "platform_system == \"Linux\" and platform_machine == \"aarch64\" and python_version >= \"3.8\" and python_version < \"3.10\" or python_version > \"3.9\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_system != \"Darwin\" and python_version < \"3.10\" or python_version >= \"3.9\" and platform_machine != \"arm64\" and python_version < \"3.10\""},
 ]
 
 [[package]]
@@ -3751,13 +3782,13 @@ xml = ["lxml (>=4.9.2)"]
 
 [[package]]
 name = "pandas-stubs"
-version = "2.2.3.241009"
+version = "2.2.2.240807"
 description = "Type annotations for pandas"
 optional = false
-python-versions = ">=3.10"
+python-versions = ">=3.9"
 files = [
-    {file = "pandas_stubs-2.2.3.241009-py3-none-any.whl", hash = "sha256:3a6f8f142105a42550be677ba741ba532621f4e0acad2155c0e7b2450f114cfa"},
+    {file = "pandas_stubs-2.2.2.240807-py3-none-any.whl", hash = "sha256:893919ad82be4275f0d07bb47a95d08bae580d3fdea308a7acfcb3f02e76186e"},
-    {file = "pandas_stubs-2.2.3.241009.tar.gz", hash = "sha256:d4ab618253f0acf78a5d0d2bfd6dffdd92d91a56a69bdc8144e5a5c6d25be3b5"},
+    {file = "pandas_stubs-2.2.2.240807.tar.gz", hash = "sha256:64a559725a57a449f46225fbafc422520b7410bff9252b661a225b5559192a93"},
 ]
 
 [package.dependencies]
@@ -4492,6 +4523,7 @@ mccabe = ">=0.6,<0.8"
 platformdirs = ">=2.2.0"
 tomli = {version = ">=1.1.0", markers = "python_version < \"3.11\""}
 tomlkit = ">=0.10.1"
+typing-extensions = {version = ">=3.10.0", markers = "python_version < \"3.10\""}
 
 [package.extras]
 spelling = ["pyenchant (>=3.2,<4.0)"]
@@ -4540,6 +4572,102 @@ bulk-writer = ["azure-storage-blob", "minio (>=7.0.0)", "pyarrow (>=12.0.0)", "r
 dev = ["black", "grpcio (==1.62.2)", "grpcio-testing (==1.62.2)", "grpcio-tools (==1.62.2)", "pytest (>=5.3.4)", "pytest-cov (>=2.8.1)", "pytest-timeout (>=1.3.4)", "ruff (>0.4.0)"]
 model = ["milvus-model (>=0.1.0)"]
 
+[[package]]
+name = "pyobjc-core"
+version = "10.3.1"
+description = "Python<->ObjC Interoperability Module"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "pyobjc_core-10.3.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:ea46d2cda17921e417085ac6286d43ae448113158afcf39e0abe484c58fb3d78"},
+    {file = "pyobjc_core-10.3.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:899d3c84d2933d292c808f385dc881a140cf08632907845043a333a9d7c899f9"},
+    {file = "pyobjc_core-10.3.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:6ff5823d13d0a534cdc17fa4ad47cf5bee4846ce0fd27fc40012e12b46db571b"},
+    {file = "pyobjc_core-10.3.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:2581e8e68885bcb0e11ec619e81ef28e08ee3fac4de20d8cc83bc5af5bcf4a90"},
+    {file = "pyobjc_core-10.3.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:ea98d4c2ec39ca29e62e0327db21418696161fb138ee6278daf2acbedf7ce504"},
+    {file = "pyobjc_core-10.3.1-cp38-cp38-macosx_11_0_universal2.whl", hash = "sha256:4c179c26ee2123d0aabffb9dbc60324b62b6f8614fb2c2328b09386ef59ef6d8"},
+    {file = "pyobjc_core-10.3.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:cb901fce65c9be420c40d8a6ee6fff5ff27c6945f44fd7191989b982baa66dea"},
+    {file = "pyobjc_core-10.3.1.tar.gz", hash = "sha256:b204a80ccc070f9ab3f8af423a3a25a6fd787e228508d00c4c30f8ac538ba720"},
+]
+
+[[package]]
+name = "pyobjc-framework-cocoa"
+version = "10.3.1"
+description = "Wrappers for the Cocoa frameworks on macOS"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "pyobjc_framework_Cocoa-10.3.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:4cb4f8491ab4d9b59f5187e42383f819f7a46306a4fa25b84f126776305291d1"},
+    {file = "pyobjc_framework_Cocoa-10.3.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:5f31021f4f8fdf873b57a97ee1f3c1620dbe285e0b4eaed73dd0005eb72fd773"},
+    {file = "pyobjc_framework_Cocoa-10.3.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:11b4e0bad4bbb44a4edda128612f03cdeab38644bbf174de0c13129715497296"},
+    {file = "pyobjc_framework_Cocoa-10.3.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:de5e62e5ccf2871a94acf3bf79646b20ea893cc9db78afa8d1fe1b0d0f7cbdb0"},
+    {file = "pyobjc_framework_Cocoa-10.3.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:6c5af24610ab639bd1f521ce4500484b40787f898f691b7a23da3339e6bc8b90"},
+    {file = "pyobjc_framework_Cocoa-10.3.1-cp38-cp38-macosx_11_0_universal2.whl", hash = "sha256:a7151186bb7805deea434fae9a4423335e6371d105f29e73cc2036c6779a9dbc"},
+    {file = "pyobjc_framework_Cocoa-10.3.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:743d2a1ac08027fd09eab65814c79002a1d0421d7c0074ffd1217b6560889744"},
+    {file = "pyobjc_framework_cocoa-10.3.1.tar.gz", hash = "sha256:1cf20714daaa986b488fb62d69713049f635c9d41a60c8da97d835710445281a"},
+]
+
+[package.dependencies]
+pyobjc-core = ">=10.3.1"
+
+[[package]]
+name = "pyobjc-framework-coreml"
+version = "10.3.1"
+description = "Wrappers for the framework CoreML on macOS"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "pyobjc_framework_CoreML-10.3.1-cp36-abi3-macosx_10_13_universal2.whl", hash = "sha256:c1fdcc0487807afa9cd0f88f25697e0e2e093d0219e8e1aa42aa3674dd78c2cb"},
+    {file = "pyobjc_framework_CoreML-10.3.1-cp36-abi3-macosx_10_9_universal2.whl", hash = "sha256:21c87e84c807b5dbe61e0f016d9aefa32d3212f175cc4b976b5c08770be7a58c"},
+    {file = "pyobjc_framework_CoreML-10.3.1-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:a0877aed5d4cdbb63d1246cd5384c09d78a0667e83c435a1257d10017c11c1a4"},
+    {file = "pyobjc_framework_CoreML-10.3.1-cp36-abi3-macosx_11_0_universal2.whl", hash = "sha256:4bd3f1acfb3245727727b71cbcf7d21a33d7e00fa488e41ad01527764b969b92"},
+    {file = "pyobjc_framework_coreml-10.3.1.tar.gz", hash = "sha256:6b7091142cfaafee76f1a804329e7a4e3aeca921eea8644e9ceba4cc2751f705"},
+]
+
+[package.dependencies]
+pyobjc-core = ">=10.3.1"
+pyobjc-framework-Cocoa = ">=10.3.1"
+
+[[package]]
+name = "pyobjc-framework-quartz"
+version = "10.3.1"
+description = "Wrappers for the Quartz frameworks on macOS"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "pyobjc_framework_Quartz-10.3.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:5ef4fd315ed2bc42ef77fdeb2bae28a88ec986bd7b8079a87ba3b3475348f96e"},
+    {file = "pyobjc_framework_Quartz-10.3.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:96578d4a3e70164efe44ad7dc320ecd4e211758ffcde5dcd694de1bbdfe090a4"},
+    {file = "pyobjc_framework_Quartz-10.3.1-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:ca35f92486869a41847a1703bb176aab8a53dbfd8e678d1f4d68d8e6e1581c71"},
+    {file = "pyobjc_framework_Quartz-10.3.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:00a0933267e3a46ea4afcc35d117b2efb920f06de797fa66279c52e7057e3590"},
+    {file = "pyobjc_framework_Quartz-10.3.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:a161bedb4c5257a02ad56a910cd7eefb28bdb0ea78607df0d70ed4efe4ea54c1"},
+    {file = "pyobjc_framework_Quartz-10.3.1-cp38-cp38-macosx_11_0_universal2.whl", hash = "sha256:d7a8028e117a94923a511944bfa9daf9744e212f06cf89010c60934a479863a5"},
+    {file = "pyobjc_framework_Quartz-10.3.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:de00c983b3267eb26fa42c6ed9f15e2bf006bde8afa7fe2b390646aa21a5d6fc"},
+    {file = "pyobjc_framework_quartz-10.3.1.tar.gz", hash = "sha256:b6d7e346d735c9a7f147cd78e6da79eeae416a0b7d3874644c83a23786c6f886"},
+]
+
+[package.dependencies]
+pyobjc-core = ">=10.3.1"
+pyobjc-framework-Cocoa = ">=10.3.1"
+
+[[package]]
+name = "pyobjc-framework-vision"
+version = "10.3.1"
+description = "Wrappers for the framework Vision on macOS"
+optional = true
+python-versions = ">=3.8"
+files = [
+    {file = "pyobjc_framework_Vision-10.3.1-cp36-abi3-macosx_10_13_universal2.whl", hash = "sha256:dff3582678930461a0bb11bf070854d49f6944a851dc89edc63fac93c75ddf39"},
+    {file = "pyobjc_framework_Vision-10.3.1-cp36-abi3-macosx_10_9_universal2.whl", hash = "sha256:32626183c51674efb3b5738e2884c3fea37edca010117cf71bd72cb3c49c869a"},
+    {file = "pyobjc_framework_Vision-10.3.1-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:2473b346a112c51ac485184305bd13c402e0db45f2df3d277315bd49efba18e9"},
+    {file = "pyobjc_framework_Vision-10.3.1-cp36-abi3-macosx_11_0_universal2.whl", hash = "sha256:4302e2c5f68c9667ecd4273809cbc4611af6368b123d69596e5b088f1b1aa16b"},
+    {file = "pyobjc_framework_vision-10.3.1.tar.gz", hash = "sha256:aa071656d395afc2d624600a9f30d6a3344aa747bf37f613ff3972158c40881c"},
+]
+
+[package.dependencies]
+pyobjc-core = ">=10.3.1"
+pyobjc-framework-Cocoa = ">=10.3.1"
+pyobjc-framework-CoreML = ">=10.3.1"
+pyobjc-framework-Quartz = ">=10.3.1"
+
 [[package]]
 name = "pypdfium2"
 version = "4.30.0"
@@ -5663,53 +5791,45 @@ tests = ["black (>=24.3.0)", "matplotlib (>=3.3.4)", "mypy (>=1.9)", "numpydoc (
 
 [[package]]
 name = "scipy"
-version = "1.14.1"
+version = "1.13.1"
 description = "Fundamental algorithms for scientific computing in Python"
 optional = false
-python-versions = ">=3.10"
+python-versions = ">=3.9"
 files = [
-    {file = "scipy-1.14.1-cp310-cp310-macosx_10_13_x86_64.whl", hash = "sha256:b28d2ca4add7ac16ae8bb6632a3c86e4b9e4d52d3e34267f6e1b0c1f8d87e389"},
+    {file = "scipy-1.13.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:20335853b85e9a49ff7572ab453794298bcf0354d8068c5f6775a0eabf350aca"},
-    {file = "scipy-1.14.1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:d0d2821003174de06b69e58cef2316a6622b60ee613121199cb2852a873f8cf3"},
+    {file = "scipy-1.13.1-cp310-cp310-macosx_12_0_arm64.whl", hash = "sha256:d605e9c23906d1994f55ace80e0125c587f96c020037ea6aa98d01b4bd2e222f"},
-    {file = "scipy-1.14.1-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:8bddf15838ba768bb5f5083c1ea012d64c9a444e16192762bd858f1e126196d0"},
+    {file = "scipy-1.13.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cfa31f1def5c819b19ecc3a8b52d28ffdcc7ed52bb20c9a7589669dd3c250989"},
-    {file = "scipy-1.14.1-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:97c5dddd5932bd2a1a31c927ba5e1463a53b87ca96b5c9bdf5dfd6096e27efc3"},
+    {file = "scipy-1.13.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f26264b282b9da0952a024ae34710c2aff7d27480ee91a2e82b7b7073c24722f"},
-    {file = "scipy-1.14.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2ff0a7e01e422c15739ecd64432743cf7aae2b03f3084288f399affcefe5222d"},
+    {file = "scipy-1.13.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:eccfa1906eacc02de42d70ef4aecea45415f5be17e72b61bafcfd329bdc52e94"},
-    {file = "scipy-1.14.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8e32dced201274bf96899e6491d9ba3e9a5f6b336708656466ad0522d8528f69"},
+    {file = "scipy-1.13.1-cp310-cp310-win_amd64.whl", hash = "sha256:2831f0dc9c5ea9edd6e51e6e769b655f08ec6db6e2e10f86ef39bd32eb11da54"},
-    {file = "scipy-1.14.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:8426251ad1e4ad903a4514712d2fa8fdd5382c978010d1c6f5f37ef286a713ad"},
+    {file = "scipy-1.13.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:27e52b09c0d3a1d5b63e1105f24177e544a222b43611aaf5bc44d4a0979e32f9"},
-    {file = "scipy-1.14.1-cp310-cp310-win_amd64.whl", hash = "sha256:a49f6ed96f83966f576b33a44257d869756df6cf1ef4934f59dd58b25e0327e5"},
+    {file = "scipy-1.13.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:54f430b00f0133e2224c3ba42b805bfd0086fe488835effa33fa291561932326"},
-    {file = "scipy-1.14.1-cp311-cp311-macosx_10_13_x86_64.whl", hash = "sha256:2da0469a4ef0ecd3693761acbdc20f2fdeafb69e6819cc081308cc978153c675"},
+    {file = "scipy-1.13.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e89369d27f9e7b0884ae559a3a956e77c02114cc60a6058b4e5011572eea9299"},
-    {file = "scipy-1.14.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:c0ee987efa6737242745f347835da2cc5bb9f1b42996a4d97d5c7ff7928cb6f2"},
+    {file = "scipy-1.13.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a78b4b3345f1b6f68a763c6e25c0c9a23a9fd0f39f5f3d200efe8feda560a5fa"},
-    {file = "scipy-1.14.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:3a1b111fac6baec1c1d92f27e76511c9e7218f1695d61b59e05e0fe04dc59617"},
+    {file = "scipy-1.13.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:45484bee6d65633752c490404513b9ef02475b4284c4cfab0ef946def50b3f59"},
-    {file = "scipy-1.14.1-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:8475230e55549ab3f207bff11ebfc91c805dc3463ef62eda3ccf593254524ce8"},
+    {file = "scipy-1.13.1-cp311-cp311-win_amd64.whl", hash = "sha256:5713f62f781eebd8d597eb3f88b8bf9274e79eeabf63afb4a737abc6c84ad37b"},
-    {file = "scipy-1.14.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:278266012eb69f4a720827bdd2dc54b2271c97d84255b2faaa8f161a158c3b37"},
+    {file = "scipy-1.13.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:5d72782f39716b2b3509cd7c33cdc08c96f2f4d2b06d51e52fb45a19ca0c86a1"},
-    {file = "scipy-1.14.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fef8c87f8abfb884dac04e97824b61299880c43f4ce675dd2cbeadd3c9b466d2"},
+    {file = "scipy-1.13.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:017367484ce5498445aade74b1d5ab377acdc65e27095155e448c88497755a5d"},
-    {file = "scipy-1.14.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b05d43735bb2f07d689f56f7b474788a13ed8adc484a85aa65c0fd931cf9ccd2"},
+    {file = "scipy-1.13.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:949ae67db5fa78a86e8fa644b9a6b07252f449dcf74247108c50e1d20d2b4627"},
-    {file = "scipy-1.14.1-cp311-cp311-win_amd64.whl", hash = "sha256:716e389b694c4bb564b4fc0c51bc84d381735e0d39d3f26ec1af2556ec6aad94"},
+    {file = "scipy-1.13.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:de3ade0e53bc1f21358aa74ff4830235d716211d7d077e340c7349bc3542e884"},
-    {file = "scipy-1.14.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:631f07b3734d34aced009aaf6fedfd0eb3498a97e581c3b1e5f14a04164a456d"},
+    {file = "scipy-1.13.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:2ac65fb503dad64218c228e2dc2d0a0193f7904747db43014645ae139c8fad16"},
-    {file = "scipy-1.14.1-cp312-cp312-macosx_12_0_arm64.whl", hash = "sha256:af29a935803cc707ab2ed7791c44288a682f9c8107bc00f0eccc4f92c08d6e07"},
+    {file = "scipy-1.13.1-cp312-cp312-win_amd64.whl", hash = "sha256:cdd7dacfb95fea358916410ec61bbc20440f7860333aee6d882bb8046264e949"},
-    {file = "scipy-1.14.1-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:2843f2d527d9eebec9a43e6b406fb7266f3af25a751aa91d62ff416f54170bc5"},
+    {file = "scipy-1.13.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:436bbb42a94a8aeef855d755ce5a465479c721e9d684de76bf61a62e7c2b81d5"},
-    {file = "scipy-1.14.1-cp312-cp312-macosx_14_0_x86_64.whl", hash = "sha256:eb58ca0abd96911932f688528977858681a59d61a7ce908ffd355957f7025cfc"},
+    {file = "scipy-1.13.1-cp39-cp39-macosx_12_0_arm64.whl", hash = "sha256:8335549ebbca860c52bf3d02f80784e91a004b71b059e3eea9678ba994796a24"},
-    {file = "scipy-1.14.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:30ac8812c1d2aab7131a79ba62933a2a76f582d5dbbc695192453dae67ad6310"},
+    {file = "scipy-1.13.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d533654b7d221a6a97304ab63c41c96473ff04459e404b83275b60aa8f4b7004"},
-    {file = "scipy-1.14.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f9ea80f2e65bdaa0b7627fb00cbeb2daf163caa015e59b7516395fe3bd1e066"},
+    {file = "scipy-1.13.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:637e98dcf185ba7f8e663e122ebf908c4702420477ae52a04f9908707456ba4d"},
-    {file = "scipy-1.14.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:edaf02b82cd7639db00dbff629995ef185c8df4c3ffa71a5562a595765a06ce1"},
+    {file = "scipy-1.13.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:a014c2b3697bde71724244f63de2476925596c24285c7a637364761f8710891c"},
-    {file = "scipy-1.14.1-cp312-cp312-win_amd64.whl", hash = "sha256:2ff38e22128e6c03ff73b6bb0f85f897d2362f8c052e3b8ad00532198fbdae3f"},
+    {file = "scipy-1.13.1-cp39-cp39-win_amd64.whl", hash = "sha256:392e4ec766654852c25ebad4f64e4e584cf19820b980bc04960bca0b0cd6eaa2"},
-    {file = "scipy-1.14.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:1729560c906963fc8389f6aac023739ff3983e727b1a4d87696b7bf108316a79"},
+    {file = "scipy-1.13.1.tar.gz", hash = "sha256:095a87a0312b08dfd6a6155cbbd310a8c51800fc931b8c0b84003014b874ed3c"},
-    {file = "scipy-1.14.1-cp313-cp313-macosx_12_0_arm64.whl", hash = "sha256:4079b90df244709e675cdc8b93bfd8a395d59af40b72e339c2287c91860deb8e"},
-    {file = "scipy-1.14.1-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:e0cf28db0f24a38b2a0ca33a85a54852586e43cf6fd876365c86e0657cfe7d73"},
-    {file = "scipy-1.14.1-cp313-cp313-macosx_14_0_x86_64.whl", hash = "sha256:0c2f95de3b04e26f5f3ad5bb05e74ba7f68b837133a4492414b3afd79dfe540e"},
-    {file = "scipy-1.14.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b99722ea48b7ea25e8e015e8341ae74624f72e5f21fc2abd45f3a93266de4c5d"},
-    {file = "scipy-1.14.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5149e3fd2d686e42144a093b206aef01932a0059c2a33ddfa67f5f035bdfe13e"},
-    {file = "scipy-1.14.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:e4f5a7c49323533f9103d4dacf4e4f07078f360743dec7f7596949149efeec06"},
-    {file = "scipy-1.14.1-cp313-cp313-win_amd64.whl", hash = "sha256:baff393942b550823bfce952bb62270ee17504d02a1801d7fd0719534dfb9c84"},
-    {file = "scipy-1.14.1.tar.gz", hash = "sha256:5a275584e726026a5699459aa72f828a610821006228e841b94275c4a7c08417"},
 ]
 
 [package.dependencies]
-numpy = ">=1.23.5,<2.3"
+numpy = ">=1.22.4,<2.3"
 
 [package.extras]
-dev = ["cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy (==1.10.0)", "pycodestyle", "pydevtool", "rich-click", "ruff (>=0.0.292)", "types-psutil", "typing_extensions"]
+dev = ["cython-lint (>=0.12.2)", "doit (>=0.36.0)", "mypy", "pycodestyle", "pydevtool", "rich-click", "ruff", "types-psutil", "typing_extensions"]
-doc = ["jupyterlite-pyodide-kernel", "jupyterlite-sphinx (>=0.13.1)", "jupytext", "matplotlib (>=3.5)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (>=0.15.2)", "sphinx (>=5.0.0,<=7.3.7)", "sphinx-design (>=0.4.0)"]
+doc = ["jupyterlite-pyodide-kernel", "jupyterlite-sphinx (>=0.12.0)", "jupytext", "matplotlib (>=3.5)", "myst-nb", "numpydoc", "pooch", "pydata-sphinx-theme (>=0.15.2)", "sphinx (>=5.0.0)", "sphinx-design (>=0.4.0)"]
-test = ["Cython", "array-api-strict (>=2.0)", "asv", "gmpy2", "hypothesis (>=6.30)", "meson", "mpmath", "ninja", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
+test = ["array-api-strict", "asv", "gmpy2", "hypothesis (>=6.30)", "mpmath", "pooch", "pytest", "pytest-cov", "pytest-timeout", "pytest-xdist", "scikit-umfpack", "threadpoolctl"]
 
 [[package]]
 name = "secretstorage"
@@ -6027,13 +6147,13 @@ files = [
 
 [[package]]
 name = "tifffile"
-version = "2024.9.20"
+version = "2024.8.30"
 description = "Read and write TIFF files"
 optional = false
-python-versions = ">=3.10"
+python-versions = ">=3.9"
 files = [
-    {file = "tifffile-2024.9.20-py3-none-any.whl", hash = "sha256:c54dc85bc1065d972cb8a6ffb3181389d597876aa80177933459733e4ed243dd"},
+    {file = "tifffile-2024.8.30-py3-none-any.whl", hash = "sha256:8bc59a8f02a2665cd50a910ec64961c5373bee0b8850ec89d3b7b485bf7be7ad"},
-    {file = "tifffile-2024.9.20.tar.gz", hash = "sha256:3fbf3be2f995a7051a8ae05a4be70c96fc0789f22ed6f1c4104c973cf68a640b"},
+    {file = "tifffile-2024.8.30.tar.gz", hash = "sha256:2c9508fe768962e30f87def61819183fb07692c258cb175b3c114828368485a4"},
 ]
 
 [package.dependencies]
@@ -7232,10 +7352,10 @@ test = ["big-O", "importlib-resources", "jaraco.functools", "jaraco.itertools",
 type = ["pytest-mypy"]
 
 [extras]
-paddleocr = []
+ocrmac = ["ocrmac"]
 tesserocr = ["tesserocr"]
 
 [metadata]
 lock-version = "2.0"
-python-versions = "^3.10"
+python-versions = "^3.9"
-content-hash = "679c46aadb43260cba2dcfa91648456334dbce5d0fc7f515504ba4e555b4970c"
+content-hash = "de2354d1c01d11017a742eb0bf826b08aaaeec5e84f62f0e2101c3bc685b7a6f"

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "2.6.0"  # DO NOT EDIT, updated automatically
+version = "2.7.0"  # DO NOT EDIT, updated automatically
 description = "SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications."
 authors = ["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 = "MIT"
@@ -24,10 +24,10 @@ packages = [{include = "docling"}]
 ######################
 # actual dependencies:
 ######################
-python = "^3.10"
+python = "^3.9"
 pydantic = "^2.0.0"
 docling-core = "^2.4.0"
-docling-ibm-models = "^2.0.3"
+docling-ibm-models = "^2.0.6"
 deepsearch-glm = "^0.26.1"
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
@@ -36,10 +36,10 @@ huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = "^1.7"
 tesserocr = { version = "^2.7.1", optional = true }
-docling-parse = "^2.0.2"
+docling-parse = "^2.0.5"
 certifi = ">=2024.7.4"
 rtree = "^1.3.0"
-scipy = "^1.14.1"
+scipy = "^1.6.0"
 pyarrow = "^16.1.0"
 typer = "^0.12.5"
 python-docx = "^1.1.2"
@@ -48,6 +48,7 @@ beautifulsoup4 = "^4.12.3"
 pandas = "^2.1.4"
 marko = "^2.1.2"
 openpyxl = "^3.1.5"
+ocrmac = { version = "^1.0.0", markers = "sys_platform == 'darwin'", optional = true }
 
 [tool.poetry.group.dev.dependencies]
 black = {extras = ["jupyter"], version = "^24.4.2"}
@@ -80,6 +81,12 @@ langchain-huggingface = "^0.0.3"
 langchain-milvus = "^0.1.4"
 langchain-text-splitters = "^0.2.4"
 
+[tool.poetry.group.constraints.dependencies]
+numpy = [
+    { version = "^2.1.0", markers = 'python_version >= "3.13"' },
+    { version = "^1.24.4", markers = 'python_version < "3.13"' },
+]
+
 [tool.poetry.group.mac_intel]
 optional = true
 
@@ -95,7 +102,7 @@ torchvision = [
 
 [tool.poetry.extras]
 tesserocr = ["tesserocr"]
-paddleocr = ["paddlepaddle", "paddleocr"]
+ocrmac = ["ocrmac"]
 
 [tool.poetry.scripts]
 docling = "docling.cli.main:app"
@@ -106,13 +113,13 @@ build-backend = "poetry.core.masonry.api"
 
 [tool.black]
 line-length = 88
-target-version = ["py310"]
+target-version = ["py39"]
 include = '\.pyi?$'
 
 [tool.isort]
 profile = "black"
 line_length = 88
-py_version=311
+py_version=39
 
 [tool.mypy]
 pretty = true
@@ -131,6 +138,7 @@ module = [
     "tesserocr.*",
     "docling_ibm_models.*",
     "easyocr.*",
+    "ocrmac.*",
     "deepsearch_glm.*",
     "lxml.*",
     "bs4.*",

tests/test_e2e_ocr_conversion.py

@@ -1,3 +1,4 @@
+import sys
 from pathlib import Path
 from typing import List
 
@@ -6,6 +7,7 @@ from docling.datamodel.base_models import InputFormat
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
+    OcrMacOptions,
     OcrOptions,
     PdfPipelineOptions,
     TesseractCliOcrOptions,
@@ -62,6 +64,11 @@ def test_e2e_conversions():
         PaddleOcrOptions(force_full_page_ocr=True),
     ]
 
+    # only works on mac
+    if "darwin" == sys.platform:
+        engines.append(OcrMacOptions())
+        engines.append(OcrMacOptions(force_full_page_ocr=True))
+
     for ocr_options in engines:
         print(f"Converting with ocr_engine: {ocr_options.kind}")
         converter = get_converter(ocr_options=ocr_options)