feat: Add DoclingParseV4 backend, using high-level docling-parse API (#905)

* Add DoclingParseV3 backend implementation

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Use docling-core with docling-parse types

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fixes and test updates

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix streams

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fix streams

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Reset tests

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* update test cases

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* update test units

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Add back DoclingParse v1 backend, pipeline options

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update locks

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* fix: update docling-core to 2.22.0

Update dependency library docling-core to latest release 2.22.0
Fix regression tests and ground truth files

Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

* Ground-truth files updated

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Update tests, use TextCell.from_ocr property

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Text fixes, new test data

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Rename docling backend to v4

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Test all backends, fixes

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Reset all tests to use docling-parse v1 for now

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* Fixes for DPv4 backend init, better test coverage

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

* test_input_doc use default backend

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>

---------

Signed-off-by: Christoph Auer <cau@zurich.ibm.com>
Signed-off-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>
Co-authored-by: Cesar Berrospi Ramis <75900930+ceberam@users.noreply.github.com>

docling/backend/docling_parse_backend.py

@@ -6,12 +6,12 @@ from typing import Iterable, List, Optional, Union
 
 import pypdfium2 as pdfium
 from docling_core.types.doc import BoundingBox, CoordOrigin, Size
+from docling_core.types.doc.page import BoundingRectangle, SegmentedPdfPage, TextCell
 from docling_parse.pdf_parsers import pdf_parser_v1
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage
 
 from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
-from docling.datamodel.base_models import Cell
 from docling.datamodel.document import InputDocument
 
 _log = logging.getLogger(__name__)
@@ -68,8 +68,11 @@ class DoclingParsePageBackend(PdfPageBackend):
 
         return text_piece
 
-    def get_text_cells(self) -> Iterable[Cell]:
-        cells: List[Cell] = []
+    def get_segmented_page(self) -> Optional[SegmentedPdfPage]:
+        return None
+
+    def get_text_cells(self) -> Iterable[TextCell]:
+        cells: List[TextCell] = []
         cell_counter = 0
 
         if not self.valid:
@@ -91,19 +94,24 @@ class DoclingParsePageBackend(PdfPageBackend):
 
             text_piece = self._dpage["cells"][i]["content"]["rnormalized"]
             cells.append(
-                Cell(
-                    id=cell_counter,
+                TextCell(
+                    index=cell_counter,
                     text=text_piece,
-                    bbox=BoundingBox(
-                        # l=x0, b=y0, r=x1, t=y1,
-                        l=x0 * page_size.width / parser_width,
-                        b=y0 * page_size.height / parser_height,
-                        r=x1 * page_size.width / parser_width,
-                        t=y1 * page_size.height / parser_height,
-                        coord_origin=CoordOrigin.BOTTOMLEFT,
+                    orig=text_piece,
+                    from_ocr=False,
+                    rect=BoundingRectangle.from_bounding_box(
+                        BoundingBox(
+                            # l=x0, b=y0, r=x1, t=y1,
+                            l=x0 * page_size.width / parser_width,
+                            b=y0 * page_size.height / parser_height,
+                            r=x1 * page_size.width / parser_width,
+                            t=y1 * page_size.height / parser_height,
+                            coord_origin=CoordOrigin.BOTTOMLEFT,
+                        )
                     ).to_top_left_origin(page_size.height),
                 )
             )
+
             cell_counter += 1
 
         def draw_clusters_and_cells():
@@ -112,7 +120,7 @@ class DoclingParsePageBackend(PdfPageBackend):
             )  # make new image to avoid drawing on the saved ones
             draw = ImageDraw.Draw(image)
             for c in cells:
-                x0, y0, x1, y1 = c.bbox.as_tuple()
+                x0, y0, x1, y1 = c.rect.to_bounding_box().as_tuple()
                 cell_color = (
                     random.randint(30, 140),
                     random.randint(30, 140),

docling/backend/docling_parse_v2_backend.py

@@ -6,12 +6,13 @@ from typing import TYPE_CHECKING, Iterable, List, Optional, Union
 
 import pypdfium2 as pdfium
 from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle, SegmentedPdfPage, TextCell
 from docling_parse.pdf_parsers import pdf_parser_v2
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfPage
 
 from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
-from docling.datamodel.base_models import Cell, Size
+from docling.datamodel.base_models import Size
 from docling.utils.locks import pypdfium2_lock
 
 if TYPE_CHECKING:
@@ -78,8 +79,11 @@ class DoclingParseV2PageBackend(PdfPageBackend):
 
         return text_piece
 
-    def get_text_cells(self) -> Iterable[Cell]:
-        cells: List[Cell] = []
+    def get_segmented_page(self) -> Optional[SegmentedPdfPage]:
+        return None
+
+    def get_text_cells(self) -> Iterable[TextCell]:
+        cells: List[TextCell] = []
         cell_counter = 0
 
         if not self.valid:
@@ -106,16 +110,20 @@ class DoclingParseV2PageBackend(PdfPageBackend):
 
             text_piece = cell_data[cells_header.index("text")]
             cells.append(
-                Cell(
-                    id=cell_counter,
+                TextCell(
+                    index=cell_counter,
                     text=text_piece,
-                    bbox=BoundingBox(
-                        # l=x0, b=y0, r=x1, t=y1,
-                        l=x0 * page_size.width / parser_width,
-                        b=y0 * page_size.height / parser_height,
-                        r=x1 * page_size.width / parser_width,
-                        t=y1 * page_size.height / parser_height,
-                        coord_origin=CoordOrigin.BOTTOMLEFT,
+                    orig=text_piece,
+                    from_ocr=False,
+                    rect=BoundingRectangle.from_bounding_box(
+                        BoundingBox(
+                            # l=x0, b=y0, r=x1, t=y1,
+                            l=x0 * page_size.width / parser_width,
+                            b=y0 * page_size.height / parser_height,
+                            r=x1 * page_size.width / parser_width,
+                            t=y1 * page_size.height / parser_height,
+                            coord_origin=CoordOrigin.BOTTOMLEFT,
+                        )
                     ).to_top_left_origin(page_size.height),
                 )
             )

docling/backend/docling_parse_v4_backend.py

@@ -0,0 +1,185 @@
+import logging
+import random
+from io import BytesIO
+from pathlib import Path
+from typing import TYPE_CHECKING, Iterable, List, Optional, Union
+
+import pypdfium2 as pdfium
+from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import SegmentedPdfPage, TextCell
+from docling_parse.pdf_parser import DoclingPdfParser, PdfDocument
+from PIL import Image, ImageDraw
+from pypdfium2 import PdfPage
+
+from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
+from docling.datamodel.base_models import Size
+from docling.utils.locks import pypdfium2_lock
+
+if TYPE_CHECKING:
+    from docling.datamodel.document import InputDocument
+
+_log = logging.getLogger(__name__)
+
+
+class DoclingParseV4PageBackend(PdfPageBackend):
+    def __init__(self, parsed_page: SegmentedPdfPage, page_obj: PdfPage):
+        self._ppage = page_obj
+        self._dpage = parsed_page
+        self.valid = parsed_page is not None
+
+    def is_valid(self) -> bool:
+        return self.valid
+
+    def get_text_in_rect(self, bbox: BoundingBox) -> str:
+        # Find intersecting cells on the page
+        text_piece = ""
+        page_size = self.get_size()
+
+        scale = (
+            1  # FIX - Replace with param in get_text_in_rect across backends (optional)
+        )
+
+        for i, cell in enumerate(self._dpage.textline_cells):
+            cell_bbox = (
+                cell.rect.to_bounding_box()
+                .to_top_left_origin(page_height=page_size.height)
+                .scaled(scale)
+            )
+
+            overlap_frac = cell_bbox.intersection_area_with(bbox) / cell_bbox.area()
+
+            if overlap_frac > 0.5:
+                if len(text_piece) > 0:
+                    text_piece += " "
+                text_piece += cell.text
+
+        return text_piece
+
+    def get_segmented_page(self) -> Optional[SegmentedPdfPage]:
+        return self._dpage
+
+    def get_text_cells(self) -> Iterable[TextCell]:
+        page_size = self.get_size()
+
+        [tc.to_top_left_origin(page_size.height) for tc in self._dpage.textline_cells]
+
+        # for cell in self._dpage.textline_cells:
+        #     rect = cell.rect
+        #
+        #     assert (
+        #         rect.to_bounding_box().l <= rect.to_bounding_box().r
+        #     ), f"left is > right on bounding box {rect.to_bounding_box()} of rect {rect}"
+        #     assert (
+        #         rect.to_bounding_box().t <= rect.to_bounding_box().b
+        #     ), f"top is > bottom on bounding box {rect.to_bounding_box()} of rect {rect}"
+
+        return self._dpage.textline_cells
+
+    def get_bitmap_rects(self, scale: float = 1) -> Iterable[BoundingBox]:
+        AREA_THRESHOLD = 0  # 32 * 32
+
+        images = self._dpage.bitmap_resources
+
+        for img in images:
+            cropbox = img.rect.to_bounding_box().to_top_left_origin(
+                self.get_size().height
+            )
+
+            if cropbox.area() > AREA_THRESHOLD:
+                cropbox = cropbox.scaled(scale=scale)
+
+                yield cropbox
+
+    def get_page_image(
+        self, scale: float = 1, cropbox: Optional[BoundingBox] = None
+    ) -> Image.Image:
+
+        page_size = self.get_size()
+
+        if not cropbox:
+            cropbox = BoundingBox(
+                l=0,
+                r=page_size.width,
+                t=0,
+                b=page_size.height,
+                coord_origin=CoordOrigin.TOPLEFT,
+            )
+            padbox = BoundingBox(
+                l=0, r=0, t=0, b=0, coord_origin=CoordOrigin.BOTTOMLEFT
+            )
+        else:
+            padbox = cropbox.to_bottom_left_origin(page_size.height).model_copy()
+            padbox.r = page_size.width - padbox.r
+            padbox.t = page_size.height - padbox.t
+
+        image = (
+            self._ppage.render(
+                scale=scale * 1.5,
+                rotation=0,  # no additional rotation
+                crop=padbox.as_tuple(),
+            )
+            .to_pil()
+            .resize(size=(round(cropbox.width * scale), round(cropbox.height * scale)))
+        )  # We resize the image from 1.5x the given scale to make it sharper.
+
+        return image
+
+    def get_size(self) -> Size:
+        return Size(
+            width=self._dpage.dimension.width,
+            height=self._dpage.dimension.height,
+        )
+
+    def unload(self):
+        self._ppage = None
+        self._dpage = None
+
+
+class DoclingParseV4DocumentBackend(PdfDocumentBackend):
+    def __init__(self, in_doc: "InputDocument", path_or_stream: Union[BytesIO, Path]):
+        super().__init__(in_doc, path_or_stream)
+
+        with pypdfium2_lock:
+            self._pdoc = pdfium.PdfDocument(self.path_or_stream)
+        self.parser = DoclingPdfParser(loglevel="fatal")
+        self.dp_doc: PdfDocument = self.parser.load(path_or_stream=self.path_or_stream)
+        success = self.dp_doc is not None
+
+        if not success:
+            raise RuntimeError(
+                f"docling-parse v4 could not load document {self.document_hash}."
+            )
+
+    def page_count(self) -> int:
+        # return len(self._pdoc)  # To be replaced with docling-parse API
+
+        len_1 = len(self._pdoc)
+        len_2 = self.dp_doc.number_of_pages()
+
+        if len_1 != len_2:
+            _log.error(f"Inconsistent number of pages: {len_1}!={len_2}")
+
+        return len_2
+
+    def load_page(
+        self, page_no: int, create_words: bool = True, create_textlines: bool = True
+    ) -> DoclingParseV4PageBackend:
+        with pypdfium2_lock:
+            return DoclingParseV4PageBackend(
+                self.dp_doc.get_page(
+                    page_no + 1,
+                    create_words=create_words,
+                    create_textlines=create_textlines,
+                ),
+                self._pdoc[page_no],
+            )
+
+    def is_valid(self) -> bool:
+        return self.page_count() > 0
+
+    def unload(self):
+        super().unload()
+        self.dp_doc.unload()
+        with pypdfium2_lock:
+            self._pdoc.close()
+        self._pdoc = None

docling/backend/pdf_backend.py

@@ -4,10 +4,11 @@ from pathlib import Path
 from typing import Iterable, Optional, Set, Union
 
 from docling_core.types.doc import BoundingBox, Size
+from docling_core.types.doc.page import SegmentedPdfPage, TextCell
 from PIL import Image
 
 from docling.backend.abstract_backend import PaginatedDocumentBackend
-from docling.datamodel.base_models import Cell, InputFormat
+from docling.datamodel.base_models import InputFormat
 from docling.datamodel.document import InputDocument
 
 
@@ -17,7 +18,11 @@ class PdfPageBackend(ABC):
         pass
 
     @abstractmethod
-    def get_text_cells(self) -> Iterable[Cell]:
+    def get_segmented_page(self) -> Optional[SegmentedPdfPage]:
+        pass
+
+    @abstractmethod
+    def get_text_cells(self) -> Iterable[TextCell]:
         pass
 
     @abstractmethod

docling/backend/pypdfium2_backend.py

@@ -7,12 +7,12 @@ from typing import TYPE_CHECKING, Iterable, List, Optional, Union
 import pypdfium2 as pdfium
 import pypdfium2.raw as pdfium_c
 from docling_core.types.doc import BoundingBox, CoordOrigin, Size
+from docling_core.types.doc.page import BoundingRectangle, SegmentedPdfPage, TextCell
 from PIL import Image, ImageDraw
 from pypdfium2 import PdfTextPage
 from pypdfium2._helpers.misc import PdfiumError
 
 from docling.backend.pdf_backend import PdfDocumentBackend, PdfPageBackend
-from docling.datamodel.base_models import Cell
 from docling.utils.locks import pypdfium2_lock
 
 if TYPE_CHECKING:
@@ -68,7 +68,10 @@ class PyPdfiumPageBackend(PdfPageBackend):
 
         return text_piece
 
-    def get_text_cells(self) -> Iterable[Cell]:
+    def get_segmented_page(self) -> Optional[SegmentedPdfPage]:
+        return None
+
+    def get_text_cells(self) -> Iterable[TextCell]:
         with pypdfium2_lock:
             if not self.text_page:
                 self.text_page = self._ppage.get_textpage()
@@ -84,11 +87,19 @@ class PyPdfiumPageBackend(PdfPageBackend):
                 text_piece = self.text_page.get_text_bounded(*rect)
                 x0, y0, x1, y1 = rect
                 cells.append(
-                    Cell(
-                        id=cell_counter,
+                    TextCell(
+                        index=cell_counter,
                         text=text_piece,
-                        bbox=BoundingBox(
-                            l=x0, b=y0, r=x1, t=y1, coord_origin=CoordOrigin.BOTTOMLEFT
+                        orig=text_piece,
+                        from_ocr=False,
+                        rect=BoundingRectangle.from_bounding_box(
+                            BoundingBox(
+                                l=x0,
+                                b=y0,
+                                r=x1,
+                                t=y1,
+                                coord_origin=CoordOrigin.BOTTOMLEFT,
+                            )
                         ).to_top_left_origin(page_size.height),
                     )
                 )
@@ -97,51 +108,56 @@ class PyPdfiumPageBackend(PdfPageBackend):
         # PyPdfium2 produces very fragmented cells, with sub-word level boundaries, in many PDFs.
         # The cell merging code below is to clean this up.
         def merge_horizontal_cells(
-            cells: List[Cell],
+            cells: List[TextCell],
             horizontal_threshold_factor: float = 1.0,
             vertical_threshold_factor: float = 0.5,
-        ) -> List[Cell]:
+        ) -> List[TextCell]:
             if not cells:
                 return []
 
-            def group_rows(cells: List[Cell]) -> List[List[Cell]]:
+            def group_rows(cells: List[TextCell]) -> List[List[TextCell]]:
                 rows = []
                 current_row = [cells[0]]
-                row_top = cells[0].bbox.t
-                row_bottom = cells[0].bbox.b
-                row_height = cells[0].bbox.height
+                row_top = cells[0].rect.to_bounding_box().t
+                row_bottom = cells[0].rect.to_bounding_box().b
+                row_height = cells[0].rect.to_bounding_box().height
 
                 for cell in cells[1:]:
                     vertical_threshold = row_height * vertical_threshold_factor
                     if (
-                        abs(cell.bbox.t - row_top) <= vertical_threshold
-                        and abs(cell.bbox.b - row_bottom) <= vertical_threshold
+                        abs(cell.rect.to_bounding_box().t - row_top)
+                        <= vertical_threshold
+                        and abs(cell.rect.to_bounding_box().b - row_bottom)
+                        <= vertical_threshold
                     ):
                         current_row.append(cell)
-                        row_top = min(row_top, cell.bbox.t)
-                        row_bottom = max(row_bottom, cell.bbox.b)
+                        row_top = min(row_top, cell.rect.to_bounding_box().t)
+                        row_bottom = max(row_bottom, cell.rect.to_bounding_box().b)
                         row_height = row_bottom - row_top
                     else:
                         rows.append(current_row)
                         current_row = [cell]
-                        row_top = cell.bbox.t
-                        row_bottom = cell.bbox.b
-                        row_height = cell.bbox.height
+                        row_top = cell.rect.to_bounding_box().t
+                        row_bottom = cell.rect.to_bounding_box().b
+                        row_height = cell.rect.to_bounding_box().height
 
                 if current_row:
                     rows.append(current_row)
 
                 return rows
 
-            def merge_row(row: List[Cell]) -> List[Cell]:
+            def merge_row(row: List[TextCell]) -> List[TextCell]:
                 merged = []
                 current_group = [row[0]]
 
                 for cell in row[1:]:
                     prev_cell = current_group[-1]
-                    avg_height = (prev_cell.bbox.height + cell.bbox.height) / 2
+                    avg_height = (
+                        prev_cell.rect.height + cell.rect.to_bounding_box().height
+                    ) / 2
                     if (
-                        cell.bbox.l - prev_cell.bbox.r
+                        cell.rect.to_bounding_box().l
+                        - prev_cell.rect.to_bounding_box().r
                         <= avg_height * horizontal_threshold_factor
                     ):
                         current_group.append(cell)
@@ -154,24 +170,30 @@ class PyPdfiumPageBackend(PdfPageBackend):
 
                 return merged
 
-            def merge_group(group: List[Cell]) -> Cell:
+            def merge_group(group: List[TextCell]) -> TextCell:
                 if len(group) == 1:
                     return group[0]
 
                 merged_text = "".join(cell.text for cell in group)
                 merged_bbox = BoundingBox(
-                    l=min(cell.bbox.l for cell in group),
-                    t=min(cell.bbox.t for cell in group),
-                    r=max(cell.bbox.r for cell in group),
-                    b=max(cell.bbox.b for cell in group),
+                    l=min(cell.rect.to_bounding_box().l for cell in group),
+                    t=min(cell.rect.to_bounding_box().t for cell in group),
+                    r=max(cell.rect.to_bounding_box().r for cell in group),
+                    b=max(cell.rect.to_bounding_box().b for cell in group),
+                )
+                return TextCell(
+                    index=group[0].index,
+                    text=merged_text,
+                    orig=merged_text,
+                    rect=BoundingRectangle.from_bounding_box(merged_bbox),
+                    from_ocr=False,
                 )
-                return Cell(id=group[0].id, text=merged_text, bbox=merged_bbox)
 
             rows = group_rows(cells)
             merged_cells = [cell for row in rows for cell in merge_row(row)]
 
             for i, cell in enumerate(merged_cells, 1):
-                cell.id = i
+                cell.index = i
 
             return merged_cells
 
@@ -181,7 +203,7 @@ class PyPdfiumPageBackend(PdfPageBackend):
             )  # make new image to avoid drawing on the saved ones
             draw = ImageDraw.Draw(image)
             for c in cells:
-                x0, y0, x1, y1 = c.bbox.as_tuple()
+                x0, y0, x1, y1 = c.rect.to_bounding_box().as_tuple()
                 cell_color = (
                     random.randint(30, 140),
                     random.randint(30, 140),

docling/cli/main.py

@@ -16,6 +16,7 @@ from pydantic import TypeAdapter
 
 from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
+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.base_models import (
@@ -412,12 +413,15 @@ def convert(
         if artifacts_path is not None:
             pipeline_options.artifacts_path = artifacts_path
 
+        backend: Type[PdfDocumentBackend]
         if pdf_backend == PdfBackend.DLPARSE_V1:
-            backend: Type[PdfDocumentBackend] = DoclingParseDocumentBackend
+            backend = DoclingParseDocumentBackend
         elif pdf_backend == PdfBackend.DLPARSE_V2:
             backend = DoclingParseV2DocumentBackend
+        elif pdf_backend == PdfBackend.DLPARSE_V4:
+            backend = DoclingParseV4DocumentBackend  # type: ignore
         elif pdf_backend == PdfBackend.PYPDFIUM2:
-            backend = PyPdfiumDocumentBackend
+            backend = PyPdfiumDocumentBackend  # type: ignore
         else:
             raise RuntimeError(f"Unexpected PDF backend type {pdf_backend}")
 

docling/datamodel/base_models.py

@@ -9,6 +9,7 @@ from docling_core.types.doc import (
     Size,
     TableCell,
 )
+from docling_core.types.doc.page import SegmentedPdfPage, TextCell
 from docling_core.types.io import (  # DO ΝΟΤ REMOVE; explicitly exposed from this location
     DocumentStream,
 )
@@ -123,14 +124,10 @@ class ErrorItem(BaseModel):
     error_message: str
 
 
-class Cell(BaseModel):
-    id: int
-    text: str
-    bbox: BoundingBox
-
-
-class OcrCell(Cell):
-    confidence: float
+# class Cell(BaseModel):
+#    id: int
+#    text: str
+#    bbox: BoundingBox
 
 
 class Cluster(BaseModel):
@@ -138,7 +135,7 @@ class Cluster(BaseModel):
     label: DocItemLabel
     bbox: BoundingBox
     confidence: float = 1.0
-    cells: List[Cell] = []
+    cells: List[TextCell] = []
     children: List["Cluster"] = []  # Add child cluster support
 
 
@@ -226,7 +223,8 @@ class Page(BaseModel):
     page_no: int
     # page_hash: Optional[str] = None
     size: Optional[Size] = None
-    cells: List[Cell] = []
+    cells: List[TextCell] = []
+    parsed_page: Optional[SegmentedPdfPage] = None
     predictions: PagePredictions = PagePredictions()
     assembled: Optional[AssembledUnit] = None
 

docling/datamodel/pipeline_options.py

@@ -301,6 +301,7 @@ class PdfBackend(str, Enum):
     PYPDFIUM2 = "pypdfium2"
     DLPARSE_V1 = "dlparse_v1"
     DLPARSE_V2 = "dlparse_v2"
+    DLPARSE_V4 = "dlparse_v4"
 
 
 # Define an enum for the ocr engines
@@ -381,3 +382,5 @@ class PdfPipelineOptions(PaginatedPipelineOptions):
             "before conversion and then use the `TableItem.get_image` function."
         ),
     )
+
+    generate_parsed_pages: bool = False

docling/document_converter.py

@@ -11,7 +11,7 @@ from pydantic import BaseModel, ConfigDict, model_validator, validate_call
 from docling.backend.abstract_backend import AbstractDocumentBackend
 from docling.backend.asciidoc_backend import AsciiDocBackend
 from docling.backend.csv_backend import CsvDocumentBackend
-from docling.backend.docling_parse_v2_backend import DoclingParseV2DocumentBackend
+from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
 from docling.backend.html_backend import HTMLDocumentBackend
 from docling.backend.json.docling_json_backend import DoclingJSONBackend
 from docling.backend.md_backend import MarkdownDocumentBackend
@@ -109,12 +109,12 @@ class XMLJatsFormatOption(FormatOption):
 
 class ImageFormatOption(FormatOption):
     pipeline_cls: Type = StandardPdfPipeline
-    backend: Type[AbstractDocumentBackend] = DoclingParseV2DocumentBackend
+    backend: Type[AbstractDocumentBackend] = DoclingParseV4DocumentBackend
 
 
 class PdfFormatOption(FormatOption):
     pipeline_cls: Type = StandardPdfPipeline
-    backend: Type[AbstractDocumentBackend] = DoclingParseV2DocumentBackend
+    backend: Type[AbstractDocumentBackend] = DoclingParseV4DocumentBackend
 
 
 def _get_default_option(format: InputFormat) -> FormatOption:
@@ -147,10 +147,10 @@ def _get_default_option(format: InputFormat) -> FormatOption:
             pipeline_cls=SimplePipeline, backend=JatsDocumentBackend
         ),
         InputFormat.IMAGE: FormatOption(
-            pipeline_cls=StandardPdfPipeline, backend=DoclingParseV2DocumentBackend
+            pipeline_cls=StandardPdfPipeline, backend=DoclingParseV4DocumentBackend
         ),
         InputFormat.PDF: FormatOption(
-            pipeline_cls=StandardPdfPipeline, backend=DoclingParseV2DocumentBackend
+            pipeline_cls=StandardPdfPipeline, backend=DoclingParseV4DocumentBackend
         ),
         InputFormat.JSON_DOCLING: FormatOption(
             pipeline_cls=SimplePipeline, backend=DoclingJSONBackend

docling/models/base_ocr_model.py

@@ -6,11 +6,12 @@ from typing import Iterable, List
 
 import numpy as np
 from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle, PdfTextCell, TextCell
 from PIL import Image, ImageDraw
 from rtree import index
 from scipy.ndimage import binary_dilation, find_objects, label
 
-from docling.datamodel.base_models import Cell, OcrCell, Page
+from docling.datamodel.base_models import Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import OcrOptions
 from docling.datamodel.settings import settings
@@ -104,11 +105,13 @@ class BaseOcrModel(BasePageModel):
         p.dimension = 2
         idx = index.Index(properties=p)
         for i, cell in enumerate(programmatic_cells):
-            idx.insert(i, cell.bbox.as_tuple())
+            idx.insert(i, cell.rect.to_bounding_box().as_tuple())
 
         def is_overlapping_with_existing_cells(ocr_cell):
             # Query the R-tree to get overlapping rectangles
-            possible_matches_index = list(idx.intersection(ocr_cell.bbox.as_tuple()))
+            possible_matches_index = list(
+                idx.intersection(ocr_cell.rect.to_bounding_box().as_tuple())
+            )
 
             return (
                 len(possible_matches_index) > 0
@@ -125,10 +128,7 @@ class BaseOcrModel(BasePageModel):
         """
         if self.options.force_full_page_ocr:
             # If a full page OCR is forced, use only the OCR cells
-            cells = [
-                Cell(id=c_ocr.id, text=c_ocr.text, bbox=c_ocr.bbox)
-                for c_ocr in ocr_cells
-            ]
+            cells = ocr_cells
             return cells
 
         ## Remove OCR cells which overlap with programmatic cells.
@@ -156,7 +156,7 @@ class BaseOcrModel(BasePageModel):
 
         # Draw OCR and programmatic cells
         for tc in page.cells:
-            x0, y0, x1, y1 = tc.bbox.as_tuple()
+            x0, y0, x1, y1 = tc.rect.to_bounding_box().as_tuple()
             y0 *= scale_x
             y1 *= scale_y
             x0 *= scale_x
@@ -165,9 +165,8 @@ class BaseOcrModel(BasePageModel):
             if y1 <= y0:
                 y1, y0 = y0, y1
 
-            color = "gray"
-            if isinstance(tc, OcrCell):
-                color = "magenta"
+            color = "magenta" if tc.from_ocr else "gray"
+
             draw.rectangle([(x0, y0), (x1, y1)], outline=color)
 
         if show:

docling/models/easyocr_model.py

@@ -6,8 +6,9 @@ from typing import Iterable, List, Optional
 
 import numpy
 from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle, TextCell
 
-from docling.datamodel.base_models import Cell, OcrCell, Page
+from docling.datamodel.base_models import Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     AcceleratorDevice,
@@ -148,18 +149,22 @@ class EasyOcrModel(BaseOcrModel):
                         del im
 
                         cells = [
-                            OcrCell(
-                                id=ix,
+                            TextCell(
+                                index=ix,
                                 text=line[1],
+                                orig=line[1],
+                                from_ocr=True,
                                 confidence=line[2],
-                                bbox=BoundingBox.from_tuple(
-                                    coord=(
-                                        (line[0][0][0] / self.scale) + ocr_rect.l,
-                                        (line[0][0][1] / self.scale) + ocr_rect.t,
-                                        (line[0][2][0] / self.scale) + ocr_rect.l,
-                                        (line[0][2][1] / self.scale) + ocr_rect.t,
-                                    ),
-                                    origin=CoordOrigin.TOPLEFT,
+                                rect=BoundingRectangle.from_bounding_box(
+                                    BoundingBox.from_tuple(
+                                        coord=(
+                                            (line[0][0][0] / self.scale) + ocr_rect.l,
+                                            (line[0][0][1] / self.scale) + ocr_rect.t,
+                                            (line[0][2][0] / self.scale) + ocr_rect.l,
+                                            (line[0][2][1] / self.scale) + ocr_rect.t,
+                                        ),
+                                        origin=CoordOrigin.TOPLEFT,
+                                    )
                                 ),
                             )
                             for ix, line in enumerate(result)

docling/models/ocr_mac_model.py

@@ -3,8 +3,9 @@ import tempfile
 from typing import Iterable, Optional, Tuple
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle, TextCell
 
-from docling.datamodel.base_models import OcrCell, Page
+from docling.datamodel.base_models import Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import OcrMacOptions
 from docling.datamodel.settings import settings
@@ -94,13 +95,17 @@ class OcrMacModel(BaseOcrModel):
                             bottom = y2 / self.scale
 
                             cells.append(
-                                OcrCell(
-                                    id=ix,
+                                TextCell(
+                                    index=ix,
                                     text=text,
+                                    orig=text,
+                                    from_ocr=True,
                                     confidence=confidence,
-                                    bbox=BoundingBox.from_tuple(
-                                        coord=(left, top, right, bottom),
-                                        origin=CoordOrigin.TOPLEFT,
+                                    rect=BoundingRectangle.from_bounding_box(
+                                        BoundingBox.from_tuple(
+                                            coord=(left, top, right, bottom),
+                                            origin=CoordOrigin.TOPLEFT,
+                                        )
                                     ),
                                 )
                             )

docling/models/page_preprocessing_model.py

@@ -13,6 +13,7 @@ from docling.utils.profiling import TimeRecorder
 
 class PagePreprocessingOptions(BaseModel):
     images_scale: Optional[float]
+    create_parsed_page: bool
 
 
 class PagePreprocessingModel(BasePageModel):
@@ -55,6 +56,9 @@ class PagePreprocessingModel(BasePageModel):
 
         page.cells = list(page._backend.get_text_cells())
 
+        if self.options.create_parsed_page:
+            page.parsed_page = page._backend.get_segmented_page()
+
         # DEBUG code:
         def draw_text_boxes(image, cells, show: bool = False):
             draw = ImageDraw.Draw(image)

docling/models/rapid_ocr_model.py

@@ -3,8 +3,9 @@ from typing import Iterable
 
 import numpy
 from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle, TextCell
 
-from docling.datamodel.base_models import OcrCell, Page
+from docling.datamodel.base_models import Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import (
     AcceleratorDevice,
@@ -100,18 +101,26 @@ class RapidOcrModel(BaseOcrModel):
 
                         if result is not None:
                             cells = [
-                                OcrCell(
-                                    id=ix,
+                                TextCell(
+                                    index=ix,
                                     text=line[1],
+                                    orig=line[1],
                                     confidence=line[2],
-                                    bbox=BoundingBox.from_tuple(
-                                        coord=(
-                                            (line[0][0][0] / self.scale) + ocr_rect.l,
-                                            (line[0][0][1] / self.scale) + ocr_rect.t,
-                                            (line[0][2][0] / self.scale) + ocr_rect.l,
-                                            (line[0][2][1] / self.scale) + ocr_rect.t,
-                                        ),
-                                        origin=CoordOrigin.TOPLEFT,
+                                    from_ocr=True,
+                                    rect=BoundingRectangle.from_bounding_box(
+                                        BoundingBox.from_tuple(
+                                            coord=(
+                                                (line[0][0][0] / self.scale)
+                                                + ocr_rect.l,
+                                                (line[0][0][1] / self.scale)
+                                                + ocr_rect.t,
+                                                (line[0][2][0] / self.scale)
+                                                + ocr_rect.l,
+                                                (line[0][2][1] / self.scale)
+                                                + ocr_rect.t,
+                                            ),
+                                            origin=CoordOrigin.TOPLEFT,
+                                        )
                                     ),
                                 )
                                 for ix, line in enumerate(result)

docling/models/table_structure_model.py

@@ -5,6 +5,7 @@ from typing import Iterable, Optional, Union
 
 import numpy
 from docling_core.types.doc import BoundingBox, DocItemLabel, TableCell
+from docling_core.types.doc.page import BoundingRectangle
 from docling_ibm_models.tableformer.data_management.tf_predictor import TFPredictor
 from PIL import ImageDraw
 
@@ -129,7 +130,7 @@ class TableStructureModel(BasePageModel):
             draw.rectangle([(x0, y0), (x1, y1)], outline="red")
 
             for cell in table_element.cluster.cells:
-                x0, y0, x1, y1 = cell.bbox.as_tuple()
+                x0, y0, x1, y1 = cell.rect.to_bounding_box().as_tuple()
                 x0 *= scale_x
                 x1 *= scale_x
                 y0 *= scale_x
@@ -223,11 +224,19 @@ class TableStructureModel(BasePageModel):
                                 # Only allow non empty stings (spaces) into the cells of a table
                                 if len(c.text.strip()) > 0:
                                     new_cell = copy.deepcopy(c)
-                                    new_cell.bbox = new_cell.bbox.scaled(
-                                        scale=self.scale
+                                    new_cell.rect = BoundingRectangle.from_bounding_box(
+                                        new_cell.rect.to_bounding_box().scaled(
+                                            scale=self.scale
+                                        )
                                     )
 
-                                    tokens.append(new_cell.model_dump())
+                                    tokens.append(
+                                        {
+                                            "id": new_cell.index,
+                                            "text": new_cell.text,
+                                            "bbox": new_cell.rect.to_bounding_box().model_dump(),
+                                        }
+                                    )
                             page_input["tokens"] = tokens
 
                             tf_output = self.tf_predictor.multi_table_predict(

docling/models/tesseract_ocr_cli_model.py

@@ -8,8 +8,9 @@ from typing import Iterable, List, Optional, Tuple
 
 import pandas as pd
 from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle, TextCell
 
-from docling.datamodel.base_models import Cell, OcrCell, Page
+from docling.datamodel.base_models import Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import TesseractCliOcrOptions
 from docling.datamodel.settings import settings
@@ -228,18 +229,22 @@ class TesseractOcrCliModel(BaseOcrModel):
                             t = b + h
                             r = l + w
 
-                            cell = OcrCell(
-                                id=ix,
+                            cell = TextCell(
+                                index=ix,
                                 text=text,
+                                orig=text,
+                                from_ocr=True,
                                 confidence=conf / 100.0,
-                                bbox=BoundingBox.from_tuple(
-                                    coord=(
-                                        (l / self.scale) + ocr_rect.l,
-                                        (b / self.scale) + ocr_rect.t,
-                                        (r / self.scale) + ocr_rect.l,
-                                        (t / self.scale) + ocr_rect.t,
-                                    ),
-                                    origin=CoordOrigin.TOPLEFT,
+                                rect=BoundingRectangle.from_bounding_box(
+                                    BoundingBox.from_tuple(
+                                        coord=(
+                                            (l / self.scale) + ocr_rect.l,
+                                            (b / self.scale) + ocr_rect.t,
+                                            (r / self.scale) + ocr_rect.l,
+                                            (t / self.scale) + ocr_rect.t,
+                                        ),
+                                        origin=CoordOrigin.TOPLEFT,
+                                    )
                                 ),
                             )
                             all_ocr_cells.append(cell)

docling/models/tesseract_ocr_model.py

@@ -2,8 +2,9 @@ import logging
 from typing import Iterable
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import BoundingRectangle, TextCell
 
-from docling.datamodel.base_models import Cell, OcrCell, Page
+from docling.datamodel.base_models import Page
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import TesseractOcrOptions
 from docling.datamodel.settings import settings
@@ -173,13 +174,17 @@ class TesseractOcrModel(BaseOcrModel):
                             top = (box["y"] + box["h"]) / self.scale
 
                             cells.append(
-                                OcrCell(
-                                    id=ix,
+                                TextCell(
+                                    index=ix,
                                     text=text,
+                                    orig=text,
+                                    from_ocr=True,
                                     confidence=confidence,
-                                    bbox=BoundingBox.from_tuple(
-                                        coord=(left, top, right, bottom),
-                                        origin=CoordOrigin.TOPLEFT,
+                                    rect=BoundingRectangle.from_bounding_box(
+                                        BoundingBox.from_tuple(
+                                            coord=(left, top, right, bottom),
+                                            origin=CoordOrigin.TOPLEFT,
+                                        ),
                                     ),
                                 )
                             )

docling/pipeline/standard_pdf_pipeline.py

@@ -87,7 +87,8 @@ class StandardPdfPipeline(PaginatedPipeline):
             # Pre-processing
             PagePreprocessingModel(
                 options=PagePreprocessingOptions(
-                    images_scale=pipeline_options.images_scale
+                    images_scale=pipeline_options.images_scale,
+                    create_parsed_page=pipeline_options.generate_parsed_pages,
                 )
             ),
             # OCR

docling/utils/export.py

@@ -2,9 +2,9 @@ import logging
 from typing import Any, Dict, Iterable, List, Tuple, Union
 
 from docling_core.types.doc import BoundingBox, CoordOrigin
+from docling_core.types.doc.page import TextCell
 from docling_core.types.legacy_doc.base import BaseCell, BaseText, Ref, Table
 
-from docling.datamodel.base_models import OcrCell
 from docling.datamodel.document import ConversionResult, Page
 
 _log = logging.getLogger(__name__)
@@ -86,11 +86,13 @@ def generate_multimodal_pages(
         if page.size is None:
             return cells
         for cell in page.cells:
-            new_bbox = cell.bbox.to_top_left_origin(
-                page_height=page.size.height
-            ).normalized(page_size=page.size)
-            is_ocr = isinstance(cell, OcrCell)
-            ocr_confidence = cell.confidence if isinstance(cell, OcrCell) else 1.0
+            new_bbox = (
+                cell.rect.to_bounding_box()
+                .to_top_left_origin(page_height=page.size.height)
+                .normalized(page_size=page.size)
+            )
+            is_ocr = cell.from_ocr
+            ocr_confidence = cell.confidence
             cells.append(
                 {
                     "text": cell.text,

docling/utils/layout_postprocessor.py

@@ -5,9 +5,10 @@ from collections import defaultdict
 from typing import Dict, List, Set, Tuple
 
 from docling_core.types.doc import DocItemLabel, Size
+from docling_core.types.doc.page import TextCell
 from rtree import index
 
-from docling.datamodel.base_models import BoundingBox, Cell, Cluster, OcrCell
+from docling.datamodel.base_models import BoundingBox, Cluster
 
 _log = logging.getLogger(__name__)
 
@@ -198,7 +199,7 @@ class LayoutPostprocessor:
         DocItemLabel.TITLE: DocItemLabel.SECTION_HEADER,
     }
 
-    def __init__(self, cells: List[Cell], clusters: List[Cluster], page_size: Size):
+    def __init__(self, cells: List[TextCell], clusters: List[Cluster], page_size: Size):
         """Initialize processor with cells and clusters."""
         """Initialize processor with cells and spatial indices."""
         self.cells = cells
@@ -218,7 +219,7 @@ class LayoutPostprocessor:
             [c for c in self.special_clusters if c.label in self.WRAPPER_TYPES]
         )
 
-    def postprocess(self) -> Tuple[List[Cluster], List[Cell]]:
+    def postprocess(self) -> Tuple[List[Cluster], List[TextCell]]:
         """Main processing pipeline."""
         self.regular_clusters = self._process_regular_clusters()
         self.special_clusters = self._process_special_clusters()
@@ -271,15 +272,13 @@ class LayoutPostprocessor:
             next_id = max((c.id for c in self.all_clusters), default=0) + 1
             orphan_clusters = []
             for i, cell in enumerate(unassigned):
-                conf = 1.0
-                if isinstance(cell, OcrCell):
-                    conf = cell.confidence
+                conf = cell.confidence
 
                 orphan_clusters.append(
                     Cluster(
                         id=next_id + i,
                         label=DocItemLabel.TEXT,
-                        bbox=cell.bbox,
+                        bbox=cell.to_bounding_box(),
                         confidence=conf,
                         cells=[cell],
                     )
@@ -557,13 +556,13 @@ class LayoutPostprocessor:
 
         return current_best if current_best else clusters[0]
 
-    def _deduplicate_cells(self, cells: List[Cell]) -> List[Cell]:
+    def _deduplicate_cells(self, cells: List[TextCell]) -> List[TextCell]:
         """Ensure each cell appears only once, maintaining order of first appearance."""
         seen_ids = set()
         unique_cells = []
         for cell in cells:
-            if cell.id not in seen_ids:
-                seen_ids.add(cell.id)
+            if cell.index not in seen_ids:
+                seen_ids.add(cell.index)
                 unique_cells.append(cell)
         return unique_cells
 
@@ -582,11 +581,13 @@ class LayoutPostprocessor:
             best_cluster = None
 
             for cluster in clusters:
-                if cell.bbox.area() <= 0:
+                if cell.rect.to_bounding_box().area() <= 0:
                     continue
 
-                overlap = cell.bbox.intersection_area_with(cluster.bbox)
-                overlap_ratio = overlap / cell.bbox.area()
+                overlap = cell.rect.to_bounding_box().intersection_area_with(
+                    cluster.bbox
+                )
+                overlap_ratio = overlap / cell.rect.to_bounding_box().area()
 
                 if overlap_ratio > best_overlap:
                     best_overlap = overlap_ratio
@@ -601,11 +602,13 @@ class LayoutPostprocessor:
 
         return clusters
 
-    def _find_unassigned_cells(self, clusters: List[Cluster]) -> List[Cell]:
+    def _find_unassigned_cells(self, clusters: List[Cluster]) -> List[TextCell]:
         """Find cells not assigned to any cluster."""
-        assigned = {cell.id for cluster in clusters for cell in cluster.cells}
+        assigned = {cell.index for cluster in clusters for cell in cluster.cells}
         return [
-            cell for cell in self.cells if cell.id not in assigned and cell.text.strip()
+            cell
+            for cell in self.cells
+            if cell.index not in assigned and cell.text.strip()
         ]
 
     def _adjust_cluster_bboxes(self, clusters: List[Cluster]) -> List[Cluster]:
@@ -615,10 +618,10 @@ class LayoutPostprocessor:
                 continue
 
             cells_bbox = BoundingBox(
-                l=min(cell.bbox.l for cell in cluster.cells),
-                t=min(cell.bbox.t for cell in cluster.cells),
-                r=max(cell.bbox.r for cell in cluster.cells),
-                b=max(cell.bbox.b for cell in cluster.cells),
+                l=min(cell.rect.to_bounding_box().l for cell in cluster.cells),
+                t=min(cell.rect.to_bounding_box().t for cell in cluster.cells),
+                r=max(cell.rect.to_bounding_box().r for cell in cluster.cells),
+                b=max(cell.rect.to_bounding_box().b for cell in cluster.cells),
             )
 
             if cluster.label == DocItemLabel.TABLE:
@@ -634,9 +637,9 @@ class LayoutPostprocessor:
 
         return clusters
 
-    def _sort_cells(self, cells: List[Cell]) -> List[Cell]:
+    def _sort_cells(self, cells: List[TextCell]) -> List[TextCell]:
         """Sort cells in native reading order."""
-        return sorted(cells, key=lambda c: (c.id))
+        return sorted(cells, key=lambda c: (c.index))
 
     def _sort_clusters(
         self, clusters: List[Cluster], mode: str = "id"
@@ -647,7 +650,7 @@ class LayoutPostprocessor:
                 clusters,
                 key=lambda cluster: (
                     (
-                        min(cell.id for cell in cluster.cells)
+                        min(cell.index for cell in cluster.cells)
                         if cluster.cells
                         else sys.maxsize
                     ),

docling/utils/visualization.py

@@ -25,7 +25,7 @@ def draw_clusters(
             # Draw cells first (underneath)
             cell_color = (0, 0, 0, 40)  # Transparent black for cells
             for tc in c.cells:
-                cx0, cy0, cx1, cy1 = tc.bbox.as_tuple()
+                cx0, cy0, cx1, cy1 = tc.rect.to_bounding_box().as_tuple()
                 cx0 *= scale_x
                 cx1 *= scale_x
                 cy0 *= scale_x

docs/examples/batch_convert.py

@@ -7,6 +7,7 @@ from typing import Iterable
 import yaml
 from docling_core.types.doc import ImageRefMode
 
+from docling.backend.docling_parse_v4_backend import DoclingParseV4DocumentBackend
 from docling.datamodel.base_models import ConversionStatus, InputFormat
 from docling.datamodel.document import ConversionResult
 from docling.datamodel.pipeline_options import PdfPipelineOptions
@@ -60,6 +61,18 @@ def export_documents(
                 with (output_dir / f"{doc_filename}.yaml").open("w") as fp:
                     fp.write(yaml.safe_dump(conv_res.document.export_to_dict()))
 
+                # Export Docling document format to doctags:
+                with (output_dir / f"{doc_filename}.doctags.txt").open("w") as fp:
+                    fp.write(conv_res.document.export_to_document_tokens())
+
+                # Export Docling document format to markdown:
+                with (output_dir / f"{doc_filename}.md").open("w") as fp:
+                    fp.write(conv_res.document.export_to_markdown())
+
+                # Export Docling document format to text:
+                with (output_dir / f"{doc_filename}.txt").open("w") as fp:
+                    fp.write(conv_res.document.export_to_markdown(strict_text=True))
+
             if USE_LEGACY:
                 # Export Deep Search document JSON format:
                 with (output_dir / f"{doc_filename}.legacy.json").open(
@@ -131,7 +144,9 @@ def main():
 
     doc_converter = DocumentConverter(
         format_options={
-            InputFormat.PDF: PdfFormatOption(pipeline_options=pipeline_options)
+            InputFormat.PDF: PdfFormatOption(
+                pipeline_options=pipeline_options, backend=DoclingParseV4DocumentBackend
+            )
         }
     )
 

poetry.lock

@@ -1,18 +1,18 @@
-# This file is automatically @generated by Poetry 1.8.5 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.4 and should not be changed by hand.
 
 [[package]]
 name = "accelerate"
-version = "1.4.0"
+version = "1.5.1"
 description = "Accelerate"
 optional = true
 python-versions = ">=3.9.0"
 files = [
-    {file = "accelerate-1.4.0-py3-none-any.whl", hash = "sha256:f6e1e7dfaf9d799a20a1dc45efbf4b1546163eac133faa5acd0d89177c896e55"},
-    {file = "accelerate-1.4.0.tar.gz", hash = "sha256:37d413e1b64cb8681ccd2908ae211cf73e13e6e636a2f598a96eccaa538773a5"},
+    {file = "accelerate-1.5.1-py3-none-any.whl", hash = "sha256:4838cff9ed1bb0ddc9d967530ced62a1d74ea21cdb57688400359ab32682f03e"},
+    {file = "accelerate-1.5.1.tar.gz", hash = "sha256:5d936faf3a31894c6160f2f2a984a38aecbba760ef919ae298b2ecd57ea9bf87"},
 ]
 
 [package.dependencies]
-huggingface-hub = ">=0.21.0"
+huggingface_hub = ">=0.21.0"
 numpy = ">=1.17,<3.0.0"
 packaging = ">=20.0"
 psutil = "*"
@@ -22,24 +22,24 @@ torch = ">=2.0.0"
 
 [package.extras]
 deepspeed = ["deepspeed"]
-dev = ["bitsandbytes", "black (>=23.1,<24.0)", "datasets", "diffusers", "evaluate", "hf-doc-builder (>=0.3.0)", "parameterized", "pytest (>=7.2.0,<=8.0.0)", "pytest-subtests", "pytest-xdist", "rich", "ruff (>=0.6.4,<0.7.0)", "scikit-learn", "scipy", "timm", "torchdata (>=0.8.0)", "torchpippy (>=0.2.0)", "tqdm", "transformers"]
+dev = ["bitsandbytes", "black (>=23.1,<24.0)", "datasets", "diffusers", "evaluate", "hf-doc-builder (>=0.3.0)", "parameterized", "pytest (>=7.2.0,<=8.0.0)", "pytest-order", "pytest-subtests", "pytest-xdist", "rich", "ruff (>=0.6.4,<0.7.0)", "scikit-learn", "scipy", "timm", "torchdata (>=0.8.0)", "torchpippy (>=0.2.0)", "tqdm", "transformers"]
 quality = ["black (>=23.1,<24.0)", "hf-doc-builder (>=0.3.0)", "ruff (>=0.6.4,<0.7.0)"]
 rich = ["rich"]
 sagemaker = ["sagemaker"]
 test-dev = ["bitsandbytes", "datasets", "diffusers", "evaluate", "scikit-learn", "scipy", "timm", "torchdata (>=0.8.0)", "torchpippy (>=0.2.0)", "tqdm", "transformers"]
-test-prod = ["parameterized", "pytest (>=7.2.0,<=8.0.0)", "pytest-subtests", "pytest-xdist"]
+test-prod = ["parameterized", "pytest (>=7.2.0,<=8.0.0)", "pytest-order", "pytest-subtests", "pytest-xdist"]
 test-trackers = ["comet-ml", "dvclive", "tensorboard", "wandb"]
-testing = ["bitsandbytes", "datasets", "diffusers", "evaluate", "parameterized", "pytest (>=7.2.0,<=8.0.0)", "pytest-subtests", "pytest-xdist", "scikit-learn", "scipy", "timm", "torchdata (>=0.8.0)", "torchpippy (>=0.2.0)", "tqdm", "transformers"]
+testing = ["bitsandbytes", "datasets", "diffusers", "evaluate", "parameterized", "pytest (>=7.2.0,<=8.0.0)", "pytest-order", "pytest-subtests", "pytest-xdist", "scikit-learn", "scipy", "timm", "torchdata (>=0.8.0)", "torchpippy (>=0.2.0)", "tqdm", "transformers"]
 
 [[package]]
 name = "aiohappyeyeballs"
-version = "2.4.8"
+version = "2.6.1"
 description = "Happy Eyeballs for asyncio"
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "aiohappyeyeballs-2.4.8-py3-none-any.whl", hash = "sha256:6cac4f5dd6e34a9644e69cf9021ef679e4394f54e58a183056d12009e42ea9e3"},
-    {file = "aiohappyeyeballs-2.4.8.tar.gz", hash = "sha256:19728772cb12263077982d2f55453babd8bec6a052a926cd5c0c42796da8bf62"},
+    {file = "aiohappyeyeballs-2.6.1-py3-none-any.whl", hash = "sha256:f349ba8f4b75cb25c99c5c2d84e997e485204d2902a9597802b0371f09331fb8"},
+    {file = "aiohappyeyeballs-2.6.1.tar.gz", hash = "sha256:c3f9d0113123803ccadfdf3f0faa505bc78e6a72d1cc4806cbd719826e943558"},
 ]
 
 [[package]]
@@ -250,20 +250,20 @@ files = [
 
 [[package]]
 name = "attrs"
-version = "25.1.0"
+version = "25.3.0"
 description = "Classes Without Boilerplate"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "attrs-25.1.0-py3-none-any.whl", hash = "sha256:c75a69e28a550a7e93789579c22aa26b0f5b83b75dc4e08fe092980051e1090a"},
-    {file = "attrs-25.1.0.tar.gz", hash = "sha256:1c97078a80c814273a76b2a298a932eb681c87415c11dee0a6921de7f1b02c3e"},
+    {file = "attrs-25.3.0-py3-none-any.whl", hash = "sha256:427318ce031701fea540783410126f03899a97ffc6f61596ad581ac2e40e3bc3"},
+    {file = "attrs-25.3.0.tar.gz", hash = "sha256:75d7cefc7fb576747b2c81b4442d4d4a1ce0900973527c011d1030fd3bf4af1b"},
 ]
 
 [package.extras]
 benchmark = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
 cov = ["cloudpickle", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
 dev = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pre-commit-uv", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
-docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
+docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier"]
 tests = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
 tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
 
@@ -787,37 +787,37 @@ vision = ["Pillow (>=9.4.0)"]
 
 [[package]]
 name = "debugpy"
-version = "1.8.12"
+version = "1.8.13"
 description = "An implementation of the Debug Adapter Protocol for Python"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "debugpy-1.8.12-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:a2ba7ffe58efeae5b8fad1165357edfe01464f9aef25e814e891ec690e7dd82a"},
-    {file = "debugpy-1.8.12-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cbbd4149c4fc5e7d508ece083e78c17442ee13b0e69bfa6bd63003e486770f45"},
-    {file = "debugpy-1.8.12-cp310-cp310-win32.whl", hash = "sha256:b202f591204023b3ce62ff9a47baa555dc00bb092219abf5caf0e3718ac20e7c"},
-    {file = "debugpy-1.8.12-cp310-cp310-win_amd64.whl", hash = "sha256:9649eced17a98ce816756ce50433b2dd85dfa7bc92ceb60579d68c053f98dff9"},
-    {file = "debugpy-1.8.12-cp311-cp311-macosx_14_0_universal2.whl", hash = "sha256:36f4829839ef0afdfdd208bb54f4c3d0eea86106d719811681a8627ae2e53dd5"},
-    {file = "debugpy-1.8.12-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a28ed481d530e3138553be60991d2d61103ce6da254e51547b79549675f539b7"},
-    {file = "debugpy-1.8.12-cp311-cp311-win32.whl", hash = "sha256:4ad9a94d8f5c9b954e0e3b137cc64ef3f579d0df3c3698fe9c3734ee397e4abb"},
-    {file = "debugpy-1.8.12-cp311-cp311-win_amd64.whl", hash = "sha256:4703575b78dd697b294f8c65588dc86874ed787b7348c65da70cfc885efdf1e1"},
-    {file = "debugpy-1.8.12-cp312-cp312-macosx_14_0_universal2.whl", hash = "sha256:7e94b643b19e8feb5215fa508aee531387494bf668b2eca27fa769ea11d9f498"},
-    {file = "debugpy-1.8.12-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:086b32e233e89a2740c1615c2f775c34ae951508b28b308681dbbb87bba97d06"},
-    {file = "debugpy-1.8.12-cp312-cp312-win32.whl", hash = "sha256:2ae5df899732a6051b49ea2632a9ea67f929604fd2b036613a9f12bc3163b92d"},
-    {file = "debugpy-1.8.12-cp312-cp312-win_amd64.whl", hash = "sha256:39dfbb6fa09f12fae32639e3286112fc35ae976114f1f3d37375f3130a820969"},
-    {file = "debugpy-1.8.12-cp313-cp313-macosx_14_0_universal2.whl", hash = "sha256:696d8ae4dff4cbd06bf6b10d671e088b66669f110c7c4e18a44c43cf75ce966f"},
-    {file = "debugpy-1.8.12-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:898fba72b81a654e74412a67c7e0a81e89723cfe2a3ea6fcd3feaa3395138ca9"},
-    {file = "debugpy-1.8.12-cp313-cp313-win32.whl", hash = "sha256:22a11c493c70413a01ed03f01c3c3a2fc4478fc6ee186e340487b2edcd6f4180"},
-    {file = "debugpy-1.8.12-cp313-cp313-win_amd64.whl", hash = "sha256:fdb3c6d342825ea10b90e43d7f20f01535a72b3a1997850c0c3cefa5c27a4a2c"},
-    {file = "debugpy-1.8.12-cp38-cp38-macosx_14_0_x86_64.whl", hash = "sha256:b0232cd42506d0c94f9328aaf0d1d0785f90f87ae72d9759df7e5051be039738"},
-    {file = "debugpy-1.8.12-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9af40506a59450f1315168d47a970db1a65aaab5df3833ac389d2899a5d63b3f"},
-    {file = "debugpy-1.8.12-cp38-cp38-win32.whl", hash = "sha256:5cc45235fefac57f52680902b7d197fb2f3650112379a6fa9aa1b1c1d3ed3f02"},
-    {file = "debugpy-1.8.12-cp38-cp38-win_amd64.whl", hash = "sha256:557cc55b51ab2f3371e238804ffc8510b6ef087673303890f57a24195d096e61"},
-    {file = "debugpy-1.8.12-cp39-cp39-macosx_14_0_x86_64.whl", hash = "sha256:b5c6c967d02fee30e157ab5227706f965d5c37679c687b1e7bbc5d9e7128bd41"},
-    {file = "debugpy-1.8.12-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:88a77f422f31f170c4b7e9ca58eae2a6c8e04da54121900651dfa8e66c29901a"},
-    {file = "debugpy-1.8.12-cp39-cp39-win32.whl", hash = "sha256:a4042edef80364239f5b7b5764e55fd3ffd40c32cf6753da9bda4ff0ac466018"},
-    {file = "debugpy-1.8.12-cp39-cp39-win_amd64.whl", hash = "sha256:f30b03b0f27608a0b26c75f0bb8a880c752c0e0b01090551b9d87c7d783e2069"},
-    {file = "debugpy-1.8.12-py2.py3-none-any.whl", hash = "sha256:274b6a2040349b5c9864e475284bce5bb062e63dce368a394b8cc865ae3b00c6"},
-    {file = "debugpy-1.8.12.tar.gz", hash = "sha256:646530b04f45c830ceae8e491ca1c9320a2d2f0efea3141487c82130aba70dce"},
+    {file = "debugpy-1.8.13-cp310-cp310-macosx_14_0_x86_64.whl", hash = "sha256:06859f68e817966723ffe046b896b1bd75c665996a77313370336ee9e1de3e90"},
+    {file = "debugpy-1.8.13-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cb56c2db69fb8df3168bc857d7b7d2494fed295dfdbde9a45f27b4b152f37520"},
+    {file = "debugpy-1.8.13-cp310-cp310-win32.whl", hash = "sha256:46abe0b821cad751fc1fb9f860fb2e68d75e2c5d360986d0136cd1db8cad4428"},
+    {file = "debugpy-1.8.13-cp310-cp310-win_amd64.whl", hash = "sha256:dc7b77f5d32674686a5f06955e4b18c0e41fb5a605f5b33cf225790f114cfeec"},
+    {file = "debugpy-1.8.13-cp311-cp311-macosx_14_0_universal2.whl", hash = "sha256:eee02b2ed52a563126c97bf04194af48f2fe1f68bb522a312b05935798e922ff"},
+    {file = "debugpy-1.8.13-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4caca674206e97c85c034c1efab4483f33971d4e02e73081265ecb612af65377"},
+    {file = "debugpy-1.8.13-cp311-cp311-win32.whl", hash = "sha256:7d9a05efc6973b5aaf076d779cf3a6bbb1199e059a17738a2aa9d27a53bcc888"},
+    {file = "debugpy-1.8.13-cp311-cp311-win_amd64.whl", hash = "sha256:62f9b4a861c256f37e163ada8cf5a81f4c8d5148fc17ee31fb46813bd658cdcc"},
+    {file = "debugpy-1.8.13-cp312-cp312-macosx_14_0_universal2.whl", hash = "sha256:2b8de94c5c78aa0d0ed79023eb27c7c56a64c68217d881bee2ffbcb13951d0c1"},
+    {file = "debugpy-1.8.13-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:887d54276cefbe7290a754424b077e41efa405a3e07122d8897de54709dbe522"},
+    {file = "debugpy-1.8.13-cp312-cp312-win32.whl", hash = "sha256:3872ce5453b17837ef47fb9f3edc25085ff998ce63543f45ba7af41e7f7d370f"},
+    {file = "debugpy-1.8.13-cp312-cp312-win_amd64.whl", hash = "sha256:63ca7670563c320503fea26ac688988d9d6b9c6a12abc8a8cf2e7dd8e5f6b6ea"},
+    {file = "debugpy-1.8.13-cp313-cp313-macosx_14_0_universal2.whl", hash = "sha256:31abc9618be4edad0b3e3a85277bc9ab51a2d9f708ead0d99ffb5bb750e18503"},
+    {file = "debugpy-1.8.13-cp313-cp313-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a0bd87557f97bced5513a74088af0b84982b6ccb2e254b9312e29e8a5c4270eb"},
+    {file = "debugpy-1.8.13-cp313-cp313-win32.whl", hash = "sha256:5268ae7fdca75f526d04465931cb0bd24577477ff50e8bb03dab90983f4ebd02"},
+    {file = "debugpy-1.8.13-cp313-cp313-win_amd64.whl", hash = "sha256:79ce4ed40966c4c1631d0131606b055a5a2f8e430e3f7bf8fd3744b09943e8e8"},
+    {file = "debugpy-1.8.13-cp38-cp38-macosx_14_0_x86_64.whl", hash = "sha256:acf39a6e98630959763f9669feddee540745dfc45ad28dbc9bd1f9cd60639391"},
+    {file = "debugpy-1.8.13-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:924464d87e7d905eb0d79fb70846558910e906d9ee309b60c4fe597a2e802590"},
+    {file = "debugpy-1.8.13-cp38-cp38-win32.whl", hash = "sha256:3dae443739c6b604802da9f3e09b0f45ddf1cf23c99161f3a1a8039f61a8bb89"},
+    {file = "debugpy-1.8.13-cp38-cp38-win_amd64.whl", hash = "sha256:ed93c3155fc1f888ab2b43626182174e457fc31b7781cd1845629303790b8ad1"},
+    {file = "debugpy-1.8.13-cp39-cp39-macosx_14_0_x86_64.whl", hash = "sha256:6fab771639332bd8ceb769aacf454a30d14d7a964f2012bf9c4e04c60f16e85b"},
+    {file = "debugpy-1.8.13-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:32b6857f8263a969ce2ca098f228e5cc0604d277447ec05911a8c46cf3e7e307"},
+    {file = "debugpy-1.8.13-cp39-cp39-win32.whl", hash = "sha256:f14d2c4efa1809da125ca62df41050d9c7cd9cb9e380a2685d1e453c4d450ccb"},
+    {file = "debugpy-1.8.13-cp39-cp39-win_amd64.whl", hash = "sha256:ea869fe405880327497e6945c09365922c79d2a1eed4c3ae04d77ac7ae34b2b5"},
+    {file = "debugpy-1.8.13-py2.py3-none-any.whl", hash = "sha256:d4ba115cdd0e3a70942bd562adba9ec8c651fe69ddde2298a1be296fc331906f"},
+    {file = "debugpy-1.8.13.tar.gz", hash = "sha256:837e7bef95bdefba426ae38b9a94821ebdc5bea55627879cd48165c90b9e50ce"},
 ]
 
 [[package]]
@@ -870,13 +870,13 @@ files = [
 
 [[package]]
 name = "docling-core"
-version = "2.22.0"
+version = "2.23.0"
 description = "A python library to define and validate data types in Docling."
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "docling_core-2.22.0-py3-none-any.whl", hash = "sha256:d74d351024d016f46a09f171fb9d2d78809b132e18e25176af517ac4203c858c"},
-    {file = "docling_core-2.22.0.tar.gz", hash = "sha256:5e4bf15884560a5dc66482206f875d152701bb809f0ed52bbbe86133e0d559e2"},
+    {file = "docling_core-2.23.0-py3-none-any.whl", hash = "sha256:de17e2821216cc1817f99e226d2bad28f226289644fbffdf442ad282c842a79a"},
+    {file = "docling_core-2.23.0.tar.gz", hash = "sha256:16a5dbca0a639aa5c49b58ceb7a98e7e1dd24cd956912c68f573f77164c96526"},
 ]
 
 [package.dependencies]
@@ -929,43 +929,43 @@ transformers = [
 
 [[package]]
 name = "docling-parse"
-version = "3.4.0"
+version = "4.0.0"
 description = "Simple package to extract text with coordinates from programmatic PDFs"
 optional = false
 python-versions = "<4.0,>=3.9"
 files = [
-    {file = "docling_parse-3.4.0-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:96e95e63ab722dfe5340fcb04d0e07bd1c0a0ba2f62e93c91ac26dda0a312a44"},
-    {file = "docling_parse-3.4.0-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:f9e14a7a0b92526d4dfd3f390f3d7e075f59d14d6b8a0a564fbc26299e56cd47"},
-    {file = "docling_parse-3.4.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fdef1d51291e841e5b6a32689a39a9f35986389f863b415eaa1790b29d021101"},
-    {file = "docling_parse-3.4.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:68652610d6c34adc684dbaa77b5d596b25d004912a78e85ec4ae57910bf7086f"},
-    {file = "docling_parse-3.4.0-cp310-cp310-win_amd64.whl", hash = "sha256:daad07fe93f306d8e2378acb24ef2fa68535ccdb960a1b99d6b36ab8c299fef1"},
-    {file = "docling_parse-3.4.0-cp311-cp311-macosx_13_0_x86_64.whl", hash = "sha256:6f30c5fd3c04bd3d1a7d06baeae2e5c3adbebc284071a9a52b0150bcd4917a3d"},
-    {file = "docling_parse-3.4.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:2c3664e4c8980dc44e0d026b1b01fbc94f0dac9adf7be835071d4a761977c36d"},
-    {file = "docling_parse-3.4.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3febf7515453d18df03c275356db2bb5b0618ba9fc033aba05d58318a9846b1a"},
-    {file = "docling_parse-3.4.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:75aeb038bb7f6400ecde99cf6c4ef35867c528ac21676071a822ed72d0653149"},
-    {file = "docling_parse-3.4.0-cp311-cp311-win_amd64.whl", hash = "sha256:8d20e3584022542448c21ed0ac868b2457ae35211cea63ed20142e375549e633"},
-    {file = "docling_parse-3.4.0-cp312-cp312-macosx_13_0_x86_64.whl", hash = "sha256:ddfe2bd730ed08363f25954a0480da021e6e6bdb175276643cc2913a6bbd98e2"},
-    {file = "docling_parse-3.4.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:faf8ba9eaab8c17ea72516be5d440f754fcca27f37488dcf126a0f3ac3a63058"},
-    {file = "docling_parse-3.4.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9eb5e7e50b3057690d0d4fa651363cafd7735bb952378dd8a4ca6c7d359507db"},
-    {file = "docling_parse-3.4.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:452334b387e2c699f69acf37a4ea4ae7097d062a2dd1980c573b73051c031158"},
-    {file = "docling_parse-3.4.0-cp312-cp312-win_amd64.whl", hash = "sha256:1ba00147ccb0a1dc10cdf58645e67f4ee895c6920bc583bc6f25d27cd562bfed"},
-    {file = "docling_parse-3.4.0-cp313-cp313-macosx_13_0_x86_64.whl", hash = "sha256:2b22a33a2d2f3616a7ac0f4b2f2ba6099f8a5dc6fa328be0f17c9c506455d7c1"},
-    {file = "docling_parse-3.4.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:0dd2440a94d555f98b702e88bfe7cc5a585d9191f4ea93884b02e286e7af3a06"},
-    {file = "docling_parse-3.4.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5f5828744a0e33136e09e8c61ca0b2c0ead8f76595f2e0955beaac16adce51f5"},
-    {file = "docling_parse-3.4.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:26fff6e36809d17ff855532f985df3738ada8d86a9fc746049ea6e6524d5e0a2"},
-    {file = "docling_parse-3.4.0-cp313-cp313-win_amd64.whl", hash = "sha256:13fc442f64171280db98dc4507274ffa0a65bac94eecbcc60c3cbf41f433b556"},
-    {file = "docling_parse-3.4.0-cp39-cp39-macosx_13_0_x86_64.whl", hash = "sha256:16d570ab655ea5a25d9cd1e27bc4d6905372784907d679cde4cef2fb22df61c7"},
-    {file = "docling_parse-3.4.0-cp39-cp39-macosx_14_0_arm64.whl", hash = "sha256:05bd405635be2379ef6cb0c7c39dc08edf3ba93788eb0fca7426b2218538bce1"},
-    {file = "docling_parse-3.4.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f6c92f0353bbae7ca9b39553cc4d03f5fefdab33ecd26809ab710cc752fac03c"},
-    {file = "docling_parse-3.4.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8e883326ec4121891c48d365d064e5ae30c5b90a2dac44ed61ac02e7da41345d"},
-    {file = "docling_parse-3.4.0-cp39-cp39-win_amd64.whl", hash = "sha256:b2a0fe1e1d88c3814553137daa597ee34dc310f50fe415e1f8a1c6e611d95e42"},
-    {file = "docling_parse-3.4.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:930f5a5d78404de573c0ba302d313b6647f1e86714766e5a1cdc09af014ca111"},
-    {file = "docling_parse-3.4.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:328fd72f274b939d454e3ff20a73074d99664cb4a51e6ccdaf195a6626691b95"},
-    {file = "docling_parse-3.4.0.tar.gz", hash = "sha256:36cdd17bcc4a833b5c9af9ae3dc461ed18a975c1b084ccfd19a9d9cde4f66e14"},
+    {file = "docling_parse-4.0.0-cp310-cp310-macosx_13_0_x86_64.whl", hash = "sha256:6de7fa8ec4919f604c9a02a3fa8ca0e13a3a8e3c0652adc41848616b737925d9"},
+    {file = "docling_parse-4.0.0-cp310-cp310-macosx_14_0_arm64.whl", hash = "sha256:82704280ab086a84a30d9ec9def6cd96b733aefc6973546b2101d09eed7a958e"},
+    {file = "docling_parse-4.0.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f51ec645978d75e7cf232fa7c571ebf164a5bdf418588c663f9b3c062df6ba72"},
+    {file = "docling_parse-4.0.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d5da855f35303f9229198891da550e3c1e1f4025e52ab8c0303d345669ff46f"},
+    {file = "docling_parse-4.0.0-cp310-cp310-win_amd64.whl", hash = "sha256:ba36cb329aadb306cc25901305d49fe6d2ed9e93e9dc993b4baf13fcc90a98e1"},
+    {file = "docling_parse-4.0.0-cp311-cp311-macosx_13_0_x86_64.whl", hash = "sha256:9b7afbf09945b4d9e3ddb9c24a13d7b9f987cf32d5c9d68532ceb63fb26697df"},
+    {file = "docling_parse-4.0.0-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:6daaec89c5045e968785a225b9b5a42b36dfe6b5a4437995e2d34e1595e2c162"},
+    {file = "docling_parse-4.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:93e638ef2ad36e9e4a8ef881073696467e6699bf206e5a416de4abaaf531b0e1"},
+    {file = "docling_parse-4.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:87246eb0d259202a7f093336f17235cb1fffb67e82b41dbc0e88f9c05b08014e"},
+    {file = "docling_parse-4.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:0ae44b913b010994c3e36869e5fc9dad252a7dc7434225790928075c8b5a7f6c"},
+    {file = "docling_parse-4.0.0-cp312-cp312-macosx_13_0_x86_64.whl", hash = "sha256:ed6d8ac29c1014ed7a126d782b6bc963c9a9c09f41224fa90f9a8b45bf3191f9"},
+    {file = "docling_parse-4.0.0-cp312-cp312-macosx_14_0_arm64.whl", hash = "sha256:4a2dd46cee8e54f3aa511dbf552ef5f9f422944c54de73888ee55b2c4a6e10b9"},
+    {file = "docling_parse-4.0.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:722fbd63f7f28e8a49fa2cd92d1571290f6c5295b86c7406b7c20a6c6e8b3975"},
+    {file = "docling_parse-4.0.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cc155767b51a23f5bfd5abaabaf8c4a57777aa0277c813e13b9f6c43532964bd"},
+    {file = "docling_parse-4.0.0-cp312-cp312-win_amd64.whl", hash = "sha256:e45ab31fffe4ae571bd2ecc9e0a9d5665a1486463396924160add84828d2a7e7"},
+    {file = "docling_parse-4.0.0-cp313-cp313-macosx_13_0_x86_64.whl", hash = "sha256:d93fd3cec032e5b7f6385f7a021e228c52eb381f28fc037224708aeaad487d8b"},
+    {file = "docling_parse-4.0.0-cp313-cp313-macosx_14_0_arm64.whl", hash = "sha256:d9f64847cd7e9a7a34a3d5a14f0827022ed3b7f50f39d5126ef003c55d574ba3"},
+    {file = "docling_parse-4.0.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a6ac283f08680dfde568b5629ab94830cab32795d74086553e755460b6879901"},
+    {file = "docling_parse-4.0.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:97eca28220dc5075099e01f2cb7a3e9005b9951dee0ca0eb743e298be7284279"},
+    {file = "docling_parse-4.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:6019288cfe25a97993c2aab453386fc3e366d7761637e682b25915ba2c856cc4"},
+    {file = "docling_parse-4.0.0-cp39-cp39-macosx_13_0_x86_64.whl", hash = "sha256:168c861233fc2a1e4b7d934aa6f7e1b3f568434fd478f18f0b3bcc09880d504c"},
+    {file = "docling_parse-4.0.0-cp39-cp39-macosx_14_0_arm64.whl", hash = "sha256:b1cc0b7a214bc9e4e05c65572c4a17c19d0f4f0795fe1fa77a0ad499ab7e4e79"},
+    {file = "docling_parse-4.0.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cec16060eba37db3fa2ff0b34d283cf33384caecc73b0d8dbf012e3b3941c21d"},
+    {file = "docling_parse-4.0.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6a058c2330d7759d943ae50db9e4ecab60201a54116052f94e6e7a3886886b65"},
+    {file = "docling_parse-4.0.0-cp39-cp39-win_amd64.whl", hash = "sha256:05af04972fef73f2e10cc46c8f541aaf6713fdcad254502a0012884109c1d468"},
+    {file = "docling_parse-4.0.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:30c0c1b33c0a0aeb6897537f7d8fa09ed5a26f05685b18a2d27c73a789343679"},
+    {file = "docling_parse-4.0.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:2dff48f5fef106539137a4e63ee58b5be0e7a81ac1aedd61a4453c268b8f76d1"},
+    {file = "docling_parse-4.0.0.tar.gz", hash = "sha256:5be0ba4e0098524f116743e6b709f29fe273e441e61923c3a262e054643c5ee6"},
 ]
 
 [package.dependencies]
-docling-core = ">=2.14.0,<3.0.0"
+docling-core = ">=2.23.0,<3.0.0"
 pillow = ">=10.0.0,<12.0.0"
 pydantic = ">=2.0.0,<3.0.0"
 pywin32 = {version = ">=305", markers = "sys_platform == \"win32\""}
@@ -1086,13 +1086,13 @@ devel = ["colorama", "json-spec", "jsonschema", "pylint", "pytest", "pytest-benc
 
 [[package]]
 name = "filelock"
-version = "3.17.0"
+version = "3.18.0"
 description = "A platform independent file lock."
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "filelock-3.17.0-py3-none-any.whl", hash = "sha256:533dc2f7ba78dc2f0f531fc6c4940addf7b70a481e269a5a3b93be94ffbe8338"},
-    {file = "filelock-3.17.0.tar.gz", hash = "sha256:ee4e77401ef576ebb38cd7f13b9b28893194acc20a8e68e18730ba9c0e54660e"},
+    {file = "filelock-3.18.0-py3-none-any.whl", hash = "sha256:c401f4f8377c4464e6db25fff06205fd89bdd83b65eb0488ed1b160f780e21de"},
+    {file = "filelock-3.18.0.tar.gz", hash = "sha256:adbc88eabb99d2fec8c9c1b229b171f18afa655400173ddc653d5d01501fb9f2"},
 ]
 
 [package.extras]
@@ -1500,13 +1500,13 @@ zstd = ["zstandard (>=0.18.0)"]
 
 [[package]]
 name = "huggingface-hub"
-version = "0.29.1"
+version = "0.29.3"
 description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "huggingface_hub-0.29.1-py3-none-any.whl", hash = "sha256:352f69caf16566c7b6de84b54a822f6238e17ddd8ae3da4f8f2272aea5b198d5"},
-    {file = "huggingface_hub-0.29.1.tar.gz", hash = "sha256:9524eae42077b8ff4fc459ceb7a514eca1c1232b775276b009709fe2a084f250"},
+    {file = "huggingface_hub-0.29.3-py3-none-any.whl", hash = "sha256:0b25710932ac649c08cdbefa6c6ccb8e88eef82927cacdb048efb726429453aa"},
+    {file = "huggingface_hub-0.29.3.tar.gz", hash = "sha256:64519a25716e0ba382ba2d3fb3ca082e7c7eb4a2fc634d200e8380006e0760e5"},
 ]
 
 [package.dependencies]
@@ -1548,13 +1548,13 @@ pyreadline3 = {version = "*", markers = "sys_platform == \"win32\" and python_ve
 
 [[package]]
 name = "identify"
-version = "2.6.8"
+version = "2.6.9"
 description = "File identification library for Python"
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "identify-2.6.8-py2.py3-none-any.whl", hash = "sha256:83657f0f766a3c8d0eaea16d4ef42494b39b34629a4b3192a9d020d349b3e255"},
-    {file = "identify-2.6.8.tar.gz", hash = "sha256:61491417ea2c0c5c670484fd8abbb34de34cdae1e5f39a73ee65e48e4bb663fc"},
+    {file = "identify-2.6.9-py2.py3-none-any.whl", hash = "sha256:c98b4322da415a8e5a70ff6e51fbc2d2932c015532d77e9f8537b4ba7813b150"},
+    {file = "identify-2.6.9.tar.gz", hash = "sha256:d40dfe3142a1421d8518e3d3985ef5ac42890683e32306ad614a29490abeb6bf"},
 ]
 
 [package.extras]
@@ -1851,13 +1851,13 @@ trio = ["trio"]
 
 [[package]]
 name = "jinja2"
-version = "3.1.5"
+version = "3.1.6"
 description = "A very fast and expressive template engine."
 optional = false
 python-versions = ">=3.7"
 files = [
-    {file = "jinja2-3.1.5-py3-none-any.whl", hash = "sha256:aba0f4dc9ed8013c424088f68a5c226f7d6097ed89b246d7749c2ec4175c6adb"},
-    {file = "jinja2-3.1.5.tar.gz", hash = "sha256:8fefff8dc3034e27bb80d67c671eb8a9bc424c0ef4c0826edbff304cceff43bb"},
+    {file = "jinja2-3.1.6-py3-none-any.whl", hash = "sha256:85ece4451f492d0c13c5dd7c13a64681a86afae63a5f347908daf103ce6d2f67"},
+    {file = "jinja2-3.1.6.tar.gz", hash = "sha256:0137fb05990d35f1275a587e9aee6d56da821fc83491a0fb838183be43f66d6d"},
 ]
 
 [package.dependencies]
@@ -2666,13 +2666,13 @@ min-versions = ["babel (==2.9.0)", "click (==7.0)", "colorama (==0.4)", "ghp-imp
 
 [[package]]
 name = "mkdocs-autorefs"
-version = "1.4.0"
+version = "1.4.1"
 description = "Automatically link across pages in MkDocs."
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "mkdocs_autorefs-1.4.0-py3-none-any.whl", hash = "sha256:bad19f69655878d20194acd0162e29a89c3f7e6365ffe54e72aa3fd1072f240d"},
-    {file = "mkdocs_autorefs-1.4.0.tar.gz", hash = "sha256:a9c0aa9c90edbce302c09d050a3c4cb7c76f8b7b2c98f84a7a05f53d00392156"},
+    {file = "mkdocs_autorefs-1.4.1-py3-none-any.whl", hash = "sha256:9793c5ac06a6ebbe52ec0f8439256e66187badf4b5334b5fde0b128ec134df4f"},
+    {file = "mkdocs_autorefs-1.4.1.tar.gz", hash = "sha256:4b5b6235a4becb2b10425c2fa191737e415b37aa3418919db33e5d774c9db079"},
 ]
 
 [package.dependencies]
@@ -2733,13 +2733,13 @@ pygments = ">2.12.0"
 
 [[package]]
 name = "mkdocs-material"
-version = "9.6.7"
+version = "9.6.8"
 description = "Documentation that simply works"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "mkdocs_material-9.6.7-py3-none-any.whl", hash = "sha256:8a159e45e80fcaadd9fbeef62cbf928569b93df954d4dc5ba76d46820caf7b47"},
-    {file = "mkdocs_material-9.6.7.tar.gz", hash = "sha256:3e2c1fceb9410056c2d91f334a00cdea3215c28750e00c691c1e46b2a33309b4"},
+    {file = "mkdocs_material-9.6.8-py3-none-any.whl", hash = "sha256:0a51532dd8aa80b232546c073fe3ef60dfaef1b1b12196ac7191ee01702d1cf8"},
+    {file = "mkdocs_material-9.6.8.tar.gz", hash = "sha256:8de31bb7566379802532b248bd56d9c4bc834afc4625884bf5769f9412c6a354"},
 ]
 
 [package.dependencies]
@@ -3703,14 +3703,14 @@ files = [
 
 [[package]]
 name = "nvidia-nvjitlink-cu12"
-version = "12.8.61"
+version = "12.8.93"
 description = "Nvidia JIT LTO Library"
 optional = false
 python-versions = ">=3"
 files = [
-    {file = "nvidia_nvjitlink_cu12-12.8.61-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:45fd79f2ae20bd67e8bc411055939049873bfd8fac70ff13bd4865e0b9bdab17"},
-    {file = "nvidia_nvjitlink_cu12-12.8.61-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:9b80ecab31085dda3ce3b41d043be0ec739216c3fc633b8abe212d5a30026df0"},
-    {file = "nvidia_nvjitlink_cu12-12.8.61-py3-none-win_amd64.whl", hash = "sha256:1166a964d25fdc0eae497574d38824305195a5283324a21ccb0ce0c802cbf41c"},
+    {file = "nvidia_nvjitlink_cu12-12.8.93-py3-none-manylinux2010_x86_64.manylinux_2_12_x86_64.whl", hash = "sha256:81ff63371a7ebd6e6451970684f916be2eab07321b73c9d244dc2b4da7f73b88"},
+    {file = "nvidia_nvjitlink_cu12-12.8.93-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:adccd7161ace7261e01bb91e44e88da350895c270d23f744f0820c818b7229e7"},
+    {file = "nvidia_nvjitlink_cu12-12.8.93-py3-none-win_amd64.whl", hash = "sha256:bd93fbeeee850917903583587f4fc3a4eafa022e34572251368238ab5e6bd67f"},
 ]
 
 [[package]]
@@ -3796,32 +3796,29 @@ sympy = "*"
 
 [[package]]
 name = "onnxruntime"
-version = "1.20.1"
+version = "1.21.0"
 description = "ONNX Runtime is a runtime accelerator for Machine Learning models"
 optional = true
-python-versions = "*"
+python-versions = ">=3.10"
 files = [
-    {file = "onnxruntime-1.20.1-cp310-cp310-macosx_13_0_universal2.whl", hash = "sha256:e50ba5ff7fed4f7d9253a6baf801ca2883cc08491f9d32d78a80da57256a5439"},
-    {file = "onnxruntime-1.20.1-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7b2908b50101a19e99c4d4e97ebb9905561daf61829403061c1adc1b588bc0de"},
-    {file = "onnxruntime-1.20.1-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:d82daaec24045a2e87598b8ac2b417b1cce623244e80e663882e9fe1aae86410"},
-    {file = "onnxruntime-1.20.1-cp310-cp310-win32.whl", hash = "sha256:4c4b251a725a3b8cf2aab284f7d940c26094ecd9d442f07dd81ab5470e99b83f"},
-    {file = "onnxruntime-1.20.1-cp310-cp310-win_amd64.whl", hash = "sha256:d3b616bb53a77a9463707bb313637223380fc327f5064c9a782e8ec69c22e6a2"},
-    {file = "onnxruntime-1.20.1-cp311-cp311-macosx_13_0_universal2.whl", hash = "sha256:06bfbf02ca9ab5f28946e0f912a562a5f005301d0c419283dc57b3ed7969bb7b"},
-    {file = "onnxruntime-1.20.1-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f6243e34d74423bdd1edf0ae9596dd61023b260f546ee17d701723915f06a9f7"},
-    {file = "onnxruntime-1.20.1-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:5eec64c0269dcdb8d9a9a53dc4d64f87b9e0c19801d9321246a53b7eb5a7d1bc"},
-    {file = "onnxruntime-1.20.1-cp311-cp311-win32.whl", hash = "sha256:a19bc6e8c70e2485a1725b3d517a2319603acc14c1f1a017dda0afe6d4665b41"},
-    {file = "onnxruntime-1.20.1-cp311-cp311-win_amd64.whl", hash = "sha256:8508887eb1c5f9537a4071768723ec7c30c28eb2518a00d0adcd32c89dea3221"},
-    {file = "onnxruntime-1.20.1-cp312-cp312-macosx_13_0_universal2.whl", hash = "sha256:22b0655e2bf4f2161d52706e31f517a0e54939dc393e92577df51808a7edc8c9"},
-    {file = "onnxruntime-1.20.1-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:f1f56e898815963d6dc4ee1c35fc6c36506466eff6d16f3cb9848cea4e8c8172"},
-    {file = "onnxruntime-1.20.1-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bb71a814f66517a65628c9e4a2bb530a6edd2cd5d87ffa0af0f6f773a027d99e"},
-    {file = "onnxruntime-1.20.1-cp312-cp312-win32.whl", hash = "sha256:bd386cc9ee5f686ee8a75ba74037750aca55183085bf1941da8efcfe12d5b120"},
-    {file = "onnxruntime-1.20.1-cp312-cp312-win_amd64.whl", hash = "sha256:19c2d843eb074f385e8bbb753a40df780511061a63f9def1b216bf53860223fb"},
-    {file = "onnxruntime-1.20.1-cp313-cp313-macosx_13_0_universal2.whl", hash = "sha256:cc01437a32d0042b606f462245c8bbae269e5442797f6213e36ce61d5abdd8cc"},
-    {file = "onnxruntime-1.20.1-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:fb44b08e017a648924dbe91b82d89b0c105b1adcfe31e90d1dc06b8677ad37be"},
-    {file = "onnxruntime-1.20.1-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:bda6aebdf7917c1d811f21d41633df00c58aff2bef2f598f69289c1f1dabc4b3"},
-    {file = "onnxruntime-1.20.1-cp313-cp313-win_amd64.whl", hash = "sha256:d30367df7e70f1d9fc5a6a68106f5961686d39b54d3221f760085524e8d38e16"},
-    {file = "onnxruntime-1.20.1-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:c9158465745423b2b5d97ed25aa7740c7d38d2993ee2e5c3bfacb0c4145c49d8"},
-    {file = "onnxruntime-1.20.1-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:0df6f2df83d61f46e842dbcde610ede27218947c33e994545a22333491e72a3b"},
+    {file = "onnxruntime-1.21.0-cp310-cp310-macosx_13_0_universal2.whl", hash = "sha256:95513c9302bc8dd013d84148dcf3168e782a80cdbf1654eddc948a23147ccd3d"},
+    {file = "onnxruntime-1.21.0-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:635d4ab13ae0f150dd4c6ff8206fd58f1c6600636ecc796f6f0c42e4c918585b"},
+    {file = "onnxruntime-1.21.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:7d06bfa0dd5512bd164f25a2bf594b2e7c9eabda6fc064b684924f3e81bdab1b"},
+    {file = "onnxruntime-1.21.0-cp310-cp310-win_amd64.whl", hash = "sha256:b0fc22d219791e0284ee1d9c26724b8ee3fbdea28128ef25d9507ad3b9621f23"},
+    {file = "onnxruntime-1.21.0-cp311-cp311-macosx_13_0_universal2.whl", hash = "sha256:8e16f8a79df03919810852fb46ffcc916dc87a9e9c6540a58f20c914c575678c"},
+    {file = "onnxruntime-1.21.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:7f9156cf6f8ee133d07a751e6518cf6f84ed37fbf8243156bd4a2c4ee6e073c8"},
+    {file = "onnxruntime-1.21.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:8a5d09815a9e209fa0cb20c2985b34ab4daeba7aea94d0f96b8751eb10403201"},
+    {file = "onnxruntime-1.21.0-cp311-cp311-win_amd64.whl", hash = "sha256:1d970dff1e2fa4d9c53f2787b3b7d0005596866e6a31997b41169017d1362dd0"},
+    {file = "onnxruntime-1.21.0-cp312-cp312-macosx_13_0_universal2.whl", hash = "sha256:893d67c68ca9e7a58202fa8d96061ed86a5815b0925b5a97aef27b8ba246a20b"},
+    {file = "onnxruntime-1.21.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:37b7445c920a96271a8dfa16855e258dc5599235b41c7bbde0d262d55bcc105f"},
+    {file = "onnxruntime-1.21.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:9a04aafb802c1e5573ba4552f8babcb5021b041eb4cfa802c9b7644ca3510eca"},
+    {file = "onnxruntime-1.21.0-cp312-cp312-win_amd64.whl", hash = "sha256:7f801318476cd7003d636a5b392f7a37c08b6c8d2f829773f3c3887029e03f32"},
+    {file = "onnxruntime-1.21.0-cp313-cp313-macosx_13_0_universal2.whl", hash = "sha256:85718cbde1c2912d3a03e3b3dc181b1480258a229c32378408cace7c450f7f23"},
+    {file = "onnxruntime-1.21.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:94dff3a61538f3b7b0ea9a06bc99e1410e90509c76e3a746f039e417802a12ae"},
+    {file = "onnxruntime-1.21.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:c1e704b0eda5f2bbbe84182437315eaec89a450b08854b5a7762c85d04a28a0a"},
+    {file = "onnxruntime-1.21.0-cp313-cp313-win_amd64.whl", hash = "sha256:19b630c6a8956ef97fb7c94948b17691167aa1aaf07b5f214fa66c3e4136c108"},
+    {file = "onnxruntime-1.21.0-cp313-cp313t-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:3995c4a2d81719623c58697b9510f8de9fa42a1da6b4474052797b0d712324fe"},
+    {file = "onnxruntime-1.21.0-cp313-cp313t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:36b18b8f39c0f84e783902112a0dd3c102466897f96d73bb83f6a6bff283a423"},
 ]
 
 [package.dependencies]
@@ -4438,22 +4435,20 @@ files = [
 
 [[package]]
 name = "protobuf"
-version = "5.29.3"
+version = "6.30.1"
 description = ""
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 files = [
-    {file = "protobuf-5.29.3-cp310-abi3-win32.whl", hash = "sha256:3ea51771449e1035f26069c4c7fd51fba990d07bc55ba80701c78f886bf9c888"},
-    {file = "protobuf-5.29.3-cp310-abi3-win_amd64.whl", hash = "sha256:a4fa6f80816a9a0678429e84973f2f98cbc218cca434abe8db2ad0bffc98503a"},
-    {file = "protobuf-5.29.3-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:a8434404bbf139aa9e1300dbf989667a83d42ddda9153d8ab76e0d5dcaca484e"},
-    {file = "protobuf-5.29.3-cp38-abi3-manylinux2014_aarch64.whl", hash = "sha256:daaf63f70f25e8689c072cfad4334ca0ac1d1e05a92fc15c54eb9cf23c3efd84"},
-    {file = "protobuf-5.29.3-cp38-abi3-manylinux2014_x86_64.whl", hash = "sha256:c027e08a08be10b67c06bf2370b99c811c466398c357e615ca88c91c07f0910f"},
-    {file = "protobuf-5.29.3-cp38-cp38-win32.whl", hash = "sha256:84a57163a0ccef3f96e4b6a20516cedcf5bb3a95a657131c5c3ac62200d23252"},
-    {file = "protobuf-5.29.3-cp38-cp38-win_amd64.whl", hash = "sha256:b89c115d877892a512f79a8114564fb435943b59067615894c3b13cd3e1fa107"},
-    {file = "protobuf-5.29.3-cp39-cp39-win32.whl", hash = "sha256:0eb32bfa5219fc8d4111803e9a690658aa2e6366384fd0851064b963b6d1f2a7"},
-    {file = "protobuf-5.29.3-cp39-cp39-win_amd64.whl", hash = "sha256:6ce8cc3389a20693bfde6c6562e03474c40851b44975c9b2bf6df7d8c4f864da"},
-    {file = "protobuf-5.29.3-py3-none-any.whl", hash = "sha256:0a18ed4a24198528f2333802eb075e59dea9d679ab7a6c5efb017a59004d849f"},
-    {file = "protobuf-5.29.3.tar.gz", hash = "sha256:5da0f41edaf117bde316404bad1a486cb4ededf8e4a54891296f648e8e076620"},
+    {file = "protobuf-6.30.1-cp310-abi3-win32.whl", hash = "sha256:ba0706f948d0195f5cac504da156d88174e03218d9364ab40d903788c1903d7e"},
+    {file = "protobuf-6.30.1-cp310-abi3-win_amd64.whl", hash = "sha256:ed484f9ddd47f0f1bf0648806cccdb4fe2fb6b19820f9b79a5adf5dcfd1b8c5f"},
+    {file = "protobuf-6.30.1-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:aa4f7dfaed0d840b03d08d14bfdb41348feaee06a828a8c455698234135b4075"},
+    {file = "protobuf-6.30.1-cp39-abi3-manylinux2014_aarch64.whl", hash = "sha256:47cd320b7db63e8c9ac35f5596ea1c1e61491d8a8eb6d8b45edc44760b53a4f6"},
+    {file = "protobuf-6.30.1-cp39-abi3-manylinux2014_x86_64.whl", hash = "sha256:e3083660225fa94748ac2e407f09a899e6a28bf9c0e70c75def8d15706bf85fc"},
+    {file = "protobuf-6.30.1-cp39-cp39-win32.whl", hash = "sha256:554d7e61cce2aa4c63ca27328f757a9f3867bce8ec213bf09096a8d16bcdcb6a"},
+    {file = "protobuf-6.30.1-cp39-cp39-win_amd64.whl", hash = "sha256:b510f55ce60f84dc7febc619b47215b900466e3555ab8cb1ba42deb4496d6cc0"},
+    {file = "protobuf-6.30.1-py3-none-any.whl", hash = "sha256:3c25e51e1359f1f5fa3b298faa6016e650d148f214db2e47671131b9063c53be"},
+    {file = "protobuf-6.30.1.tar.gz", hash = "sha256:535fb4e44d0236893d5cf1263a0f706f1160b689a7ab962e9da8a9ce4050b780"},
 ]
 
 [[package]]
@@ -4875,13 +4870,13 @@ extra = ["pygments (>=2.19.1)"]
 
 [[package]]
 name = "pymilvus"
-version = "2.5.4"
+version = "2.5.5"
 description = "Python Sdk for Milvus"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "pymilvus-2.5.4-py3-none-any.whl", hash = "sha256:3f7ddaeae0c8f63554b8e316b73f265d022e05a457d47c366ce47293434a3aea"},
-    {file = "pymilvus-2.5.4.tar.gz", hash = "sha256:611732428ff669d57ded3d1f823bdeb10febf233d0251cce8498b287e5a10ce8"},
+    {file = "pymilvus-2.5.5-py3-none-any.whl", hash = "sha256:b91794fbaf72c6d7ed2419b8d4e67369263bdc16f1722f02c97927cfdf3e69da"},
+    {file = "pymilvus-2.5.5.tar.gz", hash = "sha256:8985f018961853022e03639a9ff323d5c22d0b659e66e288f4d08de11789e1d4"},
 ]
 
 [package.dependencies]
@@ -4896,7 +4891,7 @@ ujson = ">=2.0.0"
 [package.extras]
 bulk-writer = ["azure-storage-blob", "minio (>=7.0.0)", "pyarrow (>=12.0.0)", "requests"]
 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)"]
+model = ["pymilvus.model (>=0.3.0)"]
 
 [[package]]
 name = "pyobjc-core"
@@ -5332,29 +5327,27 @@ files = [
 
 [[package]]
 name = "pywin32"
-version = "308"
+version = "309"
 description = "Python for Window Extensions"
 optional = false
 python-versions = "*"
 files = [
-    {file = "pywin32-308-cp310-cp310-win32.whl", hash = "sha256:796ff4426437896550d2981b9c2ac0ffd75238ad9ea2d3bfa67a1abd546d262e"},
-    {file = "pywin32-308-cp310-cp310-win_amd64.whl", hash = "sha256:4fc888c59b3c0bef905ce7eb7e2106a07712015ea1c8234b703a088d46110e8e"},
-    {file = "pywin32-308-cp310-cp310-win_arm64.whl", hash = "sha256:a5ab5381813b40f264fa3495b98af850098f814a25a63589a8e9eb12560f450c"},
-    {file = "pywin32-308-cp311-cp311-win32.whl", hash = "sha256:5d8c8015b24a7d6855b1550d8e660d8daa09983c80e5daf89a273e5c6fb5095a"},
-    {file = "pywin32-308-cp311-cp311-win_amd64.whl", hash = "sha256:575621b90f0dc2695fec346b2d6302faebd4f0f45c05ea29404cefe35d89442b"},
-    {file = "pywin32-308-cp311-cp311-win_arm64.whl", hash = "sha256:100a5442b7332070983c4cd03f2e906a5648a5104b8a7f50175f7906efd16bb6"},
-    {file = "pywin32-308-cp312-cp312-win32.whl", hash = "sha256:587f3e19696f4bf96fde9d8a57cec74a57021ad5f204c9e627e15c33ff568897"},
-    {file = "pywin32-308-cp312-cp312-win_amd64.whl", hash = "sha256:00b3e11ef09ede56c6a43c71f2d31857cf7c54b0ab6e78ac659497abd2834f47"},
-    {file = "pywin32-308-cp312-cp312-win_arm64.whl", hash = "sha256:9b4de86c8d909aed15b7011182c8cab38c8850de36e6afb1f0db22b8959e3091"},
-    {file = "pywin32-308-cp313-cp313-win32.whl", hash = "sha256:1c44539a37a5b7b21d02ab34e6a4d314e0788f1690d65b48e9b0b89f31abbbed"},
-    {file = "pywin32-308-cp313-cp313-win_amd64.whl", hash = "sha256:fd380990e792eaf6827fcb7e187b2b4b1cede0585e3d0c9e84201ec27b9905e4"},
-    {file = "pywin32-308-cp313-cp313-win_arm64.whl", hash = "sha256:ef313c46d4c18dfb82a2431e3051ac8f112ccee1a34f29c263c583c568db63cd"},
-    {file = "pywin32-308-cp37-cp37m-win32.whl", hash = "sha256:1f696ab352a2ddd63bd07430080dd598e6369152ea13a25ebcdd2f503a38f1ff"},
-    {file = "pywin32-308-cp37-cp37m-win_amd64.whl", hash = "sha256:13dcb914ed4347019fbec6697a01a0aec61019c1046c2b905410d197856326a6"},
-    {file = "pywin32-308-cp38-cp38-win32.whl", hash = "sha256:5794e764ebcabf4ff08c555b31bd348c9025929371763b2183172ff4708152f0"},
-    {file = "pywin32-308-cp38-cp38-win_amd64.whl", hash = "sha256:3b92622e29d651c6b783e368ba7d6722b1634b8e70bd376fd7610fe1992e19de"},
-    {file = "pywin32-308-cp39-cp39-win32.whl", hash = "sha256:7873ca4dc60ab3287919881a7d4f88baee4a6e639aa6962de25a98ba6b193341"},
-    {file = "pywin32-308-cp39-cp39-win_amd64.whl", hash = "sha256:71b3322d949b4cc20776436a9c9ba0eeedcbc9c650daa536df63f0ff111bb920"},
+    {file = "pywin32-309-cp310-cp310-win32.whl", hash = "sha256:5b78d98550ca093a6fe7ab6d71733fbc886e2af9d4876d935e7f6e1cd6577ac9"},
+    {file = "pywin32-309-cp310-cp310-win_amd64.whl", hash = "sha256:728d08046f3d65b90d4c77f71b6fbb551699e2005cc31bbffd1febd6a08aa698"},
+    {file = "pywin32-309-cp310-cp310-win_arm64.whl", hash = "sha256:c667bcc0a1e6acaca8984eb3e2b6e42696fc035015f99ff8bc6c3db4c09a466a"},
+    {file = "pywin32-309-cp311-cp311-win32.whl", hash = "sha256:d5df6faa32b868baf9ade7c9b25337fa5eced28eb1ab89082c8dae9c48e4cd51"},
+    {file = "pywin32-309-cp311-cp311-win_amd64.whl", hash = "sha256:e7ec2cef6df0926f8a89fd64959eba591a1eeaf0258082065f7bdbe2121228db"},
+    {file = "pywin32-309-cp311-cp311-win_arm64.whl", hash = "sha256:54ee296f6d11db1627216e9b4d4c3231856ed2d9f194c82f26c6cb5650163f4c"},
+    {file = "pywin32-309-cp312-cp312-win32.whl", hash = "sha256:de9acacced5fa82f557298b1fed5fef7bd49beee04190f68e1e4783fbdc19926"},
+    {file = "pywin32-309-cp312-cp312-win_amd64.whl", hash = "sha256:6ff9eebb77ffc3d59812c68db33c0a7817e1337e3537859499bd27586330fc9e"},
+    {file = "pywin32-309-cp312-cp312-win_arm64.whl", hash = "sha256:619f3e0a327b5418d833f44dc87859523635cf339f86071cc65a13c07be3110f"},
+    {file = "pywin32-309-cp313-cp313-win32.whl", hash = "sha256:008bffd4afd6de8ca46c6486085414cc898263a21a63c7f860d54c9d02b45c8d"},
+    {file = "pywin32-309-cp313-cp313-win_amd64.whl", hash = "sha256:bd0724f58492db4cbfbeb1fcd606495205aa119370c0ddc4f70e5771a3ab768d"},
+    {file = "pywin32-309-cp313-cp313-win_arm64.whl", hash = "sha256:8fd9669cfd41863b688a1bc9b1d4d2d76fd4ba2128be50a70b0ea66b8d37953b"},
+    {file = "pywin32-309-cp38-cp38-win32.whl", hash = "sha256:617b837dc5d9dfa7e156dbfa7d3906c009a2881849a80a9ae7519f3dd8c6cb86"},
+    {file = "pywin32-309-cp38-cp38-win_amd64.whl", hash = "sha256:0be3071f555480fbfd86a816a1a773880ee655bf186aa2931860dbb44e8424f8"},
+    {file = "pywin32-309-cp39-cp39-win32.whl", hash = "sha256:72ae9ae3a7a6473223589a1621f9001fe802d59ed227fd6a8503c9af67c1d5f4"},
+    {file = "pywin32-309-cp39-cp39-win_amd64.whl", hash = "sha256:88bc06d6a9feac70783de64089324568ecbc65866e2ab318eab35da3811fd7ef"},
 ]
 
 [[package]]
@@ -5446,120 +5439,104 @@ pyyaml = "*"
 
 [[package]]
 name = "pyzmq"
-version = "26.2.1"
+version = "26.3.0"
 description = "Python bindings for 0MQ"
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.8"
 files = [
-    {file = "pyzmq-26.2.1-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:f39d1227e8256d19899d953e6e19ed2ccb689102e6d85e024da5acf410f301eb"},
-    {file = "pyzmq-26.2.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a23948554c692df95daed595fdd3b76b420a4939d7a8a28d6d7dea9711878641"},
-    {file = "pyzmq-26.2.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:95f5728b367a042df146cec4340d75359ec6237beebf4a8f5cf74657c65b9257"},
-    {file = "pyzmq-26.2.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:95f7b01b3f275504011cf4cf21c6b885c8d627ce0867a7e83af1382ebab7b3ff"},
-    {file = "pyzmq-26.2.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:80a00370a2ef2159c310e662c7c0f2d030f437f35f478bb8b2f70abd07e26b24"},
-    {file = "pyzmq-26.2.1-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:8531ed35dfd1dd2af95f5d02afd6545e8650eedbf8c3d244a554cf47d8924459"},
-    {file = "pyzmq-26.2.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:cdb69710e462a38e6039cf17259d328f86383a06c20482cc154327968712273c"},
-    {file = "pyzmq-26.2.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:e7eeaef81530d0b74ad0d29eec9997f1c9230c2f27242b8d17e0ee67662c8f6e"},
-    {file = "pyzmq-26.2.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:361edfa350e3be1f987e592e834594422338d7174364763b7d3de5b0995b16f3"},
-    {file = "pyzmq-26.2.1-cp310-cp310-win32.whl", hash = "sha256:637536c07d2fb6a354988b2dd1d00d02eb5dd443f4bbee021ba30881af1c28aa"},
-    {file = "pyzmq-26.2.1-cp310-cp310-win_amd64.whl", hash = "sha256:45fad32448fd214fbe60030aa92f97e64a7140b624290834cc9b27b3a11f9473"},
-    {file = "pyzmq-26.2.1-cp310-cp310-win_arm64.whl", hash = "sha256:d9da0289d8201c8a29fd158aaa0dfe2f2e14a181fd45e2dc1fbf969a62c1d594"},
-    {file = "pyzmq-26.2.1-cp311-cp311-macosx_10_15_universal2.whl", hash = "sha256:c059883840e634a21c5b31d9b9a0e2b48f991b94d60a811092bc37992715146a"},
-    {file = "pyzmq-26.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:ed038a921df836d2f538e509a59cb638df3e70ca0fcd70d0bf389dfcdf784d2a"},
-    {file = "pyzmq-26.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9027a7fcf690f1a3635dc9e55e38a0d6602dbbc0548935d08d46d2e7ec91f454"},
-    {file = "pyzmq-26.2.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6d75fcb00a1537f8b0c0bb05322bc7e35966148ffc3e0362f0369e44a4a1de99"},
-    {file = "pyzmq-26.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f0019cc804ac667fb8c8eaecdb66e6d4a68acf2e155d5c7d6381a5645bd93ae4"},
-    {file = "pyzmq-26.2.1-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:f19dae58b616ac56b96f2e2290f2d18730a898a171f447f491cc059b073ca1fa"},
-    {file = "pyzmq-26.2.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:f5eeeb82feec1fc5cbafa5ee9022e87ffdb3a8c48afa035b356fcd20fc7f533f"},
-    {file = "pyzmq-26.2.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:000760e374d6f9d1a3478a42ed0c98604de68c9e94507e5452951e598ebecfba"},
-    {file = "pyzmq-26.2.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:817fcd3344d2a0b28622722b98500ae9c8bfee0f825b8450932ff19c0b15bebd"},
-    {file = "pyzmq-26.2.1-cp311-cp311-win32.whl", hash = "sha256:88812b3b257f80444a986b3596e5ea5c4d4ed4276d2b85c153a6fbc5ca457ae7"},
-    {file = "pyzmq-26.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:ef29630fde6022471d287c15c0a2484aba188adbfb978702624ba7a54ddfa6c1"},
-    {file = "pyzmq-26.2.1-cp311-cp311-win_arm64.whl", hash = "sha256:f32718ee37c07932cc336096dc7403525301fd626349b6eff8470fe0f996d8d7"},
-    {file = "pyzmq-26.2.1-cp312-cp312-macosx_10_15_universal2.whl", hash = "sha256:a6549ecb0041dafa55b5932dcbb6c68293e0bd5980b5b99f5ebb05f9a3b8a8f3"},
-    {file = "pyzmq-26.2.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:0250c94561f388db51fd0213cdccbd0b9ef50fd3c57ce1ac937bf3034d92d72e"},
-    {file = "pyzmq-26.2.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:36ee4297d9e4b34b5dc1dd7ab5d5ea2cbba8511517ef44104d2915a917a56dc8"},
-    {file = "pyzmq-26.2.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c2a9cb17fd83b7a3a3009901aca828feaf20aa2451a8a487b035455a86549c09"},
-    {file = "pyzmq-26.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:786dd8a81b969c2081b31b17b326d3a499ddd1856e06d6d79ad41011a25148da"},
-    {file = "pyzmq-26.2.1-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:2d88ba221a07fc2c5581565f1d0fe8038c15711ae79b80d9462e080a1ac30435"},
-    {file = "pyzmq-26.2.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:1c84c1297ff9f1cd2440da4d57237cb74be21fdfe7d01a10810acba04e79371a"},
-    {file = "pyzmq-26.2.1-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:46d4ebafc27081a7f73a0f151d0c38d4291656aa134344ec1f3d0199ebfbb6d4"},
-    {file = "pyzmq-26.2.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:91e2bfb8e9a29f709d51b208dd5f441dc98eb412c8fe75c24ea464734ccdb48e"},
-    {file = "pyzmq-26.2.1-cp312-cp312-win32.whl", hash = "sha256:4a98898fdce380c51cc3e38ebc9aa33ae1e078193f4dc641c047f88b8c690c9a"},
-    {file = "pyzmq-26.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:a0741edbd0adfe5f30bba6c5223b78c131b5aa4a00a223d631e5ef36e26e6d13"},
-    {file = "pyzmq-26.2.1-cp312-cp312-win_arm64.whl", hash = "sha256:e5e33b1491555843ba98d5209439500556ef55b6ab635f3a01148545498355e5"},
-    {file = "pyzmq-26.2.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:099b56ef464bc355b14381f13355542e452619abb4c1e57a534b15a106bf8e23"},
-    {file = "pyzmq-26.2.1-cp313-cp313-macosx_10_15_universal2.whl", hash = "sha256:651726f37fcbce9f8dd2a6dab0f024807929780621890a4dc0c75432636871be"},
-    {file = "pyzmq-26.2.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:57dd4d91b38fa4348e237a9388b4423b24ce9c1695bbd4ba5a3eada491e09399"},
-    {file = "pyzmq-26.2.1-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d51a7bfe01a48e1064131f3416a5439872c533d756396be2b39e3977b41430f9"},
-    {file = "pyzmq-26.2.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c7154d228502e18f30f150b7ce94f0789d6b689f75261b623f0fdc1eec642aab"},
-    {file = "pyzmq-26.2.1-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:f1f31661a80cc46aba381bed475a9135b213ba23ca7ff6797251af31510920ce"},
-    {file = "pyzmq-26.2.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:290c96f479504439b6129a94cefd67a174b68ace8a8e3f551b2239a64cfa131a"},
-    {file = "pyzmq-26.2.1-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:f2c307fbe86e18ab3c885b7e01de942145f539165c3360e2af0f094dd440acd9"},
-    {file = "pyzmq-26.2.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:b314268e716487bfb86fcd6f84ebbe3e5bec5fac75fdf42bc7d90fdb33f618ad"},
-    {file = "pyzmq-26.2.1-cp313-cp313-win32.whl", hash = "sha256:edb550616f567cd5603b53bb52a5f842c0171b78852e6fc7e392b02c2a1504bb"},
-    {file = "pyzmq-26.2.1-cp313-cp313-win_amd64.whl", hash = "sha256:100a826a029c8ef3d77a1d4c97cbd6e867057b5806a7276f2bac1179f893d3bf"},
-    {file = "pyzmq-26.2.1-cp313-cp313-win_arm64.whl", hash = "sha256:6991ee6c43e0480deb1b45d0c7c2bac124a6540cba7db4c36345e8e092da47ce"},
-    {file = "pyzmq-26.2.1-cp313-cp313t-macosx_10_13_x86_64.whl", hash = "sha256:25e720dba5b3a3bb2ad0ad5d33440babd1b03438a7a5220511d0c8fa677e102e"},
-    {file = "pyzmq-26.2.1-cp313-cp313t-macosx_10_15_universal2.whl", hash = "sha256:9ec6abfb701437142ce9544bd6a236addaf803a32628d2260eb3dbd9a60e2891"},
-    {file = "pyzmq-26.2.1-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2e1eb9d2bfdf5b4e21165b553a81b2c3bd5be06eeddcc4e08e9692156d21f1f6"},
-    {file = "pyzmq-26.2.1-cp313-cp313t-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:90dc731d8e3e91bcd456aa7407d2eba7ac6f7860e89f3766baabb521f2c1de4a"},
-    {file = "pyzmq-26.2.1-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0b6a93d684278ad865fc0b9e89fe33f6ea72d36da0e842143891278ff7fd89c3"},
-    {file = "pyzmq-26.2.1-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:c1bb37849e2294d519117dd99b613c5177934e5c04a5bb05dd573fa42026567e"},
-    {file = "pyzmq-26.2.1-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:632a09c6d8af17b678d84df442e9c3ad8e4949c109e48a72f805b22506c4afa7"},
-    {file = "pyzmq-26.2.1-cp313-cp313t-musllinux_1_1_i686.whl", hash = "sha256:fc409c18884eaf9ddde516d53af4f2db64a8bc7d81b1a0c274b8aa4e929958e8"},
-    {file = "pyzmq-26.2.1-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:17f88622b848805d3f6427ce1ad5a2aa3cf61f12a97e684dab2979802024d460"},
-    {file = "pyzmq-26.2.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3ef584f13820d2629326fe20cc04069c21c5557d84c26e277cfa6235e523b10f"},
-    {file = "pyzmq-26.2.1-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:160194d1034902937359c26ccfa4e276abffc94937e73add99d9471e9f555dd6"},
-    {file = "pyzmq-26.2.1-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:574b285150afdbf0a0424dddf7ef9a0d183988eb8d22feacb7160f7515e032cb"},
-    {file = "pyzmq-26.2.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:44dba28c34ce527cf687156c81f82bf1e51f047838d5964f6840fd87dfecf9fe"},
-    {file = "pyzmq-26.2.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:9fbdb90b85c7624c304f72ec7854659a3bd901e1c0ffb2363163779181edeb68"},
-    {file = "pyzmq-26.2.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:a7ad34a2921e8f76716dc7205c9bf46a53817e22b9eec2e8a3e08ee4f4a72468"},
-    {file = "pyzmq-26.2.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:866c12b7c90dd3a86983df7855c6f12f9407c8684db6aa3890fc8027462bda82"},
-    {file = "pyzmq-26.2.1-cp37-cp37m-win32.whl", hash = "sha256:eeb37f65350d5c5870517f02f8bbb2ac0fbec7b416c0f4875219fef305a89a45"},
-    {file = "pyzmq-26.2.1-cp37-cp37m-win_amd64.whl", hash = "sha256:4eb3197f694dfb0ee6af29ef14a35f30ae94ff67c02076eef8125e2d98963cd0"},
-    {file = "pyzmq-26.2.1-cp38-cp38-macosx_10_15_universal2.whl", hash = "sha256:36d4e7307db7c847fe37413f333027d31c11d5e6b3bacbb5022661ac635942ba"},
-    {file = "pyzmq-26.2.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1c6ae0e95d0a4b0cfe30f648a18e764352d5415279bdf34424decb33e79935b8"},
-    {file = "pyzmq-26.2.1-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:5b4fc44f5360784cc02392f14235049665caaf7c0fe0b04d313e763d3338e463"},
-    {file = "pyzmq-26.2.1-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:51431f6b2750eb9b9d2b2952d3cc9b15d0215e1b8f37b7a3239744d9b487325d"},
-    {file = "pyzmq-26.2.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bdbc78ae2065042de48a65f1421b8af6b76a0386bb487b41955818c3c1ce7bed"},
-    {file = "pyzmq-26.2.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:d14f50d61a89b0925e4d97a0beba6053eb98c426c5815d949a43544f05a0c7ec"},
-    {file = "pyzmq-26.2.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:004837cb958988c75d8042f5dac19a881f3d9b3b75b2f574055e22573745f841"},
-    {file = "pyzmq-26.2.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:0b2007f28ce1b8acebdf4812c1aab997a22e57d6a73b5f318b708ef9bcabbe95"},
-    {file = "pyzmq-26.2.1-cp38-cp38-win32.whl", hash = "sha256:269c14904da971cb5f013100d1aaedb27c0a246728c341d5d61ddd03f463f2f3"},
-    {file = "pyzmq-26.2.1-cp38-cp38-win_amd64.whl", hash = "sha256:31fff709fef3b991cfe7189d2cfe0c413a1d0e82800a182cfa0c2e3668cd450f"},
-    {file = "pyzmq-26.2.1-cp39-cp39-macosx_10_15_universal2.whl", hash = "sha256:a4bffcadfd40660f26d1b3315a6029fd4f8f5bf31a74160b151f5c577b2dc81b"},
-    {file = "pyzmq-26.2.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:e76ad4729c2f1cf74b6eb1bdd05f6aba6175999340bd51e6caee49a435a13bf5"},
-    {file = "pyzmq-26.2.1-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:8b0f5bab40a16e708e78a0c6ee2425d27e1a5d8135c7a203b4e977cee37eb4aa"},
-    {file = "pyzmq-26.2.1-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:e8e47050412f0ad3a9b2287779758073cbf10e460d9f345002d4779e43bb0136"},
-    {file = "pyzmq-26.2.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f18ce33f422d119b13c1363ed4cce245b342b2c5cbbb76753eabf6aa6f69c7d"},
-    {file = "pyzmq-26.2.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:ceb0d78b7ef106708a7e2c2914afe68efffc0051dc6a731b0dbacd8b4aee6d68"},
-    {file = "pyzmq-26.2.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:7ebdd96bd637fd426d60e86a29ec14b8c1ab64b8d972f6a020baf08a30d1cf46"},
-    {file = "pyzmq-26.2.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:03719e424150c6395b9513f53a5faadcc1ce4b92abdf68987f55900462ac7eec"},
-    {file = "pyzmq-26.2.1-cp39-cp39-win32.whl", hash = "sha256:ef5479fac31df4b304e96400fc67ff08231873ee3537544aa08c30f9d22fce38"},
-    {file = "pyzmq-26.2.1-cp39-cp39-win_amd64.whl", hash = "sha256:f92a002462154c176dac63a8f1f6582ab56eb394ef4914d65a9417f5d9fde218"},
-    {file = "pyzmq-26.2.1-cp39-cp39-win_arm64.whl", hash = "sha256:1fd4b3efc6f62199886440d5e27dd3ccbcb98dfddf330e7396f1ff421bfbb3c2"},
-    {file = "pyzmq-26.2.1-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:380816d298aed32b1a97b4973a4865ef3be402a2e760204509b52b6de79d755d"},
-    {file = "pyzmq-26.2.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:97cbb368fd0debdbeb6ba5966aa28e9a1ae3396c7386d15569a6ca4be4572b99"},
-    {file = "pyzmq-26.2.1-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:abf7b5942c6b0dafcc2823ddd9154f419147e24f8df5b41ca8ea40a6db90615c"},
-    {file = "pyzmq-26.2.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3fe6e28a8856aea808715f7a4fc11f682b9d29cac5d6262dd8fe4f98edc12d53"},
-    {file = "pyzmq-26.2.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:bd8fdee945b877aa3bffc6a5a8816deb048dab0544f9df3731ecd0e54d8c84c9"},
-    {file = "pyzmq-26.2.1-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:ee7152f32c88e0e1b5b17beb9f0e2b14454235795ef68c0c120b6d3d23d12833"},
-    {file = "pyzmq-26.2.1-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:baa1da72aecf6a490b51fba7a51f1ce298a1e0e86d0daef8265c8f8f9848eb77"},
-    {file = "pyzmq-26.2.1-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:49135bb327fca159262d8fd14aa1f4a919fe071b04ed08db4c7c37d2f0647162"},
-    {file = "pyzmq-26.2.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8bacc1a10c150d58e8a9ee2b2037a70f8d903107e0f0b6e079bf494f2d09c091"},
-    {file = "pyzmq-26.2.1-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:09dac387ce62d69bec3f06d51610ca1d660e7849eb45f68e38e7f5cf1f49cbcb"},
-    {file = "pyzmq-26.2.1-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:70b3a46ecd9296e725ccafc17d732bfc3cdab850b54bd913f843a0a54dfb2c04"},
-    {file = "pyzmq-26.2.1-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:59660e15c797a3b7a571c39f8e0b62a1f385f98ae277dfe95ca7eaf05b5a0f12"},
-    {file = "pyzmq-26.2.1-pp38-pypy38_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:0f50db737d688e96ad2a083ad2b453e22865e7e19c7f17d17df416e91ddf67eb"},
-    {file = "pyzmq-26.2.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a003200b6cd64e89b5725ff7e284a93ab24fd54bbac8b4fa46b1ed57be693c27"},
-    {file = "pyzmq-26.2.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:f9ba5def063243793dec6603ad1392f735255cbc7202a3a484c14f99ec290705"},
-    {file = "pyzmq-26.2.1-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:1238c2448c58b9c8d6565579393148414a42488a5f916b3f322742e561f6ae0d"},
-    {file = "pyzmq-26.2.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8eddb3784aed95d07065bcf94d07e8c04024fdb6b2386f08c197dfe6b3528fda"},
-    {file = "pyzmq-26.2.1-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f0f19c2097fffb1d5b07893d75c9ee693e9cbc809235cf3f2267f0ef6b015f24"},
-    {file = "pyzmq-26.2.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0995fd3530f2e89d6b69a2202e340bbada3191014352af978fa795cb7a446331"},
-    {file = "pyzmq-26.2.1-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:7c6160fe513654e65665332740f63de29ce0d165e053c0c14a161fa60dd0da01"},
-    {file = "pyzmq-26.2.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:8ec8e3aea6146b761d6c57fcf8f81fcb19f187afecc19bf1701a48db9617a217"},
-    {file = "pyzmq-26.2.1.tar.gz", hash = "sha256:17d72a74e5e9ff3829deb72897a175333d3ef5b5413948cae3cf7ebf0b02ecca"},
+    {file = "pyzmq-26.3.0-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:1586944f4736515af5c6d3a5b150c7e8ca2a2d6e46b23057320584d6f2438f4a"},
+    {file = "pyzmq-26.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:aa7efc695d1fc9f72d91bf9b6c6fe2d7e1b4193836ec530a98faf7d7a7577a58"},
+    {file = "pyzmq-26.3.0-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:bd84441e4021cec6e4dd040550386cd9c9ea1d9418ea1a8002dbb7b576026b2b"},
+    {file = "pyzmq-26.3.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9176856f36c34a8aa5c0b35ddf52a5d5cd8abeece57c2cd904cfddae3fd9acd3"},
+    {file = "pyzmq-26.3.0-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:49334faa749d55b77f084389a80654bf2e68ab5191c0235066f0140c1b670d64"},
+    {file = "pyzmq-26.3.0-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:fd30fc80fe96efb06bea21667c5793bbd65c0dc793187feb39b8f96990680b00"},
+    {file = "pyzmq-26.3.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:b2eddfbbfb473a62c3a251bb737a6d58d91907f6e1d95791431ebe556f47d916"},
+    {file = "pyzmq-26.3.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:70b3acb9ad729a53d4e751dace35404a024f188aad406013454216aba5485b4e"},
+    {file = "pyzmq-26.3.0-cp310-cp310-win32.whl", hash = "sha256:c1bd75d692cd7c6d862a98013bfdf06702783b75cffbf5dae06d718fecefe8f2"},
+    {file = "pyzmq-26.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:d7165bcda0dbf203e5ad04d79955d223d84b2263df4db92f525ba370b03a12ab"},
+    {file = "pyzmq-26.3.0-cp310-cp310-win_arm64.whl", hash = "sha256:e34a63f71d2ecffb3c643909ad2d488251afeb5ef3635602b3448e609611a7ed"},
+    {file = "pyzmq-26.3.0-cp311-cp311-macosx_10_15_universal2.whl", hash = "sha256:2833602d9d42c94b9d0d2a44d2b382d3d3a4485be018ba19dddc401a464c617a"},
+    {file = "pyzmq-26.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8270d104ec7caa0bdac246d31d48d94472033ceab5ba142881704350b28159c"},
+    {file = "pyzmq-26.3.0-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c208a977843d18d3bd185f323e4eaa912eb4869cb230947dc6edd8a27a4e558a"},
+    {file = "pyzmq-26.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eddc2be28a379c218e0d92e4a432805dcb0ca5870156a90b54c03cd9799f9f8a"},
+    {file = "pyzmq-26.3.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:c0b519fa2159c42272f8a244354a0e110d65175647e5185b04008ec00df9f079"},
+    {file = "pyzmq-26.3.0-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:1595533de3a80bf8363372c20bafa963ec4bf9f2b8f539b1d9a5017f430b84c9"},
+    {file = "pyzmq-26.3.0-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:bbef99eb8d18ba9a40f00e8836b8040cdcf0f2fa649684cf7a66339599919d21"},
+    {file = "pyzmq-26.3.0-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:979486d444ca3c469cd1c7f6a619ce48ff08b3b595d451937db543754bfacb65"},
+    {file = "pyzmq-26.3.0-cp311-cp311-win32.whl", hash = "sha256:4b127cfe10b4c56e4285b69fd4b38ea1d368099ea4273d8fb349163fce3cd598"},
+    {file = "pyzmq-26.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:cf736cc1298ef15280d9fcf7a25c09b05af016656856dc6fe5626fd8912658dd"},
+    {file = "pyzmq-26.3.0-cp311-cp311-win_arm64.whl", hash = "sha256:2dc46ec09f5d36f606ac8393303149e69d17121beee13c8dac25e2a2078e31c4"},
+    {file = "pyzmq-26.3.0-cp312-cp312-macosx_10_15_universal2.whl", hash = "sha256:c80653332c6136da7f4d4e143975e74ac0fa14f851f716d90583bc19e8945cea"},
+    {file = "pyzmq-26.3.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6e317ee1d4528a03506cb1c282cd9db73660a35b3564096de37de7350e7d87a7"},
+    {file = "pyzmq-26.3.0-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:943a22ebb3daacb45f76a9bcca9a7b74e7d94608c0c0505da30af900b998ca8d"},
+    {file = "pyzmq-26.3.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3fc9e71490d989144981ea21ef4fdfaa7b6aa84aff9632d91c736441ce2f6b00"},
+    {file = "pyzmq-26.3.0-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:e281a8071a06888575a4eb523c4deeefdcd2f5fe4a2d47e02ac8bf3a5b49f695"},
+    {file = "pyzmq-26.3.0-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:be77efd735bb1064605be8dec6e721141c1421ef0b115ef54e493a64e50e9a52"},
+    {file = "pyzmq-26.3.0-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:7a4ac2ffa34f1212dd586af90f4ba894e424f0cabb3a49cdcff944925640f6ac"},
+    {file = "pyzmq-26.3.0-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:ba698c7c252af83b6bba9775035263f0df5f807f0404019916d4b71af8161f66"},
+    {file = "pyzmq-26.3.0-cp312-cp312-win32.whl", hash = "sha256:214038aaa88e801e54c2ef0cfdb2e6df27eb05f67b477380a452b595c5ecfa37"},
+    {file = "pyzmq-26.3.0-cp312-cp312-win_amd64.whl", hash = "sha256:bad7fe0372e505442482ca3ccbc0d6f38dae81b1650f57a0aa6bbee18e7df495"},
+    {file = "pyzmq-26.3.0-cp312-cp312-win_arm64.whl", hash = "sha256:b7b578d604e79e99aa39495becea013fd043fa9f36e4b490efa951f3d847a24d"},
+    {file = "pyzmq-26.3.0-cp313-cp313-macosx_10_15_universal2.whl", hash = "sha256:fa85953df84beb7b8b73cb3ec3f5d92b62687a09a8e71525c6734e020edf56fd"},
+    {file = "pyzmq-26.3.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:209d09f0ab6ddbcebe64630d1e6ca940687e736f443c265ae15bc4bfad833597"},
+    {file = "pyzmq-26.3.0-cp313-cp313-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d35cc1086f1d4f907df85c6cceb2245cb39a04f69c3f375993363216134d76d4"},
+    {file = "pyzmq-26.3.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b380e9087078ba91e45fb18cdd0c25275ffaa045cf63c947be0ddae6186bc9d9"},
+    {file = "pyzmq-26.3.0-cp313-cp313-manylinux_2_28_x86_64.whl", hash = "sha256:6d64e74143587efe7c9522bb74d1448128fdf9897cc9b6d8b9927490922fd558"},
+    {file = "pyzmq-26.3.0-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:efba4f53ac7752eea6d8ca38a4ddac579e6e742fba78d1e99c12c95cd2acfc64"},
+    {file = "pyzmq-26.3.0-cp313-cp313-musllinux_1_1_i686.whl", hash = "sha256:9b0137a1c40da3b7989839f9b78a44de642cdd1ce20dcef341de174c8d04aa53"},
+    {file = "pyzmq-26.3.0-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:a995404bd3982c089e57b428c74edd5bfc3b0616b3dbcd6a8e270f1ee2110f36"},
+    {file = "pyzmq-26.3.0-cp313-cp313-win32.whl", hash = "sha256:240b1634b9e530ef6a277d95cbca1a6922f44dfddc5f0a3cd6c722a8de867f14"},
+    {file = "pyzmq-26.3.0-cp313-cp313-win_amd64.whl", hash = "sha256:fe67291775ea4c2883764ba467eb389c29c308c56b86c1e19e49c9e1ed0cbeca"},
+    {file = "pyzmq-26.3.0-cp313-cp313-win_arm64.whl", hash = "sha256:73ca9ae9a9011b714cf7650450cd9c8b61a135180b708904f1f0a05004543dce"},
+    {file = "pyzmq-26.3.0-cp313-cp313t-macosx_10_15_universal2.whl", hash = "sha256:fea7efbd7e49af9d7e5ed6c506dfc7de3d1a628790bd3a35fd0e3c904dc7d464"},
+    {file = "pyzmq-26.3.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c4430c7cba23bb0e2ee203eee7851c1654167d956fc6d4b3a87909ccaf3c5825"},
+    {file = "pyzmq-26.3.0-cp313-cp313t-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:016d89bee8c7d566fad75516b4e53ec7c81018c062d4c51cd061badf9539be52"},
+    {file = "pyzmq-26.3.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:04bfe59852d76d56736bfd10ac1d49d421ab8ed11030b4a0332900691507f557"},
+    {file = "pyzmq-26.3.0-cp313-cp313t-manylinux_2_28_x86_64.whl", hash = "sha256:1fe05bd0d633a0f672bb28cb8b4743358d196792e1caf04973b7898a0d70b046"},
+    {file = "pyzmq-26.3.0-cp313-cp313t-musllinux_1_1_aarch64.whl", hash = "sha256:2aa1a9f236d5b835fb8642f27de95f9edcfd276c4bc1b6ffc84f27c6fb2e2981"},
+    {file = "pyzmq-26.3.0-cp313-cp313t-musllinux_1_1_i686.whl", hash = "sha256:21399b31753bf321043ea60c360ed5052cc7be20739785b1dff1820f819e35b3"},
+    {file = "pyzmq-26.3.0-cp313-cp313t-musllinux_1_1_x86_64.whl", hash = "sha256:d015efcd96aca8882057e7e6f06224f79eecd22cad193d3e6a0a91ec67590d1f"},
+    {file = "pyzmq-26.3.0-cp38-cp38-macosx_10_15_universal2.whl", hash = "sha256:18183cc3851b995fdc7e5f03d03b8a4e1b12b0f79dff1ec1da75069af6357a05"},
+    {file = "pyzmq-26.3.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:da87e977f92d930a3683e10ba2b38bcc59adfc25896827e0b9d78b208b7757a6"},
+    {file = "pyzmq-26.3.0-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:cf6db401f4957afbf372a4730c6d5b2a234393af723983cbf4bcd13d54c71e1a"},
+    {file = "pyzmq-26.3.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:03caa2ffd64252122139d50ec92987f89616b9b92c9ba72920b40e92709d5e26"},
+    {file = "pyzmq-26.3.0-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:fbf206e5329e20937fa19bd41cf3af06d5967f8f7e86b59d783b26b40ced755c"},
+    {file = "pyzmq-26.3.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:6fb539a6382a048308b409d8c66d79bf636eda1b24f70c78f2a1fd16e92b037b"},
+    {file = "pyzmq-26.3.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:7897b8c8bbbb2bd8cad887bffcb07aede71ef1e45383bd4d6ac049bf0af312a4"},
+    {file = "pyzmq-26.3.0-cp38-cp38-win32.whl", hash = "sha256:91dead2daca698ae52ce70ee2adbb94ddd9b5f96877565fd40aa4efd18ecc6a3"},
+    {file = "pyzmq-26.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:8c088e009a6d6b9f563336adb906e3a8d3fd64db129acc8d8fd0e9fe22b2dac8"},
+    {file = "pyzmq-26.3.0-cp39-cp39-macosx_10_15_universal2.whl", hash = "sha256:2eaed0d911fb3280981d5495978152fab6afd9fe217fd16f411523665089cef1"},
+    {file = "pyzmq-26.3.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:7998b60ef1c105846fb3bfca494769fde3bba6160902e7cd27a8df8257890ee9"},
+    {file = "pyzmq-26.3.0-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:96c0006a8d1d00e46cb44c8e8d7316d4a232f3d8f2ed43179d4578dbcb0829b6"},
+    {file = "pyzmq-26.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5e17cc198dc50a25a0f245e6b1e56f692df2acec3ccae82d1f60c34bfb72bbec"},
+    {file = "pyzmq-26.3.0-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:92a30840f4f2a31f7049d0a7de5fc69dd03b19bd5d8e7fed8d0bde49ce49b589"},
+    {file = "pyzmq-26.3.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:f52eba83272a26b444f4b8fc79f2e2c83f91d706d693836c9f7ccb16e6713c31"},
+    {file = "pyzmq-26.3.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:952085a09ff32115794629ba47f8940896d7842afdef1283332109d38222479d"},
+    {file = "pyzmq-26.3.0-cp39-cp39-win32.whl", hash = "sha256:0240289e33e3fbae44a5db73e54e955399179332a6b1d47c764a4983ec1524c3"},
+    {file = "pyzmq-26.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:b2db7c82f08b8ce44c0b9d1153ce63907491972a7581e8b6adea71817f119df8"},
+    {file = "pyzmq-26.3.0-cp39-cp39-win_arm64.whl", hash = "sha256:2d3459b6311463c96abcb97808ee0a1abb0d932833edb6aa81c30d622fd4a12d"},
+    {file = "pyzmq-26.3.0-pp310-pypy310_pp73-macosx_10_15_x86_64.whl", hash = "sha256:ad03f4252d9041b0635c37528dfa3f44b39f46024ae28c8567f7423676ee409b"},
+    {file = "pyzmq-26.3.0-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0f3dfb68cf7bf4cfdf34283a75848e077c5defa4907506327282afe92780084d"},
+    {file = "pyzmq-26.3.0-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:356ec0e39c5a9cda872b65aca1fd8a5d296ffdadf8e2442b70ff32e73ef597b1"},
+    {file = "pyzmq-26.3.0-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:749d671b0eec8e738bbf0b361168369d8c682b94fcd458c20741dc4d69ef5278"},
+    {file = "pyzmq-26.3.0-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:f950f17ae608e0786298340163cac25a4c5543ef25362dd5ddb6dcb10b547be9"},
+    {file = "pyzmq-26.3.0-pp311-pypy311_pp73-macosx_10_15_x86_64.whl", hash = "sha256:b4fc9903a73c25be9d5fe45c87faababcf3879445efa16140146b08fccfac017"},
+    {file = "pyzmq-26.3.0-pp311-pypy311_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c15b69af22030960ac63567e98ad8221cddf5d720d9cf03d85021dfd452324ef"},
+    {file = "pyzmq-26.3.0-pp311-pypy311_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2cf9ab0dff4dbaa2e893eb608373c97eb908e53b7d9793ad00ccbd082c0ee12f"},
+    {file = "pyzmq-26.3.0-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ec332675f6a138db57aad93ae6387953763f85419bdbd18e914cb279ee1c451"},
+    {file = "pyzmq-26.3.0-pp311-pypy311_pp73-win_amd64.whl", hash = "sha256:eb96568a22fe070590942cd4780950e2172e00fb033a8b76e47692583b1bd97c"},
+    {file = "pyzmq-26.3.0-pp38-pypy38_pp73-macosx_10_15_x86_64.whl", hash = "sha256:009a38241c76184cb004c869e82a99f0aee32eda412c1eb44df5820324a01d25"},
+    {file = "pyzmq-26.3.0-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:4c22a12713707467abedc6d75529dd365180c4c2a1511268972c6e1d472bd63e"},
+    {file = "pyzmq-26.3.0-pp38-pypy38_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:1614fcd116275d24f2346ffca4047a741c546ad9d561cbf7813f11226ca4ed2c"},
+    {file = "pyzmq-26.3.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4e2cafe7e9c7fed690e8ecf65af119f9c482923b5075a78f6f7629c63e1b4b1d"},
+    {file = "pyzmq-26.3.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:14e0b81753424bd374075df6cc30b87f2c99e5f022501d97eff66544ca578941"},
+    {file = "pyzmq-26.3.0-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:21c6ddb98557a77cfe3366af0c5600fb222a1b2de5f90d9cd052b324e0c295e8"},
+    {file = "pyzmq-26.3.0-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fc81d5d60c9d40e692de14b8d884d43cf67562402b931681f0ccb3ce6b19875"},
+    {file = "pyzmq-26.3.0-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:52b064fafef772d0f5dbf52d4c39f092be7bc62d9a602fe6e82082e001326de3"},
+    {file = "pyzmq-26.3.0-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b72206eb041f780451c61e1e89dbc3705f3d66aaaa14ee320d4f55864b13358a"},
+    {file = "pyzmq-26.3.0-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:8ab78dc21c7b1e13053086bcf0b4246440b43b5409904b73bfd1156654ece8a1"},
+    {file = "pyzmq-26.3.0-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:0b42403ad7d1194dca9574cd3c56691c345f4601fa2d0a33434f35142baec7ac"},
+    {file = "pyzmq-26.3.0.tar.gz", hash = "sha256:f1cd68b8236faab78138a8fc703f7ca0ad431b17a3fcac696358600d4e6243b3"},
 ]
 
 [package.dependencies]
@@ -5906,21 +5883,21 @@ files = [
 
 [[package]]
 name = "rtree"
-version = "1.3.0"
+version = "1.4.0"
 description = "R-Tree spatial index for Python GIS"
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 files = [
-    {file = "Rtree-1.3.0-py3-none-macosx_10_9_x86_64.whl", hash = "sha256:80879d9db282a2273ca3a0d896c84583940e9777477727a277624ebfd424c517"},
-    {file = "Rtree-1.3.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:4328e9e421797c347e6eb08efbbade962fe3664ebd60c1dffe82c40911b1e125"},
-    {file = "Rtree-1.3.0-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:037130d3ce1fc029de81941ec416ba5546f66228380ba19bb41f2ea1294e8423"},
-    {file = "Rtree-1.3.0-py3-none-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:864a05d0c3b7ce6c5e34378b7ab630057603b79179368bc50624258bdf2ff631"},
-    {file = "Rtree-1.3.0-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ec2ed6d1635753dab966e68f592a9c4896f3f4ec6ad2b09b776d592eacd883a9"},
-    {file = "Rtree-1.3.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:b4485fb3e5c5e85b94a95f0a930a3848e040d2699cfb012940ba5b0130f1e09a"},
-    {file = "Rtree-1.3.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:7e2e9211f4fb404c06a08fd2cbebb03234214f73c51913bb371c3d9954e99cc9"},
-    {file = "Rtree-1.3.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:c021f4772b25cc24915da8073e553ded6fa8d0b317caa4202255ed26b2344c1c"},
-    {file = "Rtree-1.3.0-py3-none-win_amd64.whl", hash = "sha256:97f835801d24c10bbf02381abe5e327345c8296ec711dde7658792376abafc66"},
-    {file = "rtree-1.3.0.tar.gz", hash = "sha256:b36e9dd2dc60ffe3d02e367242d2c26f7281b00e1aaf0c39590442edaaadd916"},
+    {file = "rtree-1.4.0-py3-none-macosx_10_9_x86_64.whl", hash = "sha256:4d1bebc418101480aabf41767e772dd2155d3b27b1376cccbd93e4509485e091"},
+    {file = "rtree-1.4.0-py3-none-macosx_11_0_arm64.whl", hash = "sha256:997f8c38d5dffa3949ea8adb4c8b291ea5cd4ef5ee69455d642dd171baf9991d"},
+    {file = "rtree-1.4.0-py3-none-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:0133d9c54ab3ffe874ba6d411dbe0254765c5e68d92da5b91362c370f16fd997"},
+    {file = "rtree-1.4.0-py3-none-manylinux2014_i686.manylinux_2_17_i686.whl", hash = "sha256:d3b7bf1fe6463139377995ebe22a01a7005d134707f43672a3c09305e12f5f43"},
+    {file = "rtree-1.4.0-py3-none-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:27e4a6d617d63dcb82fcd4c2856134b8a3741bd1af3b1a0d98e886054f394da5"},
+    {file = "rtree-1.4.0-py3-none-musllinux_1_2_aarch64.whl", hash = "sha256:5258e826064eab82439760201e9421ce6d4340789d6d080c1b49367ddd03f61f"},
+    {file = "rtree-1.4.0-py3-none-musllinux_1_2_i686.whl", hash = "sha256:20d5b3f9cf8bbbcc9fec42ab837c603c5dd86103ef29134300c8da2495c1248b"},
+    {file = "rtree-1.4.0-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:a67bee1233370a4c72c0969a96d2a1df1ba404ddd9f146849c53ab420eab361b"},
+    {file = "rtree-1.4.0-py3-none-win_amd64.whl", hash = "sha256:ba83efc7b7563905b1bfdfc14490c4bfb59e92e5e6156bdeb6ec5df5117252f4"},
+    {file = "rtree-1.4.0.tar.gz", hash = "sha256:9d97c7c5dcf25f6c0599c76d9933368c6a8d7238f2c1d00e76f1a69369ca82a0"},
 ]
 
 [[package]]
@@ -6241,13 +6218,13 @@ train = ["accelerate (>=0.20.3)", "datasets"]
 
 [[package]]
 name = "setuptools"
-version = "75.8.2"
+version = "76.0.0"
 description = "Easily download, build, install, upgrade, and uninstall Python packages"
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "setuptools-75.8.2-py3-none-any.whl", hash = "sha256:558e47c15f1811c1fa7adbd0096669bf76c1d3f433f58324df69f3f5ecac4e8f"},
-    {file = "setuptools-75.8.2.tar.gz", hash = "sha256:4880473a969e5f23f2a2be3646b2dfd84af9028716d398e46192f84bc36900d2"},
+    {file = "setuptools-76.0.0-py3-none-any.whl", hash = "sha256:199466a166ff664970d0ee145839f5582cb9bca7a0a3a2e795b6a9cb2308e9c6"},
+    {file = "setuptools-76.0.0.tar.gz", hash = "sha256:43b4ee60e10b0d0ee98ad11918e114c70701bc6051662a9a675a0496c1a158f4"},
 ]
 
 [package.extras]
@@ -6491,13 +6468,13 @@ files = [
 
 [[package]]
 name = "threadpoolctl"
-version = "3.5.0"
+version = "3.6.0"
 description = "threadpoolctl"
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 files = [
-    {file = "threadpoolctl-3.5.0-py3-none-any.whl", hash = "sha256:56c1e26c150397e58c4926da8eeee87533b1e32bef131bd4bf6a2f45f3185467"},
-    {file = "threadpoolctl-3.5.0.tar.gz", hash = "sha256:082433502dd922bf738de0d8bcc4fdcbf0979ff44c42bd40f5af8a282f6fa107"},
+    {file = "threadpoolctl-3.6.0-py3-none-any.whl", hash = "sha256:43a0b8fd5a2928500110039e43a5eed8480b918967083ea48dc3ab9f13c4a7fb"},
+    {file = "threadpoolctl-3.6.0.tar.gz", hash = "sha256:8ab8b4aa3491d812b623328249fab5302a68d2d71745c8a4c719a2fcaba9f44e"},
 ]
 
 [[package]]
@@ -6670,26 +6647,26 @@ testing = ["black (==22.3)", "datasets", "numpy", "pytest", "requests", "ruff"]
 
 [[package]]
 name = "tokenizers"
-version = "0.21.0"
+version = "0.21.1"
 description = ""
 optional = false
-python-versions = ">=3.7"
+python-versions = ">=3.9"
 files = [
-    {file = "tokenizers-0.21.0-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:3c4c93eae637e7d2aaae3d376f06085164e1660f89304c0ab2b1d08a406636b2"},
-    {file = "tokenizers-0.21.0-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:f53ea537c925422a2e0e92a24cce96f6bc5046bbef24a1652a5edc8ba975f62e"},
-    {file = "tokenizers-0.21.0-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6b177fb54c4702ef611de0c069d9169f0004233890e0c4c5bd5508ae05abf193"},
-    {file = "tokenizers-0.21.0-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:6b43779a269f4629bebb114e19c3fca0223296ae9fea8bb9a7a6c6fb0657ff8e"},
-    {file = "tokenizers-0.21.0-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9aeb255802be90acfd363626753fda0064a8df06031012fe7d52fd9a905eb00e"},
-    {file = "tokenizers-0.21.0-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d8b09dbeb7a8d73ee204a70f94fc06ea0f17dcf0844f16102b9f414f0b7463ba"},
-    {file = "tokenizers-0.21.0-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:400832c0904f77ce87c40f1a8a27493071282f785724ae62144324f171377273"},
-    {file = "tokenizers-0.21.0-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e84ca973b3a96894d1707e189c14a774b701596d579ffc7e69debfc036a61a04"},
-    {file = "tokenizers-0.21.0-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:eb7202d231b273c34ec67767378cd04c767e967fda12d4a9e36208a34e2f137e"},
-    {file = "tokenizers-0.21.0-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:089d56db6782a73a27fd8abf3ba21779f5b85d4a9f35e3b493c7bbcbbf0d539b"},
-    {file = "tokenizers-0.21.0-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:c87ca3dc48b9b1222d984b6b7490355a6fdb411a2d810f6f05977258400ddb74"},
-    {file = "tokenizers-0.21.0-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:4145505a973116f91bc3ac45988a92e618a6f83eb458f49ea0790df94ee243ff"},
-    {file = "tokenizers-0.21.0-cp39-abi3-win32.whl", hash = "sha256:eb1702c2f27d25d9dd5b389cc1f2f51813e99f8ca30d9e25348db6585a97e24a"},
-    {file = "tokenizers-0.21.0-cp39-abi3-win_amd64.whl", hash = "sha256:87841da5a25a3a5f70c102de371db120f41873b854ba65e52bccd57df5a3780c"},
-    {file = "tokenizers-0.21.0.tar.gz", hash = "sha256:ee0894bf311b75b0c03079f33859ae4b2334d675d4e93f5a4132e1eae2834fe4"},
+    {file = "tokenizers-0.21.1-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:e78e413e9e668ad790a29456e677d9d3aa50a9ad311a40905d6861ba7692cf41"},
+    {file = "tokenizers-0.21.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:cd51cd0a91ecc801633829fcd1fda9cf8682ed3477c6243b9a095539de4aecf3"},
+    {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:28da6b72d4fb14ee200a1bd386ff74ade8992d7f725f2bde2c495a9a98cf4d9f"},
+    {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:34d8cfde551c9916cb92014e040806122295a6800914bab5865deb85623931cf"},
+    {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:aaa852d23e125b73d283c98f007e06d4595732104b65402f46e8ef24b588d9f8"},
+    {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a21a15d5c8e603331b8a59548bbe113564136dc0f5ad8306dd5033459a226da0"},
+    {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2fdbd4c067c60a0ac7eca14b6bd18a5bebace54eb757c706b47ea93204f7a37c"},
+    {file = "tokenizers-0.21.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2dd9a0061e403546f7377df940e866c3e678d7d4e9643d0461ea442b4f89e61a"},
+    {file = "tokenizers-0.21.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:db9484aeb2e200c43b915a1a0150ea885e35f357a5a8fabf7373af333dcc8dbf"},
+    {file = "tokenizers-0.21.1-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:ed248ab5279e601a30a4d67bdb897ecbe955a50f1e7bb62bd99f07dd11c2f5b6"},
+    {file = "tokenizers-0.21.1-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:9ac78b12e541d4ce67b4dfd970e44c060a2147b9b2a21f509566d556a509c67d"},
+    {file = "tokenizers-0.21.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:e5a69c1a4496b81a5ee5d2c1f3f7fbdf95e90a0196101b0ee89ed9956b8a168f"},
+    {file = "tokenizers-0.21.1-cp39-abi3-win32.whl", hash = "sha256:1039a3a5734944e09de1d48761ade94e00d0fa760c0e0551151d4dd851ba63e3"},
+    {file = "tokenizers-0.21.1-cp39-abi3-win_amd64.whl", hash = "sha256:0f0dcbcc9f6e13e675a66d7a5f2f225a736745ce484c1a4e07476a89ccdad382"},
+    {file = "tokenizers-0.21.1.tar.gz", hash = "sha256:a1bb04dc5b448985f86ecd4b05407f5a8d97cb2c0532199b2a302a604a0165ab"},
 ]
 
 [package.dependencies]
@@ -7223,13 +7200,13 @@ typing-extensions = ">=3.7.4.3"
 
 [[package]]
 name = "types-openpyxl"
-version = "3.1.5.20241225"
+version = "3.1.5.20250306"
 description = "Typing stubs for openpyxl"
 optional = false
-python-versions = ">=3.8"
+python-versions = ">=3.9"
 files = [
-    {file = "types_openpyxl-3.1.5.20241225-py3-none-any.whl", hash = "sha256:903d92f58f42135b0614d609868c619aee12e1c7b65ccf8472dfd2706bcc6f47"},
-    {file = "types_openpyxl-3.1.5.20241225.tar.gz", hash = "sha256:3c076f4c6f114e1859b6857ffd486e96c938c0434451c60dc54c2bcb62750d78"},
+    {file = "types_openpyxl-3.1.5.20250306-py3-none-any.whl", hash = "sha256:f7733dac1dcb07c89ff5ffde8452ee8d272be638defed855f4c48b2990ce5aa7"},
+    {file = "types_openpyxl-3.1.5.20250306.tar.gz", hash = "sha256:aa7ad2425e8020ff46a31633becfe1f3c64114498d964c536199f654b464e6bc"},
 ]
 
 [[package]]
@@ -7245,13 +7222,13 @@ files = [
 
 [[package]]
 name = "types-requests"
-version = "2.32.0.20250301"
+version = "2.32.0.20250306"
 description = "Typing stubs for requests"
 optional = false
 python-versions = ">=3.9"
 files = [
-    {file = "types_requests-2.32.0.20250301-py3-none-any.whl", hash = "sha256:0003e0124e2cbefefb88222ff822b48616af40c74df83350f599a650c8de483b"},
-    {file = "types_requests-2.32.0.20250301.tar.gz", hash = "sha256:3d909dc4eaab159c0d964ebe8bfa326a7afb4578d8706408d417e17d61b0c500"},
+    {file = "types_requests-2.32.0.20250306-py3-none-any.whl", hash = "sha256:25f2cbb5c8710b2022f8bbee7b2b66f319ef14aeea2f35d80f18c9dbf3b60a0b"},
+    {file = "types_requests-2.32.0.20250306.tar.gz", hash = "sha256:0962352694ec5b2f95fda877ee60a159abdf84a0fc6fdace599f20acb41a03d1"},
 ]
 
 [package.dependencies]
@@ -7399,13 +7376,13 @@ zstd = ["zstandard (>=0.18.0)"]
 
 [[package]]
 name = "virtualenv"
-version = "20.29.2"
+version = "20.29.3"
 description = "Virtual Python Environment builder"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "virtualenv-20.29.2-py3-none-any.whl", hash = "sha256:febddfc3d1ea571bdb1dc0f98d7b45d24def7428214d4fb73cc486c9568cce6a"},
-    {file = "virtualenv-20.29.2.tar.gz", hash = "sha256:fdaabebf6d03b5ba83ae0a02cfe96f48a716f4fae556461d180825866f75b728"},
+    {file = "virtualenv-20.29.3-py3-none-any.whl", hash = "sha256:3e3d00f5807e83b234dfb6122bf37cfadf4be216c53a49ac059d02414f819170"},
+    {file = "virtualenv-20.29.3.tar.gz", hash = "sha256:95e39403fcf3940ac45bc717597dba16110b74506131845d9b687d5e73d947ac"},
 ]
 
 [package.dependencies]
@@ -7861,4 +7838,4 @@ vlm = ["accelerate", "transformers", "transformers"]
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.9"
-content-hash = "c37ae7d39cb2af7031248c2f0308c91160facafd948e982899245e5d8369bbbb"
+content-hash = "6917ebe61625f5b719df46c3f1597c61241b2a3b81bae640d9167d20d0182dd8"

pyproject.toml

@@ -46,9 +46,9 @@ packages = [{ include = "docling" }]
 ######################
 python = "^3.9"
 pydantic = "^2.0.0"
-docling-core = {extras = ["chunking"], version = "^2.22.0"}
+docling-core = {extras = ["chunking"], version = "^2.23.0"}
 docling-ibm-models = "^3.4.0"
-docling-parse = "^3.3.0"
+docling-parse = "^4.0.0"
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
 pydantic-settings = "^2.3.0"

tests/data/groundtruth/docling_v2/2203.01017v2.md

@@ -140,13 +140,13 @@ tention encoding is then multiplied to the encoded image to produce a feature fo
 
 The output features for each table cell are then fed into the feed-forward network (FFN). The FFN consists of a Multi-Layer Perceptron (3 layers with ReLU activation function) that predicts the normalized coordinates for the bounding box of each table cell. Finally, the predicted bounding boxes are classified based on whether they are empty or not using a linear layer.
 
-Loss Functions. We formulate a multi-task loss Eq. 2 to train our network. The Cross-Entropy loss (denoted as l$_{s}$ ) is used to train the Structure Decoder which predicts the structure tokens. As for the Cell BBox Decoder it is trained with a combination of losses denoted as l$_{box}$ . l$_{box}$ consists of the generally used l$_{1}$ loss for object detection and the IoU loss ( l$_{iou}$ ) to be scale invariant as explained in [25]. In comparison to DETR, we do not use the Hungarian algorithm [15] to match the predicted bounding boxes with the ground-truth boxes, as we have already achieved a one-toone match through two steps: 1) Our token input sequence is naturally ordered, therefore the hidden states of the table data cells are also in order when they are provided as input to the Cell BBox Decoder , and 2) Our bounding boxes generation mechanism (see Sec. 3) ensures a one-to-one mapping between the cell content and its bounding box for all post-processed datasets.
+Loss Functions. We formulate a multi-task loss Eq. 2 to train our network. The Cross-Entropy loss (denoted as l$\_{s}$ ) is used to train the Structure Decoder which predicts the structure tokens. As for the Cell BBox Decoder it is trained with a combination of losses denoted as l$\_{box}$ . l$\_{box}$ consists of the generally used l$\_{1}$ loss for object detection and the IoU loss ( l$\_{iou}$ ) to be scale invariant as explained in [25]. In comparison to DETR, we do not use the Hungarian algorithm [15] to match the predicted bounding boxes with the ground-truth boxes, as we have already achieved a one-toone match through two steps: 1) Our token input sequence is naturally ordered, therefore the hidden states of the table data cells are also in order when they are provided as input to the Cell BBox Decoder , and 2) Our bounding boxes generation mechanism (see Sec. 3) ensures a one-to-one mapping between the cell content and its bounding box for all post-processed datasets.
 
 The loss used to train the TableFormer can be defined as following:
 
 <!-- formula-not-decoded -->
 
-where λ ∈ [0, 1], and λ$_{iou}$, λ$_{l}$$\_{1}$ ∈$\_{R}$ are hyper-parameters.
+where λ ∈ [0, 1], and λ$\_{iou}$, λ$\_{l}$$\_{1}$ ∈$\_{R}$ are hyper-parameters.
 
 ## 5. Experimental Results
 
@@ -176,7 +176,7 @@ The Tree-Edit-Distance-Based Similarity (TEDS) metric was introduced in [37]. It
 
 <!-- formula-not-decoded -->
 
-where T$_{a}$ and T$_{b}$ represent tables in tree structure HTML format. EditDist denotes the tree-edit distance, and | T | represents the number of nodes in T .
+where T$\_{a}$ and T$\_{b}$ represent tables in tree structure HTML format. EditDist denotes the tree-edit distance, and | T | represents the number of nodes in T .
 
 ## 5.4. Quantitative Analysis
 
@@ -372,7 +372,7 @@ Here is a step-by-step description of the prediction postprocessing:
 
 <!-- formula-not-decoded -->
 
-where c is one of { left, centroid, right } and x$_{c}$ is the xcoordinate for the corresponding point.
+where c is one of { left, centroid, right } and x$\_{c}$ is the xcoordinate for the corresponding point.
 
 - 5. Use the alignment computed in step 4, to compute the median x -coordinate for all table columns and the me-
 - 6. Snap all cells with bad IOU to their corresponding median x -coordinates and cell sizes.

tests/data/groundtruth/docling_v2/csv-comma-in-cell.csv.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "csv-comma-in-cell",
   "origin": {
     "mimetype": "text/csv",

tests/data/groundtruth/docling_v2/csv-comma.csv.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "csv-comma",
   "origin": {
     "mimetype": "text/csv",

tests/data/groundtruth/docling_v2/csv-inconsistent-header.csv.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "csv-inconsistent-header",
   "origin": {
     "mimetype": "text/csv",

tests/data/groundtruth/docling_v2/csv-pipe.csv.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "csv-pipe",
   "origin": {
     "mimetype": "text/csv",

tests/data/groundtruth/docling_v2/csv-semicolon.csv.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "csv-semicolon",
   "origin": {
     "mimetype": "text/csv",

tests/data/groundtruth/docling_v2/csv-tab.csv.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "csv-tab",
   "origin": {
     "mimetype": "text/csv",

tests/data/groundtruth/docling_v2/csv-too-few-columns.csv.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "csv-too-few-columns",
   "origin": {
     "mimetype": "text/csv",

tests/data/groundtruth/docling_v2/csv-too-many-columns.csv.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "csv-too-many-columns",
   "origin": {
     "mimetype": "text/csv",

tests/data/groundtruth/docling_v2/equations.docx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.2.0",
+  "version": "1.3.0",
   "name": "equations",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

tests/data/groundtruth/docling_v2/example_01.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "example_01",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_01.html.md

@@ -2,7 +2,7 @@
 
 This is the first paragraph of the introduction.
 
-## Background
+### Background
 
 Some background information here.
 

tests/data/groundtruth/docling_v2/example_02.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "example_02",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_02.html.md

@@ -2,7 +2,7 @@
 
 This is the first paragraph of the introduction.
 
-## Background
+### Background
 
 Some background information here.
 

tests/data/groundtruth/docling_v2/example_03.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "example_03",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_03.html.md

@@ -1,10 +1,10 @@
 # Example Document
 
-## Introduction
+### Introduction
 
 This is the first paragraph of the introduction.
 
-## Background
+### Background
 
 Some background information here.
 
@@ -18,7 +18,7 @@ Some background information here.
     2. Nested ordered item 2
 3. Second item in ordered list
 
-## Data Table
+### Data Table
 
 | Header 1     | Header 2     | Header 3     |
 |--------------|--------------|--------------|

tests/data/groundtruth/docling_v2/example_04.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "example_04",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_04.html.md

@@ -1,7 +1,7 @@
 # Data Table with Rowspan and Colspan
 
-| Header 1                   | Header 2 & 3 (colspan)     | Header 2 & 3 (colspan)     |
+| Header 1                   | Header 2 & 3 (colspan)     | Header 2 & 3 (colspan)     |
 |----------------------------|----------------------------|----------------------------|
-| Row 1 & 2, Col 1 (rowspan) | Row 1, Col 2               | Row 1, Col 3               |
-| Row 1 & 2, Col 1 (rowspan) | Row 2, Col 2 & 3 (colspan) | Row 2, Col 2 & 3 (colspan) |
+| Row 1 & 2, Col 1 (rowspan) | Row 1, Col 2               | Row 1, Col 3               |
+| Row 1 & 2, Col 1 (rowspan) | Row 2, Col 2 & 3 (colspan) | Row 2, Col 2 & 3 (colspan) |
 | Row 3, Col 1               | Row 3, Col 2               | Row 3, Col 3               |

tests/data/groundtruth/docling_v2/example_05.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "example_05",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_05.html.md

@@ -1,7 +1,7 @@
 # Omitted html and body tags
 
-| Header 1                   | Header 2 & 3 (colspan)     | Header 2 & 3 (colspan)     |
+| Header 1                   | Header 2 & 3 (colspan)     | Header 2 & 3 (colspan)     |
 |----------------------------|----------------------------|----------------------------|
-| Row 1 & 2, Col 1 (rowspan) | Row 1, Col 2               | Row 1, Col 3               |
-| Row 1 & 2, Col 1 (rowspan) | Row 2, Col 2 & 3 (colspan) | Row 2, Col 2 & 3 (colspan) |
+| Row 1 & 2, Col 1 (rowspan) | Row 1, Col 2               | Row 1, Col 3               |
+| Row 1 & 2, Col 1 (rowspan) | Row 2, Col 2 & 3 (colspan) | Row 2, Col 2 & 3 (colspan) |
 | Row 3, Col 1               | Row 3, Col 2               | Row 3, Col 3               |

tests/data/groundtruth/docling_v2/example_06.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "example_06",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/example_07.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.2.0",
+  "version": "1.3.0",
   "name": "example_07",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/ipa20180000016.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "ipa20180000016.xml",
   "origin": {
     "mimetype": "application/xml",

tests/data/groundtruth/docling_v2/ipa20180000016.md

@@ -1,20 +1,20 @@
 # LIGHT EMITTING DEVICE AND PLANT CULTIVATION METHOD
 
-## ABSTRACT
+### ABSTRACT
 
 Provided is a light emitting device that includes a light emitting element having a light emission peak wavelength ranging from 380 nm to 490 nm, and a fluorescent material excited by light from the light emitting element and emitting light having at a light emission peak wavelength ranging from 580 nm or more to less than 680 nm. The light emitting device emits light having a ratio R/B of a photon flux density R to a photon flux density B ranging from 2.0 to 4.0 and a ratio R/FR of the photon flux density R to a photon flux density FR ranging from 0.7 to 13.0, the photon flux density R being in a wavelength range of 620 nm or more and less than 700 nm, the photon flux density B being in a wavelength range of 380 nm or more and 490 nm or less, and the photon flux density FR being in a wavelength range of 700 nm or more and 780 nm or less.
 
-## CROSS-REFERENCE TO RELATED APPLICATION
+### CROSS-REFERENCE TO RELATED APPLICATION
 
 The application claims benefit of Japanese Patent Application No. 2016-128835 filed on Jun. 29, 2016, the entire disclosure of which is hereby incorporated by reference in its entirety.
 
-## BACKGROUND
+### BACKGROUND
 
-## Technical Field
+### Technical Field
 
 The present disclosure relates to a light emitting device and a plant cultivation method.
 
-## Description of Related Art
+### Description of Related Art
 
 With environmental changes due to climate change and other artificial disruptions, plant factories are expected to increase production efficiency of vegetables and be capable of adjusting production in order to make it possible to stably supply vegetables. Plant factories that are capable of artificial management can stably supply clean and safe vegetables to markets, and therefore are expected to be the next-generation industries.
 
@@ -26,7 +26,7 @@ In plant factories, the light source used in place of sunlight affect a growth p
 
 For example, Japanese Unexamined Patent Publication No. 2009-125007 discloses a plant growth method. In this method, the plants is irradiated with light emitted from a first LED light emitting element and/or a second LED light emitting element at predetermined timings using a lighting apparatus including the first LED light emitting element emitting light having a wavelength region of 625 to 690 nm and the second LED light emitting element emitting light having a wavelength region of 420 to 490 nm in order to emit lights having sufficient intensities and different wavelengths from each other.
 
-## SUMMARY
+### SUMMARY
 
 However, even though plants are merely irradiated with lights having different wavelengths as in the plant growth method disclosed in Japanese Unexamined Patent Publication No. 2009-125007, the effect of promoting plant growth is not sufficient. Further improvement is required in promotion of plant growth.
 
@@ -40,7 +40,7 @@ A second embodiment of the present disclosure is a plant cultivation method incl
 
 According to embodiments of the present disclosure, a light emitting device capable of promoting growth of plants and a plant cultivation method can be provided.
 
-## BRIEF DESCRIPTION OF THE DRAWINGS
+### BRIEF DESCRIPTION OF THE DRAWINGS
 
 FIG. 1 is a schematic cross sectional view of a light emitting device according to an embodiment of the present disclosure.
 
@@ -50,11 +50,11 @@ FIG. 3 is a graph showing fresh weight (edible part) at the harvest time of each
 
 FIG. 4 is a graph showing nitrate nitrogen content in each plant grown by irradiating the plant with light from exemplary light emitting devices according to embodiments of the present disclosure and a comparative light emitting device.
 
-## DETAILED DESCRIPTION
+### DETAILED DESCRIPTION
 
 A light emitting device and a plant cultivation method according to the present invention will be described below based on an embodiment. However, the embodiment described below only exemplifies the technical concept of the present invention, and the present invention is not limited to the light emitting device and plant cultivation method described below. In the present specification, the relationship between the color name and the chromaticity coordinate, the relationship between the wavelength range of light and the color name of monochromatic light follows JIS Z8110.
 
-### Light Emitting Device
+#### Light Emitting Device
 
 An embodiment of the present disclosure is a light emitting device including a light emitting element having a light emission peak wavelength in a range of 380 nm or more and 490 nm or less (hereinafter sometimes referred to as a “region of from near ultraviolet to blue color”), and a first fluorescent material emitting light having at least one light emission peak wavelength in a range of 580 nm or more and less than 680 nm by being excited by light from the light emitting element. The light emitting device emits light having a ratio R/B of a photon flux density R to a photon flux density B within a range of 2.0 or more and 4.0 or less, and a ratio R/FR of the photon flux density R to a photon flux density FR within a range of 0.7 or more and 13.0 or less, where the photon flux density R is the number of light quanta (μmol·m⁻²·g⁻¹) incident per unit time and unit area in a wavelength range of 620 nm or more and less than 700 nm, the photon flux density B is the number of light quanta (μmol·m⁻²·g⁻¹) incident per unit time and unit area in a wavelength range of 380 nm or more and 490 nm or less, and the photon flux density FR is the number of light quanta (μmol·m⁻²·g⁻¹) incident per unit time and unit area in a wavelength range of 700 nm or more and 780 nm or less.
 
@@ -84,7 +84,7 @@ For the above reasons, nitrogen is one of nutrients necessary for growth of plan
 
 It is preferred that the light emitting device 100 further include the second fluorescent material 72 having at least one light emission peak wavelength in a range of 680 nm or more and 800 nm or less by being excited by light from the light emitting element 10, wherein the R/FR ratio is within a range of 0.7 or more and 5.0 or less. The R/FR ratio is more preferably within a range of 0.7 or more and 2.0 or less.
 
-### Light Emitting Element
+#### Light Emitting Element
 
 The light emitting element 10 is used as an excitation light source, and is a light emitting element emitting light having a light emission peak wavelength in a range of 380 nm or more and 490 nm or less. As a result, a stable light emitting device having high efficiency, high linearity of output to input and strong mechanical impacts can be obtained.
 
@@ -92,7 +92,7 @@ The range of the light emission peak wavelength of the light emitting element 10
 
 The half value width of emission spectrum of the light emitting element 10 can be, for example, 30 nm or less.
 
-### Fluorescent Member
+#### Fluorescent Member
 
 The fluorescent member 50 used in the light emitting device 100 preferably includes the first fluorescent material 71 and a sealing material, and more preferably further includes the second fluorescent material 72. A thermoplastic resin and a thermosetting resin can be used as the sealing material. The fluorescent member 50 may contain other components such as a filler, a light stabilizer and a colorant, in addition to the fluorescent material and the sealing material. Examples of the filler include silica, barium titanate, titanium oxide and aluminum oxide.
 
@@ -100,7 +100,7 @@ The content of other components other than the fluorescent material 70 and the s
 
 The total content of the fluorescent material 70 in the fluorescent member 50 can be, for example, 5 parts by mass or more and 300 parts by mass or less, per 100 parts by mass of the sealing material. The total content is preferably 10 parts by mass or more and 250 parts by mass or less, more preferably 15 parts by mass or more and 230 parts by mass or less, and still more preferably 15 parts by mass or more and 200 parts by mass or less. When the total content of the fluorescent material 70 in the fluorescent member 50 is within the above range, the light emitted from the light emitting element 10 can be efficiently subjected to wavelength conversion in the fluorescent material 70.
 
-### First Fluorescent Material
+#### First Fluorescent Material
 
 The first fluorescent material 71 is a fluorescent material that is excited by light from the light emitting element 10 and emits light having at least one light emission peak wavelength in a range of 580 nm or more and less than 680 nm. Examples of the first fluorescent material 71 include an Mn⁴⁺-activated fluorogermanate fluorescent material, an Eu²⁺-activated nitride fluorescent material, an Eu²⁺-activated alkaline earth sulfide fluorescent material and an Mn⁴⁺-activated halide fluorescent material. The first fluorescent material 71 may use one selected from those fluorescent materials and may use a combination of two or more thereof. The first fluorescent material preferably contains an Eu²⁺-activated nitride fluorescent material and an Mn⁴⁺-activated fluorogermanate fluorescent material.
 
@@ -138,7 +138,7 @@ The first fluorescent material 71 preferably contains at least two fluorescent m
 
 In the case where the first fluorescent material 71 contains at least two fluorescent materials and two fluorescent materials are a MGF fluorescent material and a CASN fluorescent material, where a compounding ratio thereof (MGF fluorescent material:CASN fluorescent material) is preferably in a range of 50:50 or more and 99:1 or less, more preferably in a range of 60:40 or more and 97:3 or less, and still more preferably in a range of 70:30 or more and 96:4 or less, in mass ratio. In the case where the first fluorescent material contains two fluorescent materials, when those fluorescent materials are a MGF fluorescent material and a CASN fluorescent material and the mass ratio thereof is within the aforementioned range, the light emitted from the light emitting element 10 can be efficiently subjected to wavelength conversion in the first fluorescent material 71. In addition, the R/B ratio can be adjusted to within a range of 2.0 or more and 4.0 or less, and the R/FR ratio is easy to be adjusted to within a range of 0.7 or more and 13.0 or less.
 
-### Second Fluorescent Material
+#### Second Fluorescent Material
 
 The second fluorescent material 72 is a fluorescent material that is excited by the light from the light emitting element 10 and emits light having at least one light emission peak wavelength in a range of 680 nm or more and 800 nm or less.
 
@@ -160,25 +160,25 @@ In the second fluorescent material 72, the value of the parameter y is preferabl
 
 The parameter x is an activation amount of Ce and the value of the parameter x is in a range of exceeding 0.0002 and less than 0.50 (0.0002<x<0.50), and the parameter y is an activation amount of Cr. When the value of the parameter y is in a range of exceeding 0.0001 and less than 0.05 (0.0001<y<0.05), the activation amount of Ce and the activation amount of Cr that are light emission centers contained in the crystal structure of the fluorescent material are within optimum ranges, the decrease of light emission intensity due to the decrease of light emission center can be suppressed, the decrease of light emission intensity due to concentration quenching caused by the increase of the activation amount can be suppressed, and light emission intensity can be enhanced.
 
-### Production Method of Second Fluorescent Material
+#### Production Method of Second Fluorescent Material
 
 A method for producing the second fluorescent material 72 includes the following method.
 
 A compound containing at least one rare earth element Ln selected from the group consisting of rare earth elements excluding Ce, a compound containing at least one element M selected from the group consisting of Al, Ga, and In, a compound containing Ce and a compound containing Cr are mixed such that, when the total molar composition ratio of the M is taken as 5 as the standard, in the case where the total molar composition ratio of Ln, Ce, and Nd is 3, the molar ratio of Ce is a product of 3 and a value of a parameter x, and the molar ratio of Cr is a product of 3 and a value of a parameter y, the value of the parameter x is in a range of exceeding 0.0002 and less than 0.50 and the value of the parameter y is in a range of exceeding 0.0001 and less than 0.05, thereby obtaining a raw material mixture, the raw material mixture is heat-treated, followed by classification and the like, thereby obtaining the second fluorescent material.
 
-### Compound Containing Rare Earth Element Ln
+#### Compound Containing Rare Earth Element Ln
 
 Examples of the compound containing rare earth element Ln include oxides, hydroxides, nitrides, oxynitrides, fluorides, and chlorides, that contain at least one rare earth element Ln selected from the group consisting of rare earth elements excluding Ce. Those compounds may be hydrates. At least a part of the compounds containing rare earth element may use a metal simple substance or an alloy containing rare earth element. The compound containing rare earth element is preferably a compound containing at least one rare earth element Ln selected from the group consisting of Y, Gd, Lu, La, Tb, and Pr. The compound containing rare earth element may be used alone or may be used as a combination of at least two compounds containing rare earth element.
 
 The compound containing rare earth element is preferably an oxide that does not contain elements other than the target composition, as compared with other materials. Examples of the oxide specifically include Y₂O₃, Gd₂O₃, Lu₂O₃, La₂O₃, Tb₄O₇ and Pr₆O₁₁.
 
-### Compound Containing M
+#### Compound Containing M
 
 Examples of the compound containing at least one element M selected from the group consisting of Al, Ga, and In include oxides, hydroxides, nitrides, oxynitrides, fluorides, and chlorides, that contain Al, Ga, or In. Those compounds may be hydrates. Furthermore, Al metal simple substance, Ga metal simple substance, In metal simple substance, Al alloy, Ga alloy or In alloy may be used, and metal simple substance or an alloy may be used in place of at least a part of the compound. The compound containing Al, Ga, or In may be used alone or may be used as a combination of two or more thereof. The compound containing at least one element selected from the group consisting of Al, Ga, and In is preferably an oxide. The reason for this is that an oxide that does not contain elements other than the target composition, as compared with other materials, and a fluorescent material having a target composition are easy to be obtained. When a compound containing elements other than the target composition has been used, residual impurity elements are sometimes present in the fluorescent material obtained. The residual impurity element becomes a killer factor in light emission, leading to the possibility of remarkable decrease of light emission intensity.
 
 Examples of the compound containing Al, Ga, or In specifically include Al₂O₃, Ga₂O₃, and In₂O₃.
 
-### Compound Containing Ce and Compound Containing Cr
+#### Compound Containing Ce and Compound Containing Cr
 
 Examples of the compound containing Ce or the compound containing Cr include oxides, hydroxides, nitrides, fluorides, and chlorides, that contain cerium (Ce) or chromium (Cr). Those compounds may be hydrates. Ce metal simple substance, Ce alloy, Cr metal simple substance, or Cr alloy may be used, and a metal simple substance or an alloy may be used in place of a part of the compound. The compound containing Ce or the compound containing Cr may be used alone or may be used as a combination of two or more thereof. The compound containing Ce or the compound containing Cr is preferably an oxide. The reason for this is that an oxide that does not contain elements other than the target composition, as compared with other materials, and a fluorescent material having a target composition are easy to be obtained. When a compound containing elements other than the target composition has been used, residual impurity elements are sometimes present in the fluorescent material obtained. The residual impurity element becomes a killer factor in light emission, leading to the possibility of remarkable decrease of light emission intensity.
 
@@ -204,7 +204,7 @@ The atmosphere for heat-treating the raw material mixture is an inert atmosphere
 
 The fluorescent material obtained may be subjected to post-treatment steps such as a solid-liquid separation by a method such as cleaning or filtration, drying by a method such as vacuum drying, and classification by dry sieving. After those post-treatment steps, a fluorescent material having a desired average particle diameter is obtained.
 
-### Other Fluorescent Materials
+#### Other Fluorescent Materials
 
 The light emitting device 100 may contain other kinds of fluorescent materials, in addition to the first fluorescent material 71.
 
@@ -250,21 +250,21 @@ GdAlO₃:Cr (x)
 
 The light emitting device 100 can be utilized as a light emitting device for plant cultivation that can activate photosynthesis of plants and promote growth of plants so as to have favorable form and weight.
 
-### Plant Cultivation Method
+#### Plant Cultivation Method
 
 The plant cultivation method of one embodiment of the present disclosure is a method for cultivating plants, including irradiating plants with light emitted from the light emitting device 100. In the plant cultivation method, plants can be irradiated with light from the light emitting device 100 in plant factories that are completely isolated from external environment and make it possible for artificial control. The kind of plants is not particularly limited. However, the light emitting device 100 of one embodiment of the present disclosure can activate photosynthesis of plants and promote growth of plants such that a stem, a leaf, a root, a fruit have favorable form and weight, and therefore is preferably applied to cultivation of vegetables, flowers that contain much chlorophyll performing photosynthesis. Examples of the vegetables include lettuces such as garden lettuce, curl lettuce, Lamb's lettuce, Romaine lettuce, endive, Lollo Rosso, Rucola lettuce, and frill lettuce; Asteraceae vegetables such as “shungiku” (chrysanthemum coronarium); morning glory vegetables such as spinach; Rosaceae vegetables such as strawberry; and flowers such as chrysanthemum, gerbera, rose, and tulip.
 
-## EXAMPLES
+### EXAMPLES
 
 The present invention is further specifically described below by Examples and Comparative Examples.
 
-## Examples 1 to 5
+### Examples 1 to 5
 
-### First Fluorescent Material
+#### First Fluorescent Material
 
 Two fluorescent materials of fluorogarmanate fluorescent material that is activated by Mn⁴⁺, having a light emission peak at 660 nm and fluorescent material containing silicon nitride that are activated by Eu²⁺, having a light emission peak at 660 nm were used as the first fluorescent material 71. In the first fluorescent material 71, a mass ratio of a MGF fluorescent material to a CASN fluorescent material (MGF:CASN) was 95:5.
 
-### Second Fluorescent Material
+#### Second Fluorescent Material
 
 Fluorescent material that is obtained by the following production method was used as the second fluorescent material 72.
 
@@ -272,7 +272,7 @@ Fluorescent material that is obtained by the following production method was use
 
 The raw material mixture obtained was placed in an alumina crucible, and a lid was put on the alumina crucible. The raw material mixture was heat-treated at 1,500° C. for 10 hours in a reducing atmosphere of H₂: 3 vol % and N₂: 97 vol %. Thus, a calcined product was obtained. The calcined product was passed through a dry sieve to obtain a second fluorescent material. The second fluorescent material obtained was subjected to composition analysis by ICP-AES emission spectrometry using an inductively coupled plasma emission analyzer (manufactured by Perkin Elmer). The composition of the second fluorescent material obtained was (Y₀.₉₇₇Ce₀.₀₀₉Cr₀.₀₁₄)₃Al₅O₁₂ (hereinafter referred to as “YAG: Ce, Cr”).
 
-### Light Emitting Device
+#### Light Emitting Device
 
 Nitride semiconductor having a light emission peak wavelength of 450 nm was used as the light emitting element 10 in the light emitting device 100.
 
@@ -280,17 +280,17 @@ Silicone resin was used as a sealing material constituting the fluorescent membe
 
 The resin composition was poured on the light emitting element 10 of a depressed portion of the molded article 40 to fill the depressed portion, and heated at 150° C. for 4 hours to cure the resin composition, thereby forming the fluorescent member 50. Thus, the light emitting device 100 as shown in FIG. 1 was produced in each of Examples 1 to 5.
 
-## Comparative Example 1
+### Comparative Example 1
 
 A light emitting device X including a semiconductor light emitting element having a light emission peak wavelength of 450 nm and a light emitting device Y including a semiconductor light emitting element having a light emission peak length of 660 nm were used, and the R/B ratio was adjusted to 2.5.
 
-### Evaluation
+#### Evaluation
 
-### Photon Flux Density
+#### Photon Flux Density
 
 Photon flux densities of lights emitted from the light emitting device 100 used in Examples 1 to 5 and the light emitting devices X and Y used in Comparative Example 1 were measured using a photon measuring device (LI-250A, manufactured by Li-COR). The photon flux density B, the photon flux density R, and the photon flux density FR of lights emitted from the light emitting devices used in each of the Examples and Comparative Example; the R/B ratio; and the R/FR ratio are shown in Table 1. FIG. 2 shows spectra showing the relationship between a wavelength and a relative photon flux density, in the light emitting devices used in each Example and Comparative Example.
 
-### Plant Cultivation Test
+#### Plant Cultivation Test
 
 The plant cultivation method includes a method of conducting by “growth period by RGB light source (hereinafter referred to as a first growth period)” and “growth period by light source for plant growth (hereinafter referred to as a second growth period)” using a light emitting device according to an embodiment of the present disclosure as a light source.
 
@@ -306,21 +306,21 @@ The cultivation test was specifically conducted by the following method.
 
 Romaine lettuce (green romaine, produced by Nakahara Seed Co., Ltd.) was used as cultivation plant.
 
-### First Growth Period
+#### First Growth Period
 
 Urethane sponges (salad urethane, manufactured by M Hydroponic Research Co., Ltd.) having Romaine lettuce seeded therein were placed side by side on a plastic tray, and were irradiated with light from RGB-LED light source (manufactured by Shibasaki Inc.) to cultivate plants. The plants were cultivated for 16 days under the conditions of room temperature: 22 to 23° C., humidity: 50 to 60%, photon flux density from light emitting device: 100 μmol·m⁻²·s⁻¹ and daytime hour: 16 hours/day. Only water was given until germination, and after the germination (about 4 days later), a solution obtained by mixing Otsuka House #1 (manufactured by Otsuka Chemical Co., Ltd.) and Otsuka House #2 (manufactured by Otsuka Chemical Co., Ltd.) in a mass ratio of 3:2 and dissolving the mixture in water was used as a nutrient solution (Otsuka Formulation A). Conductivity of the nutrient was 1.5 ms·cm⁻¹.
 
-### Second Growth Period
+#### Second Growth Period
 
 After the first growth period, the plants were irradiated with light from the light emitting devices of Examples 1 to 5 and Comparative Example 1, and were subjected to hydroponics.
 
 The plants were cultivated for 19 days under the conditions of room temperature: 22 to 24° C., humidity: 60 to 70%, CO₂ concentration: 600 to 700 ppm, photon flux density from light emitting device: 125 μmol·m⁻²·s⁻¹ and daytime hour: 16 hours/day. Otsuka Formulation A was used as the nutrient solution. Conductivity of the nutrient was 1.5 ms·cm⁻¹. The values of the R/B and R/FR ratios of light for plant irradiation from each light emitting device in the second growth period are shown in Table 1.
 
-### Measurement of Fresh Weight (Edible Part)
+#### Measurement of Fresh Weight (Edible Part)
 
 The plants after cultivation were harvested, and wet weights of a terrestrial part and a root were measured. The wet weight of a terrestrial part of each of 6 cultivated plants having been subjected to hydroponics by irradiating with light from the light emitting devices of Examples 1 to 5 and Comparative Example 1 was measured as a fresh weight (edible part) (g). The results obtained are shown in Table 1 and FIG. 3.
 
-### Measurement of Nitrate Nitrogen Content
+#### Measurement of Nitrate Nitrogen Content
 
 The edible part (about 20 g) of each of the cultivated plants, from which a foot about 5 cm had been removed, was frozen with liquid nitrogen and crushed with a juice mixer (laboratory mixer LM-PLUS, manufactured by Osaka Chemical Co., Ltd.) for 1 minute. The resulting liquid was filtered with Miracloth (manufactured by Milipore), and the filtrate was centrifuged at 4° C. and 15,000 rpm for 5 minutes. The nitrate nitrogen content (mg/100 g) in the cultivated plant in the supernatant was measured using a portable reflection photometer system (product name: RQ flex system, manufactured by Merck) and a test paper (product name: Reflectoquant (registered trade mark), manufactured by Kanto Chemical Co., Inc.). The results are shown in Table 1 and FIG. 4.
 
@@ -355,7 +355,7 @@ In addition, in the foregoing Detailed Description, various features may be grou
 
 The above disclosed subject matter shall be considered illustrative, and not restrictive, and the appended claims are intended to cover all such modifications, enhancements, and other embodiments which fall within the true spirit and scope of the present disclosure. Thus, to the maximum extent allowed by law, the scope of the present disclosure may be determined by the broadest permissible interpretation of the following claims and their equivalents, and shall not be restricted or limited by the foregoing detailed description.
 
-## CLAIMS
+### CLAIMS
 
 1. A light emitting device comprising: a light emitting element having a light emission peak wavelength in a range of 380 nm or more and 490 nm or less; and a fluorescent material that is excited by light from the light emitting element and emits light having at least one light emission peak wavelength in a range of 580 nm or more and less than 680 nm, wherein the light emitting device emits light having a ratio R/B of a photon flux density R to a photon flux density B within a range of 2.0 or more and 4.0 or less, and a ratio R/FR of the photon flux density R to a photon flux density FR within a range of 0.7 or more and 13.0 or less, wherein the photon flux density R is in a wavelength range of 620 nm or more and less than 700 nm, the photon flux density B is in a wavelength range of 380 nm or more and 490 nm or less, and the photon flux density FR is in a wavelength range of 700 nm or more and 780 nm or less.
 

tests/data/groundtruth/docling_v2/ipa20200022300.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "ipa20200022300.xml",
   "origin": {
     "mimetype": "application/xml",

tests/data/groundtruth/docling_v2/ipa20200022300.md

@@ -1,14 +1,14 @@
 # SYSTEM FOR CONTROLLING THE OPERATION OF AN ACTUATOR MOUNTED ON A SEED PLANTING IMPLEMENT
 
-## ABSTRACT
+### ABSTRACT
 
 In one aspect, a system for controlling an operation of an actuator mounted on a seed planting implement may include an actuator configured to adjust a position of a row unit of the seed planting implement relative to a toolbar of the seed planting implement. The system may also include a flow restrictor fluidly coupled to a fluid chamber of the actuator, with the flow restrictor being configured to reduce a rate at which fluid is permitted to exit the fluid chamber in a manner that provides damping to the row unit. Furthermore, the system may include a valve fluidly coupled to the flow restrictor in a parallel relationship such that the valve is configured to permit the fluid exiting the fluid chamber to flow through the flow restrictor and the fluid entering the fluid chamber to bypass the flow restrictor.
 
-## FIELD
+### FIELD
 
 The present disclosure generally relates to seed planting implements and, more particularly, to systems for controlling the operation of an actuator mounted on a seed planting implement in a manner that provides damping to one or more components of the seed planting implement.
 
-## BACKGROUND
+### BACKGROUND
 
 Modern farming practices strive to increase yields of agricultural fields. In this respect, seed planting implements are towed behind a tractor or other work vehicle to deposit seeds in a field. For example, seed planting implements typically include one or more ground engaging tools or openers that form a furrow or trench in the soil. One or more dispensing devices of the seed planting implement may, in turn, deposit seeds into the furrow(s). After deposition of the seeds, a packer wheel may pack the soil on top of the deposited seeds.
 
@@ -16,7 +16,7 @@ In certain instances, the packer wheel may also control the penetration depth of
 
 Accordingly, an improved system for controlling the operation of an actuator mounted on s seed planting implement to enhance the overall operation of the implement would be welcomed in the technology.
 
-## BRIEF DESCRIPTION
+### BRIEF DESCRIPTION
 
 Aspects and advantages of the technology will be set forth in part in the following description, or may be obvious from the description, or may be learned through practice of the technology.
 
@@ -28,7 +28,7 @@ In a further aspect, the present subject matter is directed to a system for prov
 
 These and other features, aspects and advantages of the present technology will become better understood with reference to the following description and appended claims. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the technology and, together with the description, serve to explain the principles of the technology.
 
-## BRIEF DESCRIPTION OF THE DRAWINGS
+### BRIEF DESCRIPTION OF THE DRAWINGS
 
 A full and enabling disclosure of the present technology, including the best mode thereof, directed to one of ordinary skill in the art, is set forth in the specification, which makes reference to the appended figures, in which:
 
@@ -52,7 +52,7 @@ FIG. 9 illustrates a cross-sectional view of a further embodiment of a system fo
 
 Repeat use of reference characters in the present specification and drawings is intended to represent the same or analogous features or elements of the present technology.
 
-## DETAILED DESCRIPTION
+### DETAILED DESCRIPTION
 
 Reference now will be made in detail to embodiments of the invention, one or more examples of which are illustrated in the drawings. Each example is provided by way of explanation of the invention, not limitation of the invention. In fact, it will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the scope or spirit of the invention. For instance, features illustrated or described as part of one embodiment can be used with another embodiment to yield a still further embodiment. Thus, it is intended that the present invention covers such modifications and variations as come within the scope of the appended claims and their equivalents.
 
@@ -114,7 +114,7 @@ Referring now to FIG. 9, a schematic view of a further embodiment of the system
 
 This written description uses examples to disclose the technology, including the best mode, and also to enable any person skilled in the art to practice the technology, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the technology is defined by the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they include structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements with insubstantial differences from the literal language of the claims.
 
-## CLAIMS
+### CLAIMS
 
 1. A system for controlling an operation of an actuator mounted on a seed planting implement, the system comprising: a toolbar; a row unit adjustably mounted on the toolbar; a fluid-driven actuator configured to adjust a position of the row unit relative to the toolbar, the fluid-driven actuator defining first and second fluid chambers; a flow restrictor fluidly coupled to the first fluid chamber, the flow restrictor being configured to reduce a rate at which fluid is permitted to exit the first fluid chamber in a manner that provides damping to the row unit; and a valve fluidly coupled to the first fluid chamber, the valve further being fluidly coupled to the flow restrictor in a parallel relationship such that the valve is configured to permit the fluid exiting the first fluid chamber to flow through the flow restrictor and the fluid entering the first fluid chamber to bypass the flow restrictor.
 

tests/data/groundtruth/docling_v2/lorem_ipsum.docx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "lorem_ipsum",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

tests/data/groundtruth/docling_v2/mixed.md.md

@@ -2,7 +2,7 @@
 
 Some text
 
-## Famous ducks
+### Famous ducks
 
 Here is a table:
 

tests/data/groundtruth/docling_v2/pa20010031492.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "pa20010031492.xml",
   "origin": {
     "mimetype": "application/xml",

tests/data/groundtruth/docling_v2/pa20010031492.md

@@ -1,6 +1,6 @@
 # Assay reagent
 
-## ABSTRACT
+### ABSTRACT
 
 A cell-derived assay reagent prepared from cells which have been killed by treatment with an antibiotic selected from the bleomycin-phleomycin family of antibiotics but which retain a signal-generating metabolic activity such as bioluminescence. 
 
@@ -74,9 +74,9 @@ FIG. 7: Control cells, stationary phase.
 
 FIG. 8: Zeocin™ treated cells, stationary phase.
 
-## EXAMPLE 1
+### EXAMPLE 1
 
-## (A) Inactivation of Bioluminescent E. coil Method
+### (A) Inactivation of Bioluminescent E. coil Method
 
 1. Bioluminescent genetically modified E. coil strain HB101 (E. coli HB101 made bioluminescent by transformation with a plasmid carrying the lux operon of Vibrio fischeri constructed by the method of Shaw and Kado, as described in Biotechnology 4: 560-564) were grown from a frozen stock in 5 ml of low salt medium (LB (5 g/ml NaCl)+glycerol+MgSO₄) for 24 hours.
 
@@ -90,7 +90,7 @@ FIG. 8: Zeocin™ treated cells, stationary phase.
 
 FIG. 1 shows the effect of Zeocin™ treatment on the light output and viable count (per ml) of recombinant bioluminescent E. coil. Zeocin™ was added to a final concentration of 1.5 mg/ml at time zero. The number of viable cells in the culture was observed to decrease with increasing contact cells with Zeocin™, the culture being completely inactivated after 3 hours. The light output from the culture was observed to decrease gradually with increasing Zeocin™ contact time.
 
-## (B) Production of Assay Reagent
+### (B) Production of Assay Reagent
 
 Five hours after the addition of Zeocin™ or water the remaining bacterial cells in the Zeocin™ treated and control cultures were harvested by the centrifugation, washed (to remove traces of Zeocin™ from the Zeocin™ treated culture), re-centrifuged and resuspended in cryoprotectant to an OD₆₃₀ of 0.25. 200 μl aliquots of the cells in cryoprotectant were dispensed into single shot vials, and freeze dried. Freeze dried samples of the Zeocin™ treated cells and control cells were reconstituted in 0.2M sucrose to form assay reagents and the light output of the assay reagents measured at various times after reconstitution.
 
@@ -98,9 +98,9 @@ The light output from assay reagent prepared from cells exposed to 1.5 mg/ml Zeo
 
 FIG. 2 shows the light output from five separate vials of reconstituted Zeocin™ treated assay reagent inactivated according to the method of Example 1(A) and processed into assay reagent as described in Example 1(B). Reconstitution solution was added at time zero and thereafter light output was observed to increase steadily before stabilising out at around 15 minutes after reconstitution. All five vials were observed to give similar light profiles after reconstitution.
 
-## EXAMPLE 2
+### EXAMPLE 2
 
-## Sensitivity of Zeocin™ Treated Assay Reagent to Toxicant Method
+### Sensitivity of Zeocin™ Treated Assay Reagent to Toxicant Method
 
 1. Bioluminescent genetically modified E. coil strain HB101 (E. coli HB101 made bioluminescent by transformation with a plasmid carrying the lux operon of vibrio fischeri constructed by the method of Shaw and Kado, as described in Biotechnology 4: 560-564) was grown in fermenter as a batch culture in low salt medium (LB(5 g/ml NaCl)+glycerol+MgSO₄).
 
@@ -160,9 +160,9 @@ Table 1: Sensitivity of the different assay reagents to ZnSo₄ expressed as EC
 
 The results of the toxicity assays indicate that Zeocin™ treatment does not significantly affect the sensitivity of a recombinant bioluminescent E. coli derived assay reagent to ZnSO₄. Similar results could be expected with other toxic substances which have an effect on signal-generating metabolic activities.
 
-## EXAMPLE 3
+### EXAMPLE 3
 
-## Method to Determine Viable Count
+### Method to Determine Viable Count
 
 1. Samples of bacterial culture to be assayed for viable count were centrifuged at 10,000 rpm for 5 minutes to pellet the bacterial cells.
 
@@ -174,7 +174,7 @@ The results of the toxicity assays indicate that Zeocin™ treatment does not si
 
 5. The number of bacterial colonies present for each of the three aliquots at each of the serial dilutions were counted and the values averaged. Viable count was calculated per ml of bacterial culture.
 
-## CLAIMS
+### CLAIMS
 
 1. A method of making a non-viable preparation of prokaryotic or eukaryotic cells, which preparation has a signal-generating metabolic activity, which method comprises contacting a viable culture of said cells having signal-generating metabolic activity with an antibiotic selected from the bleomycin/phleomycin family of antibiotics.
 

tests/data/groundtruth/docling_v2/pftaps057006474.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "pftaps057006474.txt",
   "origin": {
     "mimetype": "text/plain",

tests/data/groundtruth/docling_v2/pftaps057006474.md

@@ -1,10 +1,10 @@
 # Carbocation containing cyanine-type dye
 
-## ABSTRACT
+### ABSTRACT
 
 To provide a reagent with excellent stability under storage, which can detect a subject compound to be measured with higher specificity and sensitibity. Complexes of a compound represented by the general formula (IV):
 
-## BACKGROUND OF THE INVENTION
+### BACKGROUND OF THE INVENTION
 
 1. Field of the Invention
 
@@ -26,7 +26,7 @@ However, these known cyanine dyes emitting fluorescence via absorption or excita
 
 If the dyes are used as labeling agents and bonded to substances from living organisms such as antibodies for preparing complexes, the complexes are likely to be oxidized easily by environmental factors such as light, heat, moisture, atmospheric oxygen and the like or to be subjected to modification such as generating cross-links. Particularly in water, a modification such as hydrolysis is further accelerated, disadvantageously. Therefore, the practical use of these complexes as detecting reagents in carrying out the microassay of the components of living organisms has encountered difficulties because of their poor stability under storage.
 
-## SUMMARY OF THE INVENTION
+### SUMMARY OF THE INVENTION
 
 The present inventors have made various investigations so as to solve the above problems, and have found that a dye of a particular structure, more specifically a particular polymethine dye, and among others, a dye having an azulene skelton, are extremely stable even after the immobilization thereof as a labeling agent onto substances from living organisms. Thus, the inventors have achieved the present invention. It is an object of the present invention to provide a labeled complex with excellent storage stability which can overcome the above problems.
 
@@ -38,11 +38,11 @@ According to another aspect of the present invention, there is provided a method
 
 According to still another aspect of the present invention, there is provided a method of detecting a subject compound to be analyzed by means of optical means which method comprises using a labeled complex comprised of a substance from a living organism and a labeling agent fixed onto the substance and bonding the complex to the subject compound to be analyzed, wherein the labeling agent comprises a compound represented by the general formula (iv).
 
-## BRIEF DESCRIPTION OF THE DRAWINGS
+### BRIEF DESCRIPTION OF THE DRAWINGS
 
 FIG. 1 depicts one example of fluorescence emitting wave form of a labeling agent.
 
-## DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
+### DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
 
 The present invention will now be explained in detail hereinbelow.
 
@@ -106,7 +106,7 @@ Specific examples of these labeling agents are illustrated in Tables 1, 2 and 3,
 
 The synthetic method of these azulene dyes is described in U.S. Pat. No. 4,738,908.
 
-## CLAIMS
+### CLAIMS
 
 1. A labeled complex for detecting a subject compound to be analyzed by means of optical means using near-infrared radiation which complex comprises a substance from a living organism and a labeling agent fixed onto the substance, the substance capable of specifically binding to the subject compound, wherein the labeling agent comprises a compound represented by the general formula (IV): wherein A, B, D and E are independently selected from the group consisting of hydrogen atom, a substituted or an unsubstituted alkyl group having two or more carbon atoms, alkenyl group, aralkyl group, aryl group, styryl group and heterocyclic group, and at least one of A and B is a substituted or unsubstituted aryl group, and at least one of D and E is a substituted or unsubstituted aryl group; r.sub.1 ' and r.sub.2 ' are individually selected from the group consisting of hydrogen atom, a substituted or an unsubstituted alkyl group, cyclic alkyl group, alkenyl group, aralkyl group and aryl group; k is 0 or 1; is 0, 1 or 2; and X.sub.2.sup..crclbar.  represents an anion.
 

tests/data/groundtruth/docling_v2/pg06442728.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "pg06442728.xml",
   "origin": {
     "mimetype": "application/xml",

tests/data/groundtruth/docling_v2/pg06442728.md

@@ -1,18 +1,18 @@
 # Methods and apparatus for turbo code
 
-## ABSTRACT
+### ABSTRACT
 
 An interleaver receives incoming data frames of size N. The interleaver indexes the elements of the frame with an N₁×N₂ index array. The interleaver then effectively rearranges (permutes) the data by permuting the rows of the index array. The interleaver employs the equation I(j,k)=I(j,αjk+βj)modP) to permute the columns (indexed by k) of each row (indexed by j). P is at least equal to N₂, βj is a constant which may be different for each row, and each αj is a relative prime number relative to P. After permuting, the interleaver outputs the data in a different order than received (e.g., receives sequentially row by row, outputs sequentially each column by column).
 
-## CROSS-REFERENCE TO RELATED APPLICATIONS
+### CROSS-REFERENCE TO RELATED APPLICATIONS
 
 This application claims the benefit of U.S. Provisional Application No. 60/115,394 filed Jan. 11, 1999.
 
-## FIELD OF THE INVENTION
+### FIELD OF THE INVENTION
 
 This invention relates generally to communication systems and, more particularly, to interleavers for performing code modulation.
 
-## BACKGROUND OF THE INVENTION
+### BACKGROUND OF THE INVENTION
 
 Techniques for encoding communication channels, known as coded modulation, have been found to improve the bit error rate (BER) of electronic communication systems such as modem and wireless communication systems. Turbo coded modulation has proven to be a practical, power-efficient, and bandwidth-efficient modulation method for “random-error” channels characterized by additive white Gaussian noise (AWGN) or fading. These random-error channels can be found, for example, in the code division multiple access (CDMA) environment. Since the capacity of a CDMA environment is dependent upon the operating signal to noise ratio, improved performance translates into higher capacity.
 
@@ -34,7 +34,7 @@ It is also an object of the present invention to provide systems and methods of
 
 These and other objects of the invention will become apparent to those skilled in the art from the following description thereof.
 
-## SUMMARY OF THE INVENTION
+### SUMMARY OF THE INVENTION
 
 The foregoing objects, and others, may be accomplished by the present invention, which interleaves a data frame, where the data frame has a predetermined size and is made up of portions. An embodiment of the invention includes an interleaver for interleaving these data frames. The interleaver includes an input memory configured to store a received data frame as an array organized into rows and columns, a processor connected to the input memory and configured to permute the received data frame in accordance with the equation D(j,k)=D (j, (αjk+βj)modP), and a working memory in electrical communication with the processor and configured to store a permuted version of the data frame. The elements of the equation are as follows: D is the data frame, j and k are indexes to the rows and columns, respectively, in the data frame, α and β are sets of constants selected according to the current row, and P and each αj are relative prime numbers. (“Relative prime numbers” connotes a set of numbers that have no common divisor other than 1. Members of a set of relative prime numbers, considered by themselves, need not be prime numbers.)
 
@@ -44,7 +44,7 @@ Still another embodiment of the invention includes an interleaver which includes
 
 The invention will next be described in connection with certain illustrated embodiments and practices. However, it will be clear to those skilled in the art that various modifications, additions and subtractions can be made without departing from the spirit or scope of the claims.
 
-## BRIEF DESCRIPTION OF THE DRAWINGS
+### BRIEF DESCRIPTION OF THE DRAWINGS
 
 The invention will be more clearly understood by reference to the following detailed description of an exemplary embodiment in conjunction with the accompanying drawings, in which:
 
@@ -58,7 +58,7 @@ FIG. 4 depicts a data frame stored in consecutive storage locations;
 
 FIG. 5 depicts an index array for indexing the data frame shown in FIG. 4, and permutation of the index array.
 
-## DETAILED DESCRIPTION OF THE INVENTION
+### DETAILED DESCRIPTION OF THE INVENTION
 
 FIG. 1 illustrates a conventional turbo encoder. As illustrated, conventional turbo encoders include two encoders 20 and an interleaver 100. An interleaver 100 in accordance with the present invention receives incoming data frames 110 of size N, where N is the number of bits, number of bytes, or the number of some other portion the frame may be separated into, which are regarded as frame elements. The interleaver 100 separates the N frame elements into sets of data, such as rows. The interleaver then rearranges (permutes) the data in each set (row) in a pseudo-random fashion. The interleaver 100 may employ different methods for rearranging the data of the different sets. However, those skilled in the art will recognize that one or more of the methods could be reused on one or more of the sets without departing from the scope of the invention. After permuting the data in each of the sets, the interleaver outputs the data in a different order than received.
 
@@ -142,7 +142,7 @@ It will be understood that changes may be made in the above construction and in
 
 It is also to be understood that the following claims are intended to cover all of the generic and specific features of the invention as described herein, and all statements of the scope of the invention which, as a matter of language, might be said to fall therebetween.
 
-## CLAIMS
+### CLAIMS
 
 1. A method of interleaving elements of frames of signal data communication channel, the method comprising; storing a frame of signal data comprising a plurality of elements as an array D having N₁ rows enumerated as 0, 1, . . . N₁−1; and N₂ columns enumerated as 0, 1, . . . N₂−1, wherein N₁ and N₂ are positive integers greater than 1; and permuting array D into array D₁ according to D₁(𝑗,𝑘)=D(𝑗,(αj𝑘+βj)𝑚𝑜𝑑𝑃)  wherein j is an index through the rows of arrays D and D₁; k is an index through the columns of arrays D and D₁; αj and βj are integers predetermined for each row j; P is an integer at least equal to N₂; and each αj is a relative prime number relative to P.
 

tests/data/groundtruth/docling_v2/powerpoint_sample.pptx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "powerpoint_sample",
   "origin": {
     "mimetype": "application/vnd.ms-powerpoint",

tests/data/groundtruth/docling_v2/powerpoint_with_image.pptx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "powerpoint_with_image",
   "origin": {
     "mimetype": "application/vnd.ms-powerpoint",

tests/data/groundtruth/docling_v2/redp5110_sampled.md

@@ -27,13 +27,13 @@ Front cover
 | 1.3.2 New controls: Row and Column Access Control. . . . . . . . . . . . . . . . . . . . . . . . . . .                                                        | 5                                                                                                                                       |
 | Chapter 2. Roles and separation of duties . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                                             | 7                                                                                                                                       |
 | 2.1 Roles . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                     | 8                                                                                                                                       |
-| 2.1.1 DDM and DRDA application server access: QIBM\_DB\_DDMDRDA . . . . . . . . . . .                                                                           | 8                                                                                                                                       |
-| 2.1.2 Toolbox application server access: QIBM\_DB\_ZDA. . . . . . . . . . . . . . . . . . . . . . . .                                                           | 8                                                                                                                                       |
-| 2.1.3 Database Administrator function: QIBM\_DB\_SQLADM . . . . . . . . . . . . . . . . . . . . .                                                               | 9                                                                                                                                       |
-| 2.1.4 Database Information function: QIBM\_DB\_SYSMON                                                                                                           | . . . . . . . . . . . . . . . . . . . . . . 9                                                                                           |
-| 2.1.5 Security Administrator function: QIBM\_DB\_SECADM . . . . . . . . . . . . . . . . . . . . . .                                                             | 9                                                                                                                                       |
+| 2.1.1 DDM and DRDA application server access: QIBM_DB_DDMDRDA . . . . . . . . . . .                                                                           | 8                                                                                                                                       |
+| 2.1.2 Toolbox application server access: QIBM_DB_ZDA. . . . . . . . . . . . . . . . . . . . . . . .                                                           | 8                                                                                                                                       |
+| 2.1.3 Database Administrator function: QIBM_DB_SQLADM . . . . . . . . . . . . . . . . . . . . .                                                               | 9                                                                                                                                       |
+| 2.1.4 Database Information function: QIBM_DB_SYSMON                                                                                                           | . . . . . . . . . . . . . . . . . . . . . . 9                                                                                           |
+| 2.1.5 Security Administrator function: QIBM_DB_SECADM . . . . . . . . . . . . . . . . . . . . . .                                                             | 9                                                                                                                                       |
 | 2.1.6 Change Function Usage CL command . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                                                      | 10                                                                                                                                      |
-| 2.1.7 Verifying function usage IDs for RCAC with the FUNCTION\_USAGE view . . . . .                                                                            | 10                                                                                                                                      |
+| 2.1.7 Verifying function usage IDs for RCAC with the FUNCTION_USAGE view . . . . .                                                                            | 10                                                                                                                                      |
 | 2.2 Separation of duties . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10                             |                                                                                                                                         |
 | Chapter 3. Row and Column Access Control                                                                                                                      | . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13                                                                    |
 | 3.1 Explanation of RCAC and the concept of access control . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . | 14                                                                                                                                      |
@@ -42,11 +42,11 @@ Front cover
 | 3.2 Special registers and built-in global variables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                                           | 18                                                                                                                                      |
 | 3.2.1 Special registers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                                   | 18                                                                                                                                      |
 | 3.2.2 Built-in global variables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                                     | 19                                                                                                                                      |
-| 3.3 VERIFY\_GROUP\_FOR\_USER function . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                                                    | 20                                                                                                                                      |
+| 3.3 VERIFY_GROUP_FOR_USER function . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                                                    | 20                                                                                                                                      |
 | 3.4 Establishing and controlling accessibility by using the RCAC rule text . . . . . . . . . . . . .                                                          | 21                                                                                                                                      |
 | Human resources example . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                                           |                                                                                                                                         |
 | 3.6                                                                                                                                                           | 22                                                                                                                                      |
-| 3.6.1 Assigning the QIBM\_DB\_SECADM function ID to the consultants. . . . . . . . . . . .                                                                      | 23 23                                                                                                                                   |
+| 3.6.1 Assigning the QIBM_DB_SECADM function ID to the consultants. . . . . . . . . . . .                                                                      | 23 23                                                                                                                                   |
 | 3.6.2 Creating group profiles for the users and their roles . . . . . . . . . . . . . . . . . . . . . . .                                                     |                                                                                                                                         |
 | 3.6.3 Demonstrating data access without RCAC . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                                                      | 24                                                                                                                                      |
 | 3.6.4 Defining and creating row permissions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .                                                 | 25                                                                                                                                      |
@@ -188,10 +188,10 @@ Table 2-1 FUNCTION\_USAGE view
 
 | Column name   | Data type   | Description                                                                                                                                                           |
 |---------------|-------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------|
-| FUNCTION\_ID   | VARCHAR(30) | ID of the function.                                                                                                                                                   |
-| USER\_NAME     | VARCHAR(10) | Name of the user profile that has a usage setting for this  function.                                                                                                 |
-| USAGE         | VARCHAR(7)  | Usage setting: GLYPH<SM590000> ALLOWED: The user profile is allowed to use the function. GLYPH<SM590000> DENIED: The user profile is not allowed to use the function. |
-| USER\_TYPE     | VARCHAR(5)  | Type of user profile: GLYPH<SM590000> USER: The user profile is a user. GLYPH<SM590000> GROUP: The user profile is a group.                                           |
+| FUNCTION_ID   | VARCHAR(30) | ID of the function.                                                                                                                                                   |
+| USER_NAME     | VARCHAR(10) | Name of the user profile that has a usage setting for this  function.                                                                                                 |
+| USAGE         | VARCHAR(7)  | Usage setting: GLYPH<SM590000> ALLOWED: The user profile is allowed to use the function. GLYPH<SM590000> DENIED: The user profile is not allowed to use the function. |
+| USER_TYPE     | VARCHAR(5)  | Type of user profile: GLYPH<SM590000> USER: The user profile is a user. GLYPH<SM590000> GROUP: The user profile is a group.                                           |
 
 To discover who has authorization to define and manage RCAC, you can use the query that is shown in Example 2-1.
 
@@ -235,7 +235,7 @@ Table 2-2 shows a comparison of the different function usage IDs and *JOBCTL aut
 
 Table 2-2 Comparison of the different function usage IDs and *JOBCTL authority
 
-| User action                                                                    | *JOBCTL   | QIBM\_DB\_SECADM   | QIBM\_DB\_SQLADM   | QIBM\_DB\_SYSMON   | No Authority   |
+| User action                                                                    | *JOBCTL   | QIBM_DB_SECADM   | QIBM_DB_SQLADM   | QIBM_DB_SYSMON   | No Authority   |
 |--------------------------------------------------------------------------------|-----------|------------------|------------------|------------------|----------------|
 | SET CURRENT DEGREE  (SQL statement)                                            | X         |                  | X                |                  |                |
 | CHGQRYA  command targeting a different user’s job                              | X         |                  | X                |                  |                |
@@ -262,9 +262,9 @@ Table 3-1 Special registers and their corresponding values
 
 | Special register     | Corresponding value                                                                                                                   |
 |----------------------|---------------------------------------------------------------------------------------------------------------------------------------|
-| USER or SESSION\_USER | The effective user of the thread excluding adopted authority.                                                                         |
-| CURRENT\_USER         | The effective user of the thread including adopted authority. When no adopted  authority is present, this has the same value as USER. |
-| SYSTEM\_USER          | The authorization ID that initiated the connection.                                                                                   |
+| USER or SESSION_USER | The effective user of the thread excluding adopted authority.                                                                         |
+| CURRENT_USER         | The effective user of the thread including adopted authority. When no adopted  authority is present, this has the same value as USER. |
+| SYSTEM_USER          | The authorization ID that initiated the connection.                                                                                   |
 
 Figure 3-5 shows the difference in the special register values when an adopted authority is used:
 
@@ -290,15 +290,15 @@ Table 3-2 Built-in global variables
 
 | Global variable       | Type         | Description                                                    |
 |-----------------------|--------------|----------------------------------------------------------------|
-| CLIENT\_HOST           | VARCHAR(255) | Host name of the current client as returned by the system      |
-| CLIENT\_IPADDR         | VARCHAR(128) | IP address of the current client as returned by the system     |
-| CLIENT\_PORT           | INTEGER      | Port used by the current client to communicate with the server |
-| PACKAGE\_NAME          | VARCHAR(128) | Name of the currently running package                          |
-| PACKAGE\_SCHEMA        | VARCHAR(128) | Schema name of the currently running package                   |
-| PACKAGE\_VERSION       | VARCHAR(64)  | Version identifier of the currently running package            |
-| ROUTINE\_SCHEMA        | VARCHAR(128) | Schema name of the currently running routine                   |
-| ROUTINE\_SPECIFIC\_NAME | VARCHAR(128) | Name of the currently running routine                          |
-| ROUTINE\_TYPE          | CHAR(1)      | Type of the currently running routine                          |
+| CLIENT_HOST           | VARCHAR(255) | Host name of the current client as returned by the system      |
+| CLIENT_IPADDR         | VARCHAR(128) | IP address of the current client as returned by the system     |
+| CLIENT_PORT           | INTEGER      | Port used by the current client to communicate with the server |
+| PACKAGE_NAME          | VARCHAR(128) | Name of the currently running package                          |
+| PACKAGE_SCHEMA        | VARCHAR(128) | Schema name of the currently running package                   |
+| PACKAGE_VERSION       | VARCHAR(64)  | Version identifier of the currently running package            |
+| ROUTINE_SCHEMA        | VARCHAR(128) | Schema name of the currently running routine                   |
+| ROUTINE_SPECIFIC_NAME | VARCHAR(128) | Name of the currently running routine                          |
+| ROUTINE_TYPE          | CHAR(1)      | Type of the currently running routine                          |
 
 ## 3.3 VERIFY\_GROUP\_FOR\_USER function
 

tests/data/groundtruth/docling_v2/tablecell.docx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "tablecell",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

tests/data/groundtruth/docling_v2/test-01.xlsx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "test-01",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",

tests/data/groundtruth/docling_v2/test_emf_docx.docx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "test_emf_docx",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",

tests/data/groundtruth/docling_v2/unit_test_01.html.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "unit_test_01",
   "origin": {
     "mimetype": "text/html",

tests/data/groundtruth/docling_v2/unit_test_01.html.md

@@ -1,13 +1,13 @@
 # Title
 
-## section-1
+### section-1
 
-### section-1.1
+#### section-1.1
 
-## section-2
+### section-2
 
-#### section-2.0.1
+##### section-2.0.1
 
-### section-2.2
+#### section-2.2
 
-### section-2.3
+#### section-2.3

tests/data/groundtruth/docling_v2/unit_test_headers.docx.json

@@ -1,6 +1,6 @@
 {
   "schema_name": "DoclingDocument",
-  "version": "1.1.0",
+  "version": "1.3.0",
   "name": "unit_test_headers",
   "origin": {
     "mimetype": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",