docling 1.1.2__tar.gz → 1.5.0__tar.gz

{docling-1.1.2 → docling-1.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.1.2
+Version: 1.5.0
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -21,9 +21,11 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: easyocr
 Provides-Extra: ocr
+Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.19.0,<1)
 Requires-Dist: docling-core (>=1.1.2,<2.0.0)
-Requires-Dist: docling-ibm-models (>=1.1.0,<2.0.0)
+Requires-Dist: docling-ibm-models (>=1.1.1,<2.0.0)
+Requires-Dist: docling-parse (>=0.2.0,<0.3.0)
 Requires-Dist: easyocr (>=1.7,<2.0) ; extra == "easyocr" or extra == "ocr"
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -42,6 +44,7 @@ Description-Content-Type: text/markdown
 
 # Docling
 
+[![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
 ![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)
 [![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
@@ -92,17 +95,21 @@ print(doc.export_to_markdown())  # output: "## DocLayNet: A Large Human-Annotate
 
 ### Convert a batch of documents
 
-For an example of batch-converting documents, see [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py).
+For an example of batch-converting documents, see [batch_convert.py](https://github.com/DS4SD/docling/blob/main/examples/batch_convert.py).
 
 From a local repo clone, you can run it with:
 
 ```
-python examples/convert.py
+python examples/batch_convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
 ### Adjust pipeline features
 
+The example file [custom_convert.py](https://github.com/DS4SD/docling/blob/main/examples/custom_convert.py) contains multiple ways
+one can adjust the conversion pipeline and features.
+
+
 #### Control pipeline options
 
 You can control if table structure recognition or OCR should be performed by arguments passed to `DocumentConverter`:
@@ -166,13 +173,15 @@ Please read [Contributing to Docling](https://github.com/DS4SD/docling/blob/main
 If you use Docling in your projects, please consider citing the following:
 
 ```bib
-@software{Docling,
-author = {Deep Search Team},
-month = {7},
-title = {{Docling}},
-url = {https://github.com/DS4SD/docling},
-version = {main},
-year = {2024}
+@techreport{Docling,
+  author = {Deep Search Team},
+  month = {8},
+  title = {{Docling Technical Report}},
+  url={https://arxiv.org/abs/2408.09869},
+  eprint={2408.09869},
+  doi = "10.48550/arXiv.2408.09869",
+  version = {1.0.0},
+  year = {2024}
 }
 ```
 

{docling-1.1.2 → docling-1.5.0}/README.md

@@ -6,6 +6,7 @@
 
 # Docling
 
+[![arXiv](https://img.shields.io/badge/arXiv-2408.09869-b31b1b.svg)](https://arxiv.org/abs/2408.09869)
 [![PyPI version](https://img.shields.io/pypi/v/docling)](https://pypi.org/project/docling/)
 ![Python](https://img.shields.io/badge/python-3.10%20%7C%203.11%20%7C%203.12-blue)
 [![Poetry](https://img.shields.io/endpoint?url=https://python-poetry.org/badge/v0.json)](https://python-poetry.org/)
@@ -56,17 +57,21 @@ print(doc.export_to_markdown())  # output: "## DocLayNet: A Large Human-Annotate
 
 ### Convert a batch of documents
 
-For an example of batch-converting documents, see [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py).
+For an example of batch-converting documents, see [batch_convert.py](https://github.com/DS4SD/docling/blob/main/examples/batch_convert.py).
 
 From a local repo clone, you can run it with:
 
 ```
-python examples/convert.py
+python examples/batch_convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
 ### Adjust pipeline features
 
+The example file [custom_convert.py](https://github.com/DS4SD/docling/blob/main/examples/custom_convert.py) contains multiple ways
+one can adjust the conversion pipeline and features.
+
+
 #### Control pipeline options
 
 You can control if table structure recognition or OCR should be performed by arguments passed to `DocumentConverter`:
@@ -130,13 +135,15 @@ Please read [Contributing to Docling](https://github.com/DS4SD/docling/blob/main
 If you use Docling in your projects, please consider citing the following:
 
 ```bib
-@software{Docling,
-author = {Deep Search Team},
-month = {7},
-title = {{Docling}},
-url = {https://github.com/DS4SD/docling},
-version = {main},
-year = {2024}
+@techreport{Docling,
+  author = {Deep Search Team},
+  month = {8},
+  title = {{Docling Technical Report}},
+  url={https://arxiv.org/abs/2408.09869},
+  eprint={2408.09869},
+  doi = "10.48550/arXiv.2408.09869",
+  version = {1.0.0},
+  year = {2024}
 }
 ```
 

{docling-1.1.2 → docling-1.5.0}/docling/backend/abstract_backend.py

@@ -35,7 +35,7 @@ class PdfPageBackend(ABC):
 
 class PdfDocumentBackend(ABC):
     @abstractmethod
-    def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
         pass
 
     @abstractmethod

docling-1.5.0/docling/backend/docling_parse_backend.py

@@ -0,0 +1,187 @@
+import logging
+import random
+import time
+from io import BytesIO
+from pathlib import Path
+from typing import Iterable, List, Optional, Union
+
+import pypdfium2 as pdfium
+from docling_parse.docling_parse import pdf_parser
+from PIL import Image, ImageDraw
+from pypdfium2 import PdfPage
+
+from docling.backend.abstract_backend import PdfDocumentBackend, PdfPageBackend
+from docling.datamodel.base_models import BoundingBox, Cell, CoordOrigin, PageSize
+
+_log = logging.getLogger(__name__)
+
+
+class DoclingParsePageBackend(PdfPageBackend):
+    def __init__(self, page_obj: PdfPage, docling_page_obj):
+        super().__init__(page_obj)
+        self._ppage = page_obj
+        self._dpage = docling_page_obj
+        self.text_page = None
+
+    def get_text_in_rect(self, bbox: BoundingBox) -> str:
+        # Find intersecting cells on the page
+        text_piece = ""
+        page_size = self.get_size()
+        parser_width = self._dpage["width"]
+        parser_height = self._dpage["height"]
+
+        scale = (
+            1  # FIX - Replace with param in get_text_in_rect across backends (optional)
+        )
+
+        for i in range(len(self._dpage["cells"])):
+            rect = self._dpage["cells"][i]["box"]["device"]
+            x0, y0, x1, y1 = rect
+            cell_bbox = BoundingBox(
+                l=x0 * scale * page_size.width / parser_width,
+                b=y0 * scale * page_size.height / parser_height,
+                r=x1 * scale * page_size.width / parser_width,
+                t=y1 * scale * page_size.height / parser_height,
+                coord_origin=CoordOrigin.BOTTOMLEFT,
+            ).to_top_left_origin(page_size.height * 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 += self._dpage["cells"][i]["content"]["rnormalized"]
+
+        return text_piece
+
+    def get_text_cells(self) -> Iterable[Cell]:
+        cells = []
+        cell_counter = 0
+
+        page_size = self.get_size()
+
+        parser_width = self._dpage["width"]
+        parser_height = self._dpage["height"]
+
+        for i in range(len(self._dpage["cells"])):
+            rect = self._dpage["cells"][i]["box"]["device"]
+            x0, y0, x1, y1 = rect
+            text_piece = self._dpage["cells"][i]["content"]["rnormalized"]
+            cells.append(
+                Cell(
+                    id=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,
+                    ).to_top_left_origin(page_size.height),
+                )
+            )
+            cell_counter += 1
+
+        def draw_clusters_and_cells():
+            image = (
+                self.get_page_image()
+            )  # 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()
+                cell_color = (
+                    random.randint(30, 140),
+                    random.randint(30, 140),
+                    random.randint(30, 140),
+                )
+                draw.rectangle([(x0, y0), (x1, y1)], outline=cell_color)
+            image.show()
+
+        # before merge:
+        # draw_clusters_and_cells()
+
+        # cells = merge_horizontal_cells(cells)
+
+        # after merge:
+        # draw_clusters_and_cells()
+
+        return cells
+
+    def get_page_image(
+        self, scale: int = 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)
+            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) -> PageSize:
+        return PageSize(width=self._ppage.get_width(), height=self._ppage.get_height())
+
+    def unload(self):
+        self._ppage = None
+        self._dpage = None
+        self.text_page = None
+
+
+class DoclingParseDocumentBackend(PdfDocumentBackend):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
+        super().__init__(path_or_stream)
+        self._pdoc = pdfium.PdfDocument(path_or_stream)
+        # Parsing cells with docling_parser call
+        parser = pdf_parser()
+
+        start_pb_time = time.time()
+
+        if isinstance(path_or_stream, BytesIO):
+            self._parser_doc = parser.find_cells_from_bytesio(path_or_stream)
+        else:
+            self._parser_doc = parser.find_cells(str(path_or_stream))
+
+        end_pb_time = time.time() - start_pb_time
+        _log.info(
+            f"Time to parse {path_or_stream.name} with docling-parse: time={end_pb_time:.3f}"
+        )
+
+    def page_count(self) -> int:
+        return len(self._parser_doc["pages"])
+
+    def load_page(self, page_no: int) -> PdfPage:
+        return DoclingParsePageBackend(
+            self._pdoc[page_no], self._parser_doc["pages"][page_no]
+        )
+
+    def is_valid(self) -> bool:
+        return self.page_count() > 0
+
+    def unload(self):
+        self._pdoc.close()
+        self._pdoc = None
+        self._parser_doc = None

{docling-1.1.2 → docling-1.5.0}/docling/backend/pypdfium2_backend.py

@@ -134,7 +134,9 @@ class PyPdfiumPageBackend(PdfPageBackend):
             return merged_cells
 
         def draw_clusters_and_cells():
-            image = self.get_page_image()
+            image = (
+                self.get_page_image()
+            )  # 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()
@@ -199,7 +201,7 @@ class PyPdfiumPageBackend(PdfPageBackend):
 
 
 class PyPdfiumDocumentBackend(PdfDocumentBackend):
-    def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
         super().__init__(path_or_stream)
         self._pdoc = pdfium.PdfDocument(path_or_stream)
 

{docling-1.1.2 → docling-1.5.0}/docling/datamodel/base_models.py

@@ -1,10 +1,12 @@
 import copy
+import warnings
 from enum import Enum, auto
 from io import BytesIO
-from typing import Any, Dict, List, Optional, Tuple, Union
+from typing import Annotated, Any, Dict, List, Optional, Tuple, Union
 
 from PIL.Image import Image
-from pydantic import BaseModel, ConfigDict, model_validator
+from pydantic import BaseModel, ConfigDict, Field, model_validator
+from typing_extensions import Self
 
 from docling.backend.abstract_backend import PdfPageBackend
 
@@ -234,14 +236,30 @@ class Page(BaseModel):
     model_config = ConfigDict(arbitrary_types_allowed=True)
 
     page_no: int
-    page_hash: str = None
-    size: PageSize = None
-    image: Image = None
+    page_hash: Optional[str] = None
+    size: Optional[PageSize] = None
     cells: List[Cell] = None
     predictions: PagePredictions = PagePredictions()
-    assembled: AssembledUnit = None
+    assembled: Optional[AssembledUnit] = None
 
-    _backend: PdfPageBackend = None  # Internal PDF backend
+    _backend: Optional[PdfPageBackend] = (
+        None  # Internal PDF backend. By default it is cleared during assembling.
+    )
+    _default_image_scale: float = 1.0  # Default image scale for external usage.
+    _image_cache: Dict[float, Image] = (
+        {}
+    )  # Cache of images in different scales. By default it is cleared during assembling.
+
+    def get_image(self, scale: float = 1.0) -> Optional[Image]:
+        if self._backend is None:
+            return self._image_cache.get(scale, None)
+        if not scale in self._image_cache:
+            self._image_cache[scale] = self._backend.get_page_image(scale=scale)
+        return self._image_cache[scale]
+
+    @property
+    def image(self) -> Optional[Image]:
+        return self.get_image(scale=self._default_image_scale)
 
 
 class DocumentStream(BaseModel):
@@ -265,3 +283,22 @@ class PipelineOptions(BaseModel):
     do_ocr: bool = False  # True: perform OCR, replace programmatic PDF text
 
     table_structure_options: TableStructureOptions = TableStructureOptions()
+
+
+class AssembleOptions(BaseModel):
+    keep_page_images: Annotated[
+        bool,
+        Field(
+            deprecated="`keep_page_images` is depreacted, set the value of `images_scale` instead"
+        ),
+    ] = False  # False: page images are removed in the assemble step
+    images_scale: Optional[float] = None  # if set, the scale for generated images
+
+    @model_validator(mode="after")
+    def set_page_images_from_deprecated(self) -> Self:
+        with warnings.catch_warnings():
+            warnings.simplefilter("ignore", DeprecationWarning)
+            default_scale = 1.0
+            if self.keep_page_images and self.images_scale is None:
+                self.images_scale = default_scale
+        return self

{docling-1.1.2 → docling-1.5.0}/docling/datamodel/document.py

@@ -1,7 +1,7 @@
 import logging
 from io import BytesIO
 from pathlib import Path, PurePath
-from typing import ClassVar, Dict, Iterable, List, Optional, Type, Union
+from typing import ClassVar, Dict, Iterable, List, Optional, Tuple, Type, Union
 
 from docling_core.types import BaseCell, BaseText
 from docling_core.types import BoundingBox as DsBoundingBox
@@ -14,13 +14,14 @@ from docling_core.types import TableCell
 from pydantic import BaseModel
 
 from docling.backend.abstract_backend import PdfDocumentBackend
-from docling.backend.pypdfium2_backend import PyPdfiumDocumentBackend
+from docling.backend.docling_parse_backend import DoclingParseDocumentBackend
 from docling.datamodel.base_models import (
     AssembledUnit,
     ConversionStatus,
     DocumentStream,
     FigureElement,
     Page,
+    PageElement,
     TableElement,
     TextElement,
 )
@@ -64,7 +65,7 @@ class InputDocument(BaseModel):
         path_or_stream: Union[BytesIO, Path],
         filename: Optional[str] = None,
         limits: Optional[DocumentLimits] = None,
-        pdf_backend=PyPdfiumDocumentBackend,
+        pdf_backend=DoclingParseDocumentBackend,
     ):
         super().__init__()
 
@@ -302,13 +303,27 @@ class ConvertedDocument(BaseModel):
         else:
             return ""
 
+    def render_element_images(
+        self, element_types: Tuple[PageElement] = (FigureElement,)
+    ):
+        for element in self.assembled.elements:
+            if isinstance(element, element_types):
+                page_ix = element.page_no
+                scale = self.pages[page_ix]._default_image_scale
+                crop_bbox = element.cluster.bbox.scaled(scale=scale).to_top_left_origin(
+                    page_height=self.pages[page_ix].size.height * scale
+                )
+
+                cropped_im = self.pages[page_ix].image.crop(crop_bbox.as_tuple())
+                yield element, cropped_im
+
 
 class DocumentConversionInput(BaseModel):
 
     _path_or_stream_iterator: Iterable[Union[Path, DocumentStream]] = None
     limits: Optional[DocumentLimits] = DocumentLimits()
 
-    DEFAULT_BACKEND: ClassVar = PyPdfiumDocumentBackend
+    DEFAULT_BACKEND: ClassVar = DoclingParseDocumentBackend
 
     def docs(
         self, pdf_backend: Optional[Type[PdfDocumentBackend]] = None

{docling-1.1.2 → docling-1.5.0}/docling/document_converter.py

@@ -14,6 +14,7 @@ from pydantic import AnyHttpUrl, TypeAdapter, ValidationError
 from docling.backend.abstract_backend import PdfDocumentBackend
 from docling.datamodel.base_models import (
     AssembledUnit,
+    AssembleOptions,
     ConversionStatus,
     Page,
     PipelineOptions,
@@ -44,6 +45,7 @@ class DocumentConverter:
         pipeline_options: PipelineOptions = PipelineOptions(),
         pdf_backend: Type[PdfDocumentBackend] = DocumentConversionInput.DEFAULT_BACKEND,
         pipeline_cls: Type[BaseModelPipeline] = StandardModelPipeline,
+        assemble_options: AssembleOptions = AssembleOptions(),
     ):
         if not artifacts_path:
             artifacts_path = self.download_models_hf()
@@ -57,6 +59,7 @@ class DocumentConverter:
         self.page_assemble_model = PageAssembleModel(config={})
         self.glm_model = GlmModel(config={})
         self.pdf_backend = pdf_backend
+        self.assemble_options = assemble_options
 
     @staticmethod
     def download_models_hf(
@@ -174,17 +177,21 @@ class DocumentConverter:
                     pages_with_images,
                 )
 
+                # 4. Run pipeline stages
                 pipeline_pages = self.model_pipeline.apply(pages_with_cells)
 
-                # 7. Assemble page elements (per page)
+                # 5. Assemble page elements (per page)
                 assembled_pages = self.page_assemble_model(pipeline_pages)
 
                 # exhaust assembled_pages
                 for assembled_page in assembled_pages:
                     # Free up mem resources before moving on with next batch
-                    assembled_page.image = (
-                        None  # Comment this if you want to visualize page images
-                    )
+
+                    # Remove page images (can be disabled)
+                    if self.assemble_options.images_scale is None:
+                        assembled_page._image_cache = {}
+
+                    # Unload backend
                     assembled_page._backend.unload()
 
                     all_assembled_pages.append(assembled_page)
@@ -222,7 +229,15 @@ class DocumentConverter:
 
     # Generate the page image and store it in the page object
     def populate_page_images(self, doc: InputDocument, page: Page) -> Page:
-        page.image = page._backend.get_page_image()
+        # default scale
+        page.get_image(scale=1.0)
+
+        # user requested scales
+        if self.assemble_options.images_scale is not None:
+            page._default_image_scale = self.assemble_options.images_scale
+            page.get_image(
+                scale=self.assemble_options.images_scale
+            )  # this will trigger storing the image in the internal cache
 
         return page
 
@@ -238,7 +253,7 @@ class DocumentConverter:
                 draw.rectangle([(x0, y0), (x1, y1)], outline="red")
             image.show()
 
-        # draw_text_boxes(page.image, cells)
+        # draw_text_boxes(page.get_image(scale=1.0), cells)
 
         return page
 

{docling-1.1.2 → docling-1.5.0}/docling/models/easyocr_model.py

@@ -30,7 +30,7 @@ class EasyOcrModel:
 
         for page in page_batch:
             # rects = page._fpage.
-            high_res_image = page._backend.get_page_image(scale=self.scale)
+            high_res_image = page.get_image(scale=self.scale)
             im = numpy.array(high_res_image)
             result = self.reader.readtext(im)
 

{docling-1.1.2 → docling-1.5.0}/docling/models/layout_model.py

@@ -69,6 +69,10 @@ class LayoutModel:
             "Key-Value Region": 0.45,
         }
 
+        CLASS_REMAPPINGS = {
+            "Document Index": "Table",
+        }
+
         _log.debug("================= Start postprocess function ====================")
         start_time = time.time()
         # Apply Confidence Threshold to cluster predictions
@@ -79,6 +83,10 @@ class LayoutModel:
             confidence = CLASS_THRESHOLDS[cluster.label]
             if cluster.confidence >= confidence:
                 # annotation["created_by"] = "high_conf_pred"
+
+                # Remap class labels where needed.
+                if cluster.label in CLASS_REMAPPINGS.keys():
+                    cluster.label = CLASS_REMAPPINGS[cluster.label]
                 clusters_out.append(cluster)
 
         # map to dictionary clusters and cells, with bottom left origin
@@ -259,7 +267,9 @@ class LayoutModel:
     def __call__(self, page_batch: Iterable[Page]) -> Iterable[Page]:
         for page in page_batch:
             clusters = []
-            for ix, pred_item in enumerate(self.layout_predictor.predict(page.image)):
+            for ix, pred_item in enumerate(
+                self.layout_predictor.predict(page.get_image(scale=1.0))
+            ):
                 cluster = Cluster(
                     id=ix,
                     label=pred_item["label"],

{docling-1.1.2 → docling-1.5.0}/docling/models/table_structure_model.py

@@ -34,7 +34,9 @@ class TableStructureModel:
             self.scale = 2.0  # Scale up table input images to 144 dpi
 
     def draw_table_and_cells(self, page: Page, tbl_list: List[TableElement]):
-        image = page._backend.get_page_image()
+        image = (
+            page._backend.get_page_image()
+        )  # make new image to avoid drawing on the saved ones
         draw = ImageDraw.Draw(image)
 
         for table_element in tbl_list:
@@ -94,13 +96,7 @@ class TableStructureModel:
                 "width": page.size.width * self.scale,
                 "height": page.size.height * self.scale,
             }
-            # add image to page input.
-            if self.scale == 1.0:
-                page_input["image"] = numpy.asarray(page.image)
-            else:  # render new page image on the fly at desired scale
-                page_input["image"] = numpy.asarray(
-                    page._backend.get_page_image(scale=self.scale)
-                )
+            page_input["image"] = numpy.asarray(page.get_image(scale=self.scale))
 
             table_clusters, table_bboxes = zip(*in_tables)
 

{docling-1.1.2 → docling-1.5.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.1.2"  # DO NOT EDIT, updated automatically
+version = "1.5.0"  # DO NOT EDIT, updated automatically
 description = "Docling PDF conversion package"
 authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -24,7 +24,7 @@ packages = [{include = "docling"}]
 python = "^3.10"
 pydantic = "^2.0.0"
 docling-core = "^1.1.2"
-docling-ibm-models = "^1.1.0"
+docling-ibm-models = "^1.1.1"
 deepsearch-glm = ">=0.19.0,<1"
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
@@ -32,6 +32,8 @@ pydantic-settings = "^2.3.0"
 huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = { version = "^1.7", optional = true }
+docling-parse = "^0.2.0"
+certifi = ">=2024.7.4"
 
 [tool.poetry.group.dev.dependencies]
 black = {extras = ["jupyter"], version = "^24.4.2"}