deepdoctection 0.43.6__py3-none-any.whl → 0.44.1__py3-none-any.whl

deepdoctection/extern/fastlang.py

@@ -29,7 +29,8 @@ from typing import Any, Mapping, Union
 
 from lazy_imports import try_import
 
-from ..utils.file_utils import Requirement, get_fasttext_requirement
+from ..utils.develop import deprecated
+from ..utils.file_utils import Requirement, get_fasttext_requirement, get_numpy_v1_requirement
 from ..utils.settings import TypeOrStr, get_type
 from ..utils.types import PathLikeOrStr
 from .base import DetectionResult, LanguageDetector, ModelCategories
@@ -69,6 +70,7 @@ class FasttextLangDetectorMixin(LanguageDetector, ABC):
         return "fasttext_" + "_".join(Path(path_weights).parts[-2:])
 
 
+@deprecated("As FastText archived, it will be deprecated in the near future.", "2025-08-17")
 class FasttextLangDetector(FasttextLangDetectorMixin):
     """
     Fasttext language detector wrapper. Two models provided in the fasttext library can be used to identify languages.
@@ -114,7 +116,7 @@ class FasttextLangDetector(FasttextLangDetectorMixin):
 
     @classmethod
     def get_requirements(cls) -> list[Requirement]:
-        return [get_fasttext_requirement()]
+        return [get_numpy_v1_requirement(), get_fasttext_requirement()]
 
     def clone(self) -> FasttextLangDetector:
         return self.__class__(self.path_weights, self.categories.get_categories(), self.categories_orig)

deepdoctection/mapper/laylmstruct.py

@@ -806,17 +806,17 @@ def image_to_raw_lm_features(
     raw_features["image_id"] = page.image_id
     raw_features["width"] = page.width
     raw_features["height"] = page.height
-    raw_features["ann_ids"] = text_["ann_ids"]
-    raw_features["words"] = text_["words"]
+    raw_features["ann_ids"] = text_.ann_ids
+    raw_features["words"] = text_.words
     # We use a dummy bounding box for all bounding boxes so that we can pass the raw features to
     # raw_features_to_layoutlm_features
-    raw_features["bbox"] = [_CLS_BOX] * len(text_["words"])
+    raw_features["bbox"] = [_CLS_BOX] * len(text_.words)
     raw_features["dataset_type"] = dataset_type
 
-    if use_token_tag and text_["token_tags"]:
-        raw_features["labels"] = text_["token_tags"]
-    elif text_["token_classes"]:
-        raw_features["labels"] = text_["token_classes"]
+    if use_token_tag and text_.token_tags:
+        raw_features["labels"] = text_.token_tags
+    elif text_.token_classes:
+        raw_features["labels"] = text_.token_classes
     elif page.document_type is not None:
         document_type_id = page.image_orig.summary.get_sub_category(PageType.DOCUMENT_TYPE).category_id - 1
         raw_features["labels"] = [document_type_id]

deepdoctection/pipe/base.py

@@ -23,12 +23,11 @@ from __future__ import annotations
 
 from abc import ABC, abstractmethod
 from collections import defaultdict
-from dataclasses import dataclass, field
 from typing import Any, Callable, Mapping, Optional, Union
 from uuid import uuid1
 
 from ..dataflow import DataFlow, MapData
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..mapper.misc import curry
 from ..utils.context import timed_operation
 from ..utils.identifier import get_uuid_from_str
@@ -37,25 +36,6 @@ from ..utils.types import DP
 from .anngen import DatapointManager
 
 
-@dataclass(frozen=True)
-class MetaAnnotation:
-    """
-    A immutable dataclass that stores information about what `Image` are being
-    modified through a pipeline component.
-
-    Attributes:
-        image_annotations: Tuple of `ObjectTypes` representing image annotations.
-        sub_categories: Dictionary mapping `ObjectTypes` to sets of `ObjectTypes` for sub-categories.
-        relationships: Dictionary mapping `ObjectTypes` to sets of `ObjectTypes` for relationships.
-        summaries: Tuple of `ObjectTypes` representing summaries.
-    """
-
-    image_annotations: tuple[ObjectTypes, ...] = field(default=())
-    sub_categories: dict[ObjectTypes, set[ObjectTypes]] = field(default_factory=dict)
-    relationships: dict[ObjectTypes, set[ObjectTypes]] = field(default_factory=dict)
-    summaries: tuple[ObjectTypes, ...] = field(default=())
-
-
 class PipelineComponent(ABC):
     """
     Base class for pipeline components.
@@ -427,15 +407,24 @@ class Pipeline(ABC):
             as well as summaries (list with sub categories).
         """
         image_annotations: list[ObjectTypes] = []
-        sub_categories = defaultdict(set)
-        relationships = defaultdict(set)
+        sub_categories: dict[ObjectTypes, dict[ObjectTypes, set[ObjectTypes]]] = {}
+        relationships = defaultdict(set[ObjectTypes])  # type: ignore
         summaries: list[ObjectTypes] = []
         for component in self.pipe_component_list:
             meta_anns = component.get_meta_annotation()
             image_annotations.extend(meta_anns.image_annotations)
             for key, value in meta_anns.sub_categories.items():
-                sub_categories[key].update(value)
-            for key, value in meta_anns.relationships.items():
+                sub_dict = meta_anns.sub_categories[key]
+                for sub_cat, sub_cat_value in value.items():
+                    if sub_cat in sub_dict:
+                        sub_dict[sub_cat].update(sub_cat_value)
+                    else:
+                        sub_dict[sub_cat] = {sub_cat_value}  # type: ignore
+                if key in sub_categories:
+                    sub_categories[key].update(sub_dict)
+                else:
+                    sub_categories[key] = sub_dict
+            for key, value in meta_anns.relationships.items():  # type: ignore
                 relationships[key].update(value)
             summaries.extend(meta_anns.summaries)
         return MetaAnnotation(
@@ -445,6 +434,21 @@ class Pipeline(ABC):
             summaries=tuple(summaries),
         )
 
+    def get_service_id_to_meta_annotation(self) -> Mapping[str, MetaAnnotation]:
+        """
+        Collects meta annotations from all pipeline components and return a dict of service id to its meta annotation.
+
+        Returns:
+            `service_id` to `MetaAnnotation` with information about image annotations (list), sub categories (dict with
+            category names and generated sub categories), relationships (dict with category names and generated
+            relationships) as well as summaries (list with sub categories).
+        """
+        service_id_to_meta_annotation = {}
+        for component in self.pipe_component_list:
+            meta_anns = component.get_meta_annotation()
+            service_id_to_meta_annotation[component.service_id] = meta_anns
+        return service_id_to_meta_annotation
+
     def get_pipeline_info(
         self, service_id: Optional[str] = None, name: Optional[str] = None
     ) -> Union[str, Mapping[str, str]]:

deepdoctection/pipe/common.py

@@ -28,13 +28,13 @@ from typing import Literal, Mapping, Optional, Sequence, Union
 import numpy as np
 
 from ..dataflow import DataFlow, MapData
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..datapoint.view import IMAGE_DEFAULTS, Page
 from ..extern.base import DetectionResult
 from ..mapper.match import match_anns_by_distance, match_anns_by_intersection
 from ..mapper.misc import to_image
 from ..utils.settings import LayoutType, ObjectTypes, Relationships, TypeOrStr, get_type
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 if os.environ.get("DD_USE_TORCH"):

deepdoctection/pipe/concurrency.py

@@ -29,11 +29,11 @@ from typing import Callable, Optional, Sequence, Union
 import tqdm
 
 from ..dataflow import DataFlow, MapData
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..utils.context import timed_operation
 from ..utils.tqdm import get_tqdm
 from ..utils.types import QueueType, TqdmType
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .common import ImageParsingService, PageParsingService
 from .registry import pipeline_component_registry
 

deepdoctection/pipe/language.py

@@ -20,12 +20,12 @@ Module for language detection pipeline component
 """
 from typing import Optional, Sequence
 
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..datapoint.view import ImageDefaults, Page
 from ..extern.base import LanguageDetector, ObjectDetector
 from ..utils.error import ImageError
 from ..utils.settings import PageType, TypeOrStr, get_type
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 

deepdoctection/pipe/layout.py

@@ -24,13 +24,13 @@ from typing import Optional, Sequence, Union
 
 import numpy as np
 
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..extern.base import ObjectDetector, PdfMiner
 from ..mapper.misc import curry
 from ..utils.error import ImageError
 from ..utils.settings import ObjectTypes
 from ..utils.transform import PadTransform
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 

deepdoctection/pipe/lm.py

@@ -23,11 +23,11 @@ from __future__ import annotations
 from copy import copy
 from typing import TYPE_CHECKING, Any, Callable, Literal, Optional, Sequence, Union
 
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..extern.base import SequenceClassResult
 from ..mapper.laylmstruct import image_to_layoutlm_features, image_to_lm_features
 from ..utils.settings import BioTag, LayoutType, ObjectTypes, PageType, TokenClasses, WordType
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 if TYPE_CHECKING:
@@ -246,7 +246,17 @@ class LMTokenClassifierService(PipelineComponent):
     def get_meta_annotation(self) -> MetaAnnotation:
         return MetaAnnotation(
             image_annotations=(),
-            sub_categories={LayoutType.WORD: {WordType.TOKEN_CLASS, WordType.TAG, WordType.TOKEN_TAG}},
+            sub_categories={
+                LayoutType.WORD: {
+                    WordType.TOKEN_CLASS: set(self.language_model.categories.categories_semantics)  # type: ignore
+                    if self.language_model.categories.categories_semantics
+                    else [],
+                    WordType.TAG: set(self.language_model.categories.categories_bio)  # type: ignore
+                    if self.language_model.categories.categories_bio
+                    else [],
+                    WordType.TOKEN_TAG: set(self.language_model.categories.get_categories(as_dict=False)),
+                }
+            },
             relationships={},
             summaries=(),
         )

deepdoctection/pipe/order.py

@@ -31,11 +31,11 @@ import numpy as np
 
 from ..datapoint.annotation import ImageAnnotation
 from ..datapoint.box import BoundingBox, merge_boxes
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..datapoint.view import IMAGE_DEFAULTS
 from ..extern.base import DetectionResult
 from ..extern.tp.tpfrcnn.utils.np_box_ops import ioa as np_ioa
-from ..pipe.base import MetaAnnotation, PipelineComponent
+from ..pipe.base import PipelineComponent
 from ..pipe.registry import pipeline_component_registry
 from ..utils.logger import LoggingRecord, logger
 from ..utils.settings import LayoutType, ObjectTypes, Relationships, TypeOrStr, get_type
@@ -611,8 +611,8 @@ class TextLineService(TextLineServiceMixin):
         """
         return MetaAnnotation(
             image_annotations=(LayoutType.LINE,),
-            sub_categories={LayoutType.LINE: {Relationships.CHILD}},
-            relationships={},
+            sub_categories={},
+            relationships={LayoutType.LINE: {Relationships.CHILD}},
             summaries=(),
         )
 
@@ -818,7 +818,11 @@ class TextOrderService(TextLineServiceMixin):
         anns_with_reading_order = list(copy(self.floating_text_block_categories)) + add_category
         return MetaAnnotation(
             image_annotations=tuple(image_annotations),
-            sub_categories={category: {Relationships.READING_ORDER} for category in anns_with_reading_order},
+            sub_categories={  # type: ignore
+                category: {Relationships.READING_ORDER: {Relationships.READING_ORDER}}
+                for category in anns_with_reading_order
+            }
+            | {self.text_container: {Relationships.READING_ORDER: {Relationships.READING_ORDER}}},
             relationships={},
             summaries=(),
         )

deepdoctection/pipe/refine.py

@@ -31,12 +31,12 @@ import networkx as nx  # type: ignore
 
 from ..datapoint.annotation import ImageAnnotation
 from ..datapoint.box import merge_boxes
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..extern.base import DetectionResult
 from ..mapper.maputils import MappingContextManager
 from ..utils.error import ImageError
 from ..utils.settings import CellType, LayoutType, ObjectTypes, Relationships, TableType, get_type
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 __all__ = ["TableSegmentationRefinementService", "generate_html_string"]
@@ -537,12 +537,12 @@ class TableSegmentationRefinementService(PipelineComponent):
             image_annotations=(),
             sub_categories={
                 LayoutType.CELL: {
-                    CellType.ROW_NUMBER,
-                    CellType.COLUMN_NUMBER,
-                    CellType.ROW_SPAN,
-                    CellType.COLUMN_SPAN,
+                    CellType.ROW_NUMBER: {CellType.ROW_NUMBER},
+                    CellType.COLUMN_NUMBER: {CellType.COLUMN_NUMBER},
+                    CellType.ROW_SPAN: {CellType.ROW_SPAN},
+                    CellType.COLUMN_SPAN: {CellType.COLUMN_SPAN},
                 },
-                LayoutType.TABLE: {TableType.HTML},
+                LayoutType.TABLE: {TableType.HTML: {TableType.HTML}},
             },
             relationships={},
             summaries=(),

deepdoctection/pipe/segment.py

@@ -29,13 +29,13 @@ import numpy as np
 
 from ..datapoint.annotation import ImageAnnotation
 from ..datapoint.box import BoundingBox, global_to_local_coords, intersection_box, intersection_boxes, iou, merge_boxes
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..extern.base import DetectionResult
 from ..mapper.maputils import MappingContextManager
 from ..mapper.match import match_anns_by_intersection
 from ..utils.error import ImageError
 from ..utils.settings import CellType, LayoutType, ObjectTypes, Relationships, TableType, TypeOrStr, get_type
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .refine import generate_html_string
 from .registry import pipeline_component_registry
 
@@ -974,13 +974,13 @@ class TableSegmentationService(PipelineComponent):
             image_annotations=(),
             sub_categories={
                 LayoutType.CELL: {
-                    CellType.ROW_NUMBER,
-                    CellType.COLUMN_NUMBER,
-                    CellType.ROW_SPAN,
-                    CellType.COLUMN_SPAN,
+                    CellType.ROW_NUMBER: {CellType.ROW_NUMBER},
+                    CellType.COLUMN_NUMBER: {CellType.COLUMN_NUMBER},
+                    CellType.ROW_SPAN: {CellType.ROW_SPAN},
+                    CellType.COLUMN_SPAN: {CellType.COLUMN_SPAN},
                 },
-                LayoutType.ROW: {CellType.ROW_NUMBER},
-                LayoutType.COLUMN: {CellType.COLUMN_NUMBER},
+                LayoutType.ROW: {CellType.ROW_NUMBER: {CellType.ROW_NUMBER}},
+                LayoutType.COLUMN: {CellType.COLUMN_NUMBER: {CellType.COLUMN_NUMBER}},
             },
             relationships={},
             summaries=(),
@@ -1314,37 +1314,37 @@ class PubtablesSegmentationService(PipelineComponent):
             image_annotations=(),
             sub_categories={
                 LayoutType.CELL: {
-                    CellType.ROW_NUMBER,
-                    CellType.COLUMN_NUMBER,
-                    CellType.ROW_SPAN,
-                    CellType.COLUMN_SPAN,
+                    CellType.ROW_NUMBER: {CellType.ROW_NUMBER},
+                    CellType.COLUMN_NUMBER: {CellType.COLUMN_NUMBER},
+                    CellType.ROW_SPAN: {CellType.ROW_SPAN},
+                    CellType.COLUMN_SPAN: {CellType.COLUMN_SPAN},
                 },
                 CellType.SPANNING: {
-                    CellType.ROW_NUMBER,
-                    CellType.COLUMN_NUMBER,
-                    CellType.ROW_SPAN,
-                    CellType.COLUMN_SPAN,
+                    CellType.ROW_NUMBER: {CellType.ROW_NUMBER},
+                    CellType.COLUMN_NUMBER: {CellType.COLUMN_NUMBER},
+                    CellType.ROW_SPAN: {CellType.ROW_SPAN},
+                    CellType.COLUMN_SPAN: {CellType.COLUMN_SPAN},
                 },
                 CellType.ROW_HEADER: {
-                    CellType.ROW_NUMBER,
-                    CellType.COLUMN_NUMBER,
-                    CellType.ROW_SPAN,
-                    CellType.COLUMN_SPAN,
+                    CellType.ROW_NUMBER: {CellType.ROW_NUMBER},
+                    CellType.COLUMN_NUMBER: {CellType.COLUMN_NUMBER},
+                    CellType.ROW_SPAN: {CellType.ROW_SPAN},
+                    CellType.COLUMN_SPAN: {CellType.COLUMN_SPAN},
                 },
                 CellType.COLUMN_HEADER: {
-                    CellType.ROW_NUMBER,
-                    CellType.COLUMN_NUMBER,
-                    CellType.ROW_SPAN,
-                    CellType.COLUMN_SPAN,
+                    CellType.ROW_NUMBER: {CellType.ROW_NUMBER},
+                    CellType.COLUMN_NUMBER: {CellType.COLUMN_NUMBER},
+                    CellType.ROW_SPAN: {CellType.ROW_SPAN},
+                    CellType.COLUMN_SPAN: {CellType.COLUMN_SPAN},
                 },
                 CellType.PROJECTED_ROW_HEADER: {
-                    CellType.ROW_NUMBER,
-                    CellType.COLUMN_NUMBER,
-                    CellType.ROW_SPAN,
-                    CellType.COLUMN_SPAN,
+                    CellType.ROW_NUMBER: {CellType.ROW_NUMBER},
+                    CellType.COLUMN_NUMBER: {CellType.COLUMN_NUMBER},
+                    CellType.ROW_SPAN: {CellType.ROW_SPAN},
+                    CellType.COLUMN_SPAN: {CellType.COLUMN_SPAN},
                 },
-                LayoutType.ROW: {CellType.ROW_NUMBER},
-                LayoutType.COLUMN: {CellType.COLUMN_NUMBER},
+                LayoutType.ROW: {CellType.ROW_NUMBER: {CellType.ROW_NUMBER}},
+                LayoutType.COLUMN: {CellType.COLUMN_NUMBER: {CellType.COLUMN_NUMBER}},
             },
             relationships={},
             summaries=(),

deepdoctection/pipe/sub_layout.py

@@ -28,12 +28,12 @@ import numpy as np
 
 from ..datapoint.annotation import ImageAnnotation
 from ..datapoint.box import crop_box_from_image
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..extern.base import DetectionResult, ObjectDetector, PdfMiner
 from ..utils.settings import ObjectTypes, Relationships, TypeOrStr, get_type
 from ..utils.transform import PadTransform
 from ..utils.types import PixelValues
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 

deepdoctection/pipe/text.py

@@ -25,13 +25,13 @@ from copy import deepcopy
 from typing import Optional, Sequence, Union
 
 from ..datapoint.annotation import ImageAnnotation
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..extern.base import ObjectDetector, PdfMiner, TextRecognizer
 from ..extern.tessocr import TesseractOcrDetector
 from ..utils.error import ImageError
 from ..utils.settings import ObjectTypes, PageType, TypeOrStr, WordType, get_type
 from ..utils.types import PixelValues
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 __all__ = ["TextExtractionService"]
@@ -202,16 +202,21 @@ class TextExtractionService(PipelineComponent):
         return 1
 
     def get_meta_annotation(self) -> MetaAnnotation:
-        sub_cat_dict: dict[ObjectTypes, set[ObjectTypes]]
+        sub_cat_dict: dict[ObjectTypes, dict[ObjectTypes, set[ObjectTypes]]]
         if self.extract_from_category:
-            sub_cat_dict = {category: {WordType.CHARACTERS} for category in self.extract_from_category}
+            sub_cat_dict = {
+                category: {WordType.CHARACTERS: {WordType.CHARACTERS}} for category in self.extract_from_category
+            }
         else:
             if not isinstance(self.predictor, (ObjectDetector, PdfMiner)):
                 raise TypeError(
                     f"self.predictor must be of type ObjectDetector or PdfMiner but is of type "
                     f"{type(self.predictor)}"
                 )
-            sub_cat_dict = {category: {WordType.CHARACTERS} for category in self.predictor.get_category_names()}
+            sub_cat_dict = {
+                category: {WordType.CHARACTERS: {WordType.CHARACTERS}}
+                for category in self.predictor.get_category_names()
+            }
         return MetaAnnotation(
             image_annotations=self.predictor.get_category_names()
             if isinstance(self.predictor, (ObjectDetector, PdfMiner))

deepdoctection/pipe/transform.py

@@ -22,9 +22,9 @@ Transform style pipeline components.
 from __future__ import annotations
 
 from .. import DetectionResult
-from ..datapoint.image import Image
+from ..datapoint.image import Image, MetaAnnotation
 from ..extern.base import ImageTransformer
-from .base import MetaAnnotation, PipelineComponent
+from .base import PipelineComponent
 from .registry import pipeline_component_registry
 
 
@@ -83,8 +83,6 @@ class SimpleTransformService(PipelineComponent):
             for detect_result in output_detect_results:
                 ann = dp.get_annotation(annotation_ids=detect_result.uuid)[0]
                 transformed_ann_id = self.dp_manager.set_image_annotation(detect_result)
-                if transformed_ann_id is None:
-                    print("here")
                 transformed_ann = self.dp_manager.datapoint.get_annotation(annotation_ids=transformed_ann_id)[0]
 
                 for key, sub_ann in ann.sub_categories.items():

deepdoctection/utils/file_utils.py

@@ -18,6 +18,7 @@ from types import ModuleType
 from typing import Any, Union, no_type_check
 
 import importlib_metadata
+import numpy as np
 from packaging import version
 
 from .error import DependencyError
@@ -249,6 +250,39 @@ def get_distance_requirement() -> Requirement:
     return "distance", distance_available(), _DISTANCE_ERR_MSG
 
 
+_NUMPY_V1_ERR_MSG = "numpy v1 must be installed."
+
+
+def numpy_v1_available() -> bool:
+    """
+    Check if the installed NumPy version is version 1.
+
+    This helper function determines whether the currently installed version
+    of NumPy is version 1 by inspecting its major version number.
+
+    Returns:
+        True if the installed NumPy version is 1, otherwise False
+    """
+    major_version = np.__version__.split('.', maxsplit=1)[0]
+    print(f"major version: {major_version}")
+    if major_version in (1, "1"):
+        return True
+    return False
+
+
+def get_numpy_v1_requirement() -> Requirement:
+    """
+    Retrieves the requirement details for numpy version 1.
+
+    Returns:
+        A tuple containing three elements:
+            - The requirement name for numpy version 1.
+            - A Boolean value indicating whether numpy version 1 is available.
+            - An error message in case numpy version 1 is not available.
+    """
+    return "numpy v1", numpy_v1_available(), _NUMPY_V1_ERR_MSG
+
+
 # Transformers
 _TRANSFORMERS_AVAILABLE = importlib.util.find_spec("transformers") is not None
 _TRANSFORMERS_ERR_MSG = f"transformers must be installed. {_GENERIC_ERR_MSG}"

deepdoctection/utils/types.py

@@ -70,7 +70,6 @@ AnnotationDict: TypeAlias = dict[str, Any]
 ImageDict: TypeAlias = dict[str, Any]
 
 # We use these types for output types of the Page object
-Text_: TypeAlias = dict[str, Any]
 HTML: TypeAlias = str
 csv: TypeAlias = list[list[str]]
 Chunks: TypeAlias = list[tuple[str, str, int, str, str, str, str]]

{deepdoctection-0.43.6.dist-info → deepdoctection-0.44.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deepdoctection
-Version: 0.43.6
+Version: 0.44.1
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -27,7 +27,7 @@ Requires-Dist: networkx>=2.7.1
 Requires-Dist: numpy<2.0,>=1.21
 Requires-Dist: packaging>=20.0
 Requires-Dist: Pillow>=10.0.0
-Requires-Dist: pypdf>=3.16.0
+Requires-Dist: pypdf>=6.0.0
 Requires-Dist: pypdfium2>=4.30.0
 Requires-Dist: pyyaml>=6.0.1
 Requires-Dist: pyzmq>=16
@@ -46,7 +46,7 @@ Requires-Dist: networkx>=2.7.1; extra == "tf"
 Requires-Dist: numpy<2.0,>=1.21; extra == "tf"
 Requires-Dist: packaging>=20.0; extra == "tf"
 Requires-Dist: Pillow>=10.0.0; extra == "tf"
-Requires-Dist: pypdf>=3.16.0; extra == "tf"
+Requires-Dist: pypdf>=6.0.0; extra == "tf"
 Requires-Dist: pypdfium2>=4.30.0; extra == "tf"
 Requires-Dist: pyyaml>=6.0.1; extra == "tf"
 Requires-Dist: pyzmq>=16; extra == "tf"
@@ -78,7 +78,7 @@ Requires-Dist: networkx>=2.7.1; extra == "pt"
 Requires-Dist: numpy<2.0,>=1.21; extra == "pt"
 Requires-Dist: packaging>=20.0; extra == "pt"
 Requires-Dist: Pillow>=10.0.0; extra == "pt"
-Requires-Dist: pypdf>=3.16.0; extra == "pt"
+Requires-Dist: pypdf>=6.0.0; extra == "pt"
 Requires-Dist: pypdfium2>=4.30.0; extra == "pt"
 Requires-Dist: pyyaml>=6.0.1; extra == "pt"
 Requires-Dist: pyzmq>=16; extra == "pt"