deepdoctection 0.30__tar.gz → 0.31__tar.gz

{deepdoctection-0.30 → deepdoctection-0.31}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: deepdoctection
-Version: 0.30
+Version: 0.31
 Summary: Repository for Document AI
 Home-page: https://github.com/deepdoctection/deepdoctection
 Author: Dr. Janis Meyer
@@ -17,9 +17,9 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: catalogue==2.0.7
+Requires-Dist: catalogue==2.0.10
 Requires-Dist: huggingface_hub>=0.12.0
-Requires-Dist: importlib-metadata>=4.11.2
+Requires-Dist: importlib-metadata>=5.0.0
 Requires-Dist: jsonlines==3.1.0
 Requires-Dist: mock==4.0.3
 Requires-Dist: networkx>=2.7.1
@@ -27,15 +27,15 @@ Requires-Dist: numpy>=1.21
 Requires-Dist: packaging>=20.0
 Requires-Dist: Pillow>=10.0.0
 Requires-Dist: pypdf>=3.16.0
-Requires-Dist: pyyaml==6.0
+Requires-Dist: pyyaml>=6.0.1
 Requires-Dist: pyzmq>=16
 Requires-Dist: termcolor>=1.1
 Requires-Dist: tabulate>=0.7.7
 Requires-Dist: tqdm==4.64.0
 Provides-Extra: tf
-Requires-Dist: catalogue==2.0.7; extra == "tf"
+Requires-Dist: catalogue==2.0.10; extra == "tf"
 Requires-Dist: huggingface_hub>=0.12.0; extra == "tf"
-Requires-Dist: importlib-metadata>=4.11.2; extra == "tf"
+Requires-Dist: importlib-metadata>=5.0.0; extra == "tf"
 Requires-Dist: jsonlines==3.1.0; extra == "tf"
 Requires-Dist: mock==4.0.3; extra == "tf"
 Requires-Dist: networkx>=2.7.1; extra == "tf"
@@ -43,12 +43,12 @@ Requires-Dist: numpy>=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: pyyaml==6.0; extra == "tf"
+Requires-Dist: pyyaml>=6.0.1; extra == "tf"
 Requires-Dist: pyzmq>=16; extra == "tf"
 Requires-Dist: termcolor>=1.1; extra == "tf"
 Requires-Dist: tabulate>=0.7.7; extra == "tf"
 Requires-Dist: tqdm==4.64.0; extra == "tf"
-Requires-Dist: tensorpack; extra == "tf"
+Requires-Dist: tensorpack==0.11; extra == "tf"
 Requires-Dist: protobuf==3.20.1; extra == "tf"
 Requires-Dist: tensorflow-addons>=0.17.1; extra == "tf"
 Requires-Dist: tf2onnx>=1.9.2; extra == "tf"
@@ -56,15 +56,15 @@ Requires-Dist: python-doctr==0.7.0; extra == "tf"
 Requires-Dist: pycocotools>=2.0.2; extra == "tf"
 Requires-Dist: boto3; extra == "tf"
 Requires-Dist: pdfplumber>=0.7.1; extra == "tf"
-Requires-Dist: fasttext; extra == "tf"
-Requires-Dist: jdeskew; extra == "tf"
+Requires-Dist: fasttext==0.9.2; extra == "tf"
+Requires-Dist: jdeskew>=0.2.2; extra == "tf"
 Requires-Dist: apted==1.0.3; extra == "tf"
 Requires-Dist: distance==0.1.3; extra == "tf"
 Requires-Dist: lxml>=4.9.1; extra == "tf"
 Provides-Extra: pt
-Requires-Dist: catalogue==2.0.7; extra == "pt"
+Requires-Dist: catalogue==2.0.10; extra == "pt"
 Requires-Dist: huggingface_hub>=0.12.0; extra == "pt"
-Requires-Dist: importlib-metadata>=4.11.2; extra == "pt"
+Requires-Dist: importlib-metadata>=5.0.0; extra == "pt"
 Requires-Dist: jsonlines==3.1.0; extra == "pt"
 Requires-Dist: mock==4.0.3; extra == "pt"
 Requires-Dist: networkx>=2.7.1; extra == "pt"
@@ -72,31 +72,31 @@ Requires-Dist: numpy>=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: pyyaml==6.0; extra == "pt"
+Requires-Dist: pyyaml>=6.0.1; extra == "pt"
 Requires-Dist: pyzmq>=16; extra == "pt"
 Requires-Dist: termcolor>=1.1; extra == "pt"
 Requires-Dist: tabulate>=0.7.7; extra == "pt"
 Requires-Dist: tqdm==4.64.0; extra == "pt"
-Requires-Dist: timm; extra == "pt"
+Requires-Dist: timm>=0.9.16; extra == "pt"
 Requires-Dist: transformers>=4.36.0; extra == "pt"
-Requires-Dist: accelerate; extra == "pt"
+Requires-Dist: accelerate>=0.29.1; extra == "pt"
 Requires-Dist: python-doctr==0.7.0; extra == "pt"
 Requires-Dist: boto3; extra == "pt"
 Requires-Dist: pdfplumber>=0.7.1; extra == "pt"
-Requires-Dist: fasttext; extra == "pt"
-Requires-Dist: jdeskew; extra == "pt"
+Requires-Dist: fasttext==0.9.2; extra == "pt"
+Requires-Dist: jdeskew>=0.2.2; extra == "pt"
 Requires-Dist: apted==1.0.3; extra == "pt"
 Requires-Dist: distance==0.1.3; extra == "pt"
 Requires-Dist: lxml>=4.9.1; extra == "pt"
 Provides-Extra: docs
-Requires-Dist: tensorpack; extra == "docs"
+Requires-Dist: tensorpack==0.11; extra == "docs"
 Requires-Dist: boto3; extra == "docs"
 Requires-Dist: transformers>=4.36.0; extra == "docs"
-Requires-Dist: accelerate; extra == "docs"
+Requires-Dist: accelerate>=0.29.1; extra == "docs"
 Requires-Dist: pdfplumber>=0.7.1; extra == "docs"
 Requires-Dist: lxml>=4.9.1; extra == "docs"
-Requires-Dist: lxml-stubs; extra == "docs"
-Requires-Dist: jdeskew; extra == "docs"
+Requires-Dist: lxml-stubs>=0.5.1; extra == "docs"
+Requires-Dist: jdeskew>=0.2.2; extra == "docs"
 Requires-Dist: jinja2==3.0.3; extra == "docs"
 Requires-Dist: mkdocs-material; extra == "docs"
 Requires-Dist: mkdocstrings-python; extra == "docs"
@@ -105,47 +105,20 @@ Provides-Extra: dev
 Requires-Dist: python-dotenv==1.0.0; extra == "dev"
 Requires-Dist: click; extra == "dev"
 Requires-Dist: black==23.7.0; extra == "dev"
-Requires-Dist: isort; extra == "dev"
+Requires-Dist: isort==5.13.2; extra == "dev"
 Requires-Dist: pylint==2.17.4; extra == "dev"
 Requires-Dist: mypy==1.4.1; extra == "dev"
 Requires-Dist: wandb; extra == "dev"
-Requires-Dist: types-PyYAML; extra == "dev"
-Requires-Dist: types-termcolor==1.1.3; extra == "dev"
-Requires-Dist: types-tabulate; extra == "dev"
-Requires-Dist: types-tqdm; extra == "dev"
-Requires-Dist: lxml-stubs; extra == "dev"
-Requires-Dist: types-Pillow; extra == "dev"
-Requires-Dist: types-urllib3; extra == "dev"
+Requires-Dist: types-PyYAML>=6.0.12.12; extra == "dev"
+Requires-Dist: types-termcolor>=1.1.3; extra == "dev"
+Requires-Dist: types-tabulate>=0.9.0.3; extra == "dev"
+Requires-Dist: types-tqdm>=4.66.0.5; extra == "dev"
+Requires-Dist: lxml-stubs>=0.5.1; extra == "dev"
+Requires-Dist: types-Pillow>=10.2.0.20240406; extra == "dev"
+Requires-Dist: types-urllib3>=1.26.25.14; extra == "dev"
 Provides-Extra: test
-Requires-Dist: pytest; extra == "test"
+Requires-Dist: pytest==8.0.2; extra == "test"
 Requires-Dist: pytest-cov; extra == "test"
-Provides-Extra: hf
-Requires-Dist: catalogue==2.0.7; extra == "hf"
-Requires-Dist: huggingface_hub>=0.12.0; extra == "hf"
-Requires-Dist: importlib-metadata>=4.11.2; extra == "hf"
-Requires-Dist: jsonlines==3.1.0; extra == "hf"
-Requires-Dist: mock==4.0.3; extra == "hf"
-Requires-Dist: networkx>=2.7.1; extra == "hf"
-Requires-Dist: numpy>=1.21; extra == "hf"
-Requires-Dist: packaging>=20.0; extra == "hf"
-Requires-Dist: Pillow>=10.0.0; extra == "hf"
-Requires-Dist: pypdf>=3.16.0; extra == "hf"
-Requires-Dist: pyyaml==6.0; extra == "hf"
-Requires-Dist: pyzmq>=16; extra == "hf"
-Requires-Dist: termcolor>=1.1; extra == "hf"
-Requires-Dist: tabulate>=0.7.7; extra == "hf"
-Requires-Dist: tqdm==4.64.0; extra == "hf"
-Requires-Dist: timm; extra == "hf"
-Requires-Dist: transformers>=4.36.0; extra == "hf"
-Requires-Dist: accelerate; extra == "hf"
-Requires-Dist: python-doctr==0.7.0; extra == "hf"
-Requires-Dist: boto3; extra == "hf"
-Requires-Dist: pdfplumber>=0.7.1; extra == "hf"
-Requires-Dist: fasttext; extra == "hf"
-Requires-Dist: jdeskew; extra == "hf"
-Requires-Dist: apted==1.0.3; extra == "hf"
-Requires-Dist: distance==0.1.3; extra == "hf"
-Requires-Dist: lxml>=4.9.1; extra == "hf"
 
 
 <p align="center">
@@ -191,7 +164,9 @@ pipelines. Its core function does not depend on any specific deep learning libra
    Check this [notebook](https://github.com/deepdoctection/notebooks/blob/main/Analyzer_Configuration.ipynb) or the 
    [docs](https://deepdoctection.readthedocs.io/en/latest/tutorials/analyzer_configuration_notebook/) for more infos.
  - Document layout analysis and table recognition now runs with Torchscript (CPU) as well and Detectron2 is 
-   not required anymore for basic inference. 
+   not required anymore for basic inference.
+ - [**new**] More angle predictors for determining the rotation of a document based on Tesseract and DocTr 
+   (not contained in the built-in Analyzer).
 
 **deep**doctection provides on top of that methods for pre-processing inputs to models like cropping or resizing and to 
 post-process results, like validating duplicate outputs, relating words to detected layout segments or ordering words 

{deepdoctection-0.30 → deepdoctection-0.31}/README.md

@@ -42,7 +42,9 @@ pipelines. Its core function does not depend on any specific deep learning libra
    Check this [notebook](https://github.com/deepdoctection/notebooks/blob/main/Analyzer_Configuration.ipynb) or the 
    [docs](https://deepdoctection.readthedocs.io/en/latest/tutorials/analyzer_configuration_notebook/) for more infos.
  - Document layout analysis and table recognition now runs with Torchscript (CPU) as well and Detectron2 is 
-   not required anymore for basic inference. 
+   not required anymore for basic inference.
+ - [**new**] More angle predictors for determining the rotation of a document based on Tesseract and DocTr 
+   (not contained in the built-in Analyzer).
 
 **deep**doctection provides on top of that methods for pre-processing inputs to models like cropping or resizing and to 
 post-process results, like validating duplicate outputs, relating words to detected layout segments or ordering words 

{deepdoctection-0.30 → deepdoctection-0.31}/deepdoctection/__init__.py

@@ -27,7 +27,7 @@ from .utils.logger import logger
 
 # pylint: enable=wrong-import-position
 
-__version__ = 0.30
+__version__ = 0.31
 
 _IMPORT_STRUCTURE = {
     "analyzer": [
@@ -179,6 +179,7 @@ _IMPORT_STRUCTURE = {
         "Jdeskewer",
         "DoctrTextlineDetector",
         "DoctrTextRecognizer",
+        "DocTrRotationTransformer",
         "FasttextLangDetector",
         "HFDetrDerivedDetector",
         "HFLayoutLmTokenClassifierBase",
@@ -194,6 +195,7 @@ _IMPORT_STRUCTURE = {
         "ModelDownloadManager",
         "PdfPlumberTextDetector",
         "TesseractOcrDetector",
+        "TesseractRotationTransformer",
         "TextractOcrDetector",
         "TPFrcnnDetector",
     ],
@@ -279,7 +281,7 @@ _IMPORT_STRUCTURE = {
         "PubtablesSegmentationService",
         "SegmentationResult",
         "TextExtractionService",
-        "SimpleTransformPipelineComponent",
+        "SimpleTransformService",
     ],
     "train": [
         "D2Trainer",

{deepdoctection-0.30 → deepdoctection-0.31}/deepdoctection/analyzer/dd.py

@@ -113,11 +113,12 @@ def config_sanity_checks(cfg: AttrDict) -> None:
     """Some config sanity checks"""
     if cfg.USE_PDF_MINER and cfg.USE_OCR and cfg.OCR.USE_DOCTR:
         raise ValueError("Configuration USE_PDF_MINER= True and USE_OCR=True and USE_DOCTR=True is not allowed")
-    if cfg.OCR.USE_TESSERACT + cfg.OCR.USE_DOCTR + cfg.OCR.USE_TEXTRACT != 1:
-        raise ValueError(
-            "Choose either OCR.USE_TESSERACT=True or OCR.USE_DOCTR=True or OCR.USE_TEXTRACT=True and set the other two "
-            "to False. Only one OCR system can be activated."
-        )
+    if cfg.USE_OCR:
+        if cfg.OCR.USE_TESSERACT + cfg.OCR.USE_DOCTR + cfg.OCR.USE_TEXTRACT != 1:
+            raise ValueError(
+                "Choose either OCR.USE_TESSERACT=True or OCR.USE_DOCTR=True or OCR.USE_TEXTRACT=True "
+                "and set the other two to False. Only one OCR system can be activated."
+            )
 
 
 def build_detector(

{deepdoctection-0.30 → deepdoctection-0.31}/deepdoctection/dataflow/base.py

@@ -17,25 +17,6 @@ from typing import Any, Iterator, no_type_check
 from ..utils.utils import get_rng
 
 
-class DataFlowTerminated(BaseException):
-    """
-    An exception indicating that the DataFlow is unable to produce any more
-    data, i.e. something wrong happened so that calling `__iter__`
-    cannot give a valid iterator anymore.
-    In most DataFlow this will never be raised.
-    """
-
-
-class DataFlowResetStateNotCalled(BaseException):
-    """
-    An exception indicating that `reset_state()` has not been called before starting
-    iteration.
-    """
-
-    def __init__(self) -> None:
-        super().__init__("Iterating a dataflow requires .reset_state() to be called first")
-
-
 class DataFlowReentrantGuard:
     """
     A tool to enforce non-reentrancy.

{deepdoctection-0.30 → deepdoctection-0.31}/deepdoctection/dataflow/custom.py

@@ -25,10 +25,11 @@ from typing import Any, Callable, Iterable, Iterator, List, Optional
 
 import numpy as np
 
+from ..utils.error import DataFlowResetStateNotCalledError
 from ..utils.logger import LoggingRecord, logger
 from ..utils.tqdm import get_tqdm
 from ..utils.utils import get_rng
-from .base import DataFlow, DataFlowReentrantGuard, DataFlowResetStateNotCalled, ProxyDataFlow
+from .base import DataFlow, DataFlowReentrantGuard, ProxyDataFlow
 from .serialize import DataFromIterable, DataFromList
 
 __all__ = ["CacheData", "CustomDataFromList", "CustomDataFromIterable"]
@@ -65,7 +66,7 @@ class CacheData(ProxyDataFlow):
 
     def __iter__(self) -> Iterator[Any]:
         if self._guard is None:
-            raise DataFlowResetStateNotCalled()
+            raise DataFlowResetStateNotCalledError()
 
         with self._guard:
             if self.buffer:
@@ -139,7 +140,7 @@ class CustomDataFromList(DataFromList):
 
     def __iter__(self) -> Iterator[Any]:
         if self.rng is None:
-            raise DataFlowResetStateNotCalled()
+            raise DataFlowResetStateNotCalledError()
         if self.rebalance_func is not None:
             lst_tmp = self.rebalance_func(self.lst)
             logger.info(LoggingRecord(f"CustomDataFromList: subset size after re-balancing: {len(lst_tmp)}"))

{deepdoctection-0.30 → deepdoctection-0.31}/deepdoctection/dataflow/custom_serialize.py

@@ -27,13 +27,16 @@ from pathlib import Path
 from typing import DefaultDict, Dict, List, Optional, Sequence, Union
 
 from jsonlines import Reader, Writer
+from tabulate import tabulate
+from termcolor import colored
 
 from ..utils.context import timed_operation
 from ..utils.detection_types import JsonDict, Pathlike
+from ..utils.error import FileExtensionError
 from ..utils.identifier import get_uuid_from_str
 from ..utils.pdf_utils import PDFStreamer
 from ..utils.tqdm import get_tqdm
-from ..utils.utils import FileExtensionError, is_file_extension
+from ..utils.utils import is_file_extension
 from .base import DataFlow
 from .common import FlattenData, JoinData, MapData
 from .custom import CacheData, CustomDataFromIterable, CustomDataFromList
@@ -223,7 +226,7 @@ class SerializerFiles:
         """
         Not implemented
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
 
 class CocoParser:
@@ -283,8 +286,14 @@ class CocoParser:
         """
         Print information about the annotation file.
         """
+        rows = []
         for key, value in self.dataset["info"].items():
-            print(f"{key}: {value}")
+            row = [key, value]
+            rows.append(row)
+
+        header = ["key", "value"]
+        table = tabulate(rows, headers=header, tablefmt="fancy_grid", stralign="left", numalign="left")
+        print(colored(table, "cyan"))
 
     def get_ann_ids(
         self,
@@ -499,7 +508,7 @@ class SerializerCoco:
         """
         Not implemented
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
 
 class SerializerPdfDoc:
@@ -547,7 +556,7 @@ class SerializerPdfDoc:
         """
         Not implemented
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
     @staticmethod
     def split(path: Pathlike, path_target: Optional[Pathlike] = None, max_datapoint: Optional[int] = None) -> None:

{deepdoctection-0.30 → deepdoctection-0.31}/deepdoctection/dataflow/parallel_map.py

@@ -28,8 +28,9 @@ from typing import Any, Callable, Iterator, List, no_type_check
 import zmq
 
 from ..utils.concurrency import StoppableThread, enable_death_signal, start_proc_mask_signal
+from ..utils.error import DataFlowTerminatedError
 from ..utils.logger import LoggingRecord, logger
-from .base import DataFlow, DataFlowReentrantGuard, DataFlowTerminated, ProxyDataFlow
+from .base import DataFlow, DataFlowReentrantGuard, ProxyDataFlow
 from .common import RepeatedData
 from .serialize import PickleSerializer
 
@@ -49,14 +50,14 @@ def _zmq_catch_error(name):
         yield
     except zmq.ContextTerminated as exc:
         logger.info(LoggingRecord(f"_zmq_catch_error: [{name}] Context terminated."))
-        raise DataFlowTerminated() from exc
+        raise DataFlowTerminatedError() from exc
     except zmq.ZMQError as exc:
         if exc.errno == errno.ENOTSOCK:  # socket closed
             logger.info(LoggingRecord(f"_zmq_catch_error: [{name}]  Socket closed."))
-            raise DataFlowTerminated() from exc
-        raise ValueError from exc
+            raise DataFlowTerminatedError() from exc
+        raise ValueError() from exc
     except Exception as exc:
-        raise ValueError from exc
+        raise ValueError() from exc
 
 
 @no_type_check
@@ -78,8 +79,8 @@ def _get_pipe_name(name):
 class _ParallelMapData(ProxyDataFlow, ABC):
     def __init__(self, df: DataFlow, buffer_size: int, strict: bool = False) -> None:
         super().__init__(df)
-        if not buffer_size:
-            raise ValueError("buffer_size must be a positive number")
+        if buffer_size <= 0:
+            raise ValueError(f"buffer_size must be a positive number, got {buffer_size}")
         self._buffer_size = buffer_size
         self._buffer_occupancy = 0  # actual #elements in buffer, only useful in strict mode
         self._strict = strict
@@ -95,12 +96,12 @@ class _ParallelMapData(ProxyDataFlow, ABC):
     @no_type_check
     @abstractmethod
     def _recv(self):
-        raise NotImplementedError
+        raise NotImplementedError()
 
     @no_type_check
     @abstractmethod
     def _send(self, dp: Any):
-        raise NotImplementedError
+        raise NotImplementedError()
 
     @no_type_check
     def _recv_filter_none(self):
@@ -398,8 +399,8 @@ class MultiProcessMapData(_ParallelMapData, _MultiProcessZMQDataFlow):
 
         _ParallelMapData.__init__(self, df, buffer_size, strict)
         _MultiProcessZMQDataFlow.__init__(self)
-        if not num_proc:
-            raise ValueError("num_proc must be a positive number")
+        if num_proc <= 0:
+            raise ValueError(f"num_proc must be a positive number, got {num_proc}")
         self.num_proc = num_proc
         self.map_func = map_func
         self._strict = strict

{deepdoctection-0.30 → deepdoctection-0.31}/deepdoctection/dataflow/serialize.py

@@ -16,7 +16,8 @@ from typing import Any, Iterable, Iterator, List, Optional, Tuple, Union
 
 import numpy as np
 
-from .base import DataFlow, DataFlowResetStateNotCalled, RNGDataFlow
+from ..utils.error import DataFlowResetStateNotCalledError
+from .base import DataFlow, RNGDataFlow
 
 
 class DataFromList(RNGDataFlow):
@@ -44,7 +45,7 @@ class DataFromList(RNGDataFlow):
                 for k in idxs:
                     yield self.lst[k]
             else:
-                raise DataFlowResetStateNotCalled()
+                raise DataFlowResetStateNotCalledError()
 
 
 class DataFromIterable(DataFlow):
@@ -63,7 +64,7 @@ class DataFromIterable(DataFlow):
 
     def __len__(self) -> int:
         if self._len is None:
-            raise NotImplementedError
+            raise NotImplementedError()
         return self._len
 
     def __iter__(self) -> Iterator[Any]:
@@ -107,7 +108,7 @@ class FakeData(RNGDataFlow):
 
     def __iter__(self) -> Iterator[Any]:
         if self.rng is None:
-            raise DataFlowResetStateNotCalled()
+            raise DataFlowResetStateNotCalledError()
         if self.random:
             for _ in range(self._size):
                 val = []

{deepdoctection-0.30 → deepdoctection-0.31}/deepdoctection/datapoint/annotation.py

@@ -24,6 +24,7 @@ from dataclasses import dataclass, field
 from typing import Any, Dict, List, Optional, Union, no_type_check
 
 from ..utils.detection_types import JsonDict
+from ..utils.error import AnnotationError, UUIDError
 from ..utils.identifier import get_uuid, is_uuid_like
 from ..utils.logger import LoggingRecord, logger
 from ..utils.settings import DefaultType, ObjectTypes, SummaryType, TypeOrStr, get_type
@@ -36,7 +37,16 @@ def ann_from_dict(cls, **kwargs):
     """
     A factory function to create subclasses of annotations from a given dict
     """
-    ann = cls(kwargs.get("external_id"), kwargs.get("category_name"), kwargs.get("category_id"), kwargs.get("score"))
+    _init_kwargs = {
+        "external_id": kwargs.get("external_id"),
+        "category_name": kwargs.get("category_name"),
+        "category_id": kwargs.get("category_id"),
+        "score": kwargs.get("score"),
+        "service_id": kwargs.get("service_id"),
+        "model_id": kwargs.get("model_id"),
+        "session_id": kwargs.get("session_id"),
+    }
+    ann = cls(**_init_kwargs)
     ann.active = kwargs.get("active")
     ann._annotation_id = kwargs.get("_annotation_id")  # pylint: disable=W0212
     if isinstance(kwargs.get("sub_categories"), dict):
@@ -74,11 +84,17 @@ class Annotation(ABC):
     id will not depend on the defining attributes.
 
     `_annotation_id`: Unique id for annotations. Will always be given as string representation of a md5-hash.
+    `service_id`: Service that generated the annotation. This will be the name of a pipeline component
+    `model_id`: Model that generated the annotation. This will be the name of particular model
+    `session_id`: Session id for the annotation. This will be the id of the session in which the annotation was created.
     """
 
     active: bool = field(default=True, init=False, repr=True)
     external_id: Optional[Union[str, int]] = field(default=None, init=True, repr=False)
     _annotation_id: Optional[str] = field(default=None, init=False, repr=True)
+    service_id: Optional[str] = field(default=None)
+    model_id: Optional[str] = field(default=None)
+    session_id: Optional[str] = field(default=None)
 
     def __post_init__(self) -> None:
         """
@@ -101,7 +117,7 @@ class Annotation(ABC):
         """
         if self._annotation_id:
             return self._annotation_id
-        raise ValueError("Dump annotation first or pass external_id to create an annotation id")
+        raise AnnotationError("Dump annotation first or pass external_id to create an annotation id")
 
     @annotation_id.setter
     def annotation_id(self, input_id: str) -> None:
@@ -109,13 +125,13 @@ class Annotation(ABC):
         annotation_id setter
         """
         if self._annotation_id is not None:
-            raise AssertionError("Annotation_id already defined and cannot be reset")
+            raise AnnotationError("Annotation_id already defined and cannot be reset")
         if is_uuid_like(input_id):
             self._annotation_id = input_id
         elif isinstance(input_id, property):
             pass
         else:
-            raise ValueError("Annotation_id must be uuid3 string")
+            raise AnnotationError("Annotation_id must be uuid3 string")
 
     @abstractmethod
     def get_defining_attributes(self) -> List[str]:
@@ -126,13 +142,13 @@ class Annotation(ABC):
 
         :return: A list of attributes.
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
     def _assert_attributes_have_str(self, state_id: bool = False) -> None:
         defining_attributes = self.get_state_attributes() if state_id else self.get_defining_attributes()
         for attr in defining_attributes:
             if not hasattr(eval("self." + attr), "__str__"):  # pylint: disable=W0123
-                raise AttributeError(f"Attribute {attr} must have __str__ method")
+                raise AnnotationError(f"Attribute {attr} must have __str__ method")
 
     @staticmethod
     def set_annotation_id(annotation: "CategoryAnnotation", *container_id_context: Optional[str]) -> str:
@@ -179,7 +195,7 @@ class Annotation(ABC):
 
         :return: Annotation instance
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
     @staticmethod
     @abstractmethod
@@ -189,7 +205,7 @@ class Annotation(ABC):
 
         :return: A list of attributes.
         """
-        raise NotImplementedError
+        raise NotImplementedError()
 
     @property
     def state_id(self) -> str:
@@ -290,7 +306,12 @@ class CategoryAnnotation(Annotation):
         """
 
         if sub_category_name in self.sub_categories:
-            raise KeyError(f"{sub_category_name} as sub category already defined for " f"{self.annotation_id}")
+            raise AnnotationError(
+                f"sub category {sub_category_name} already defined: "
+                f"annotation_id: {self.annotation_id}, "
+                f"category_name: {self.category_name}, "
+                f"category_id: {self.category_id}"
+            )
 
         if self._annotation_id is not None:
             if annotation._annotation_id is None:  # pylint: disable=W0212
@@ -333,7 +354,7 @@ class CategoryAnnotation(Annotation):
         :param annotation_id: An annotation id
         """
         if not is_uuid_like(annotation_id):
-            raise ValueError("Annotation_id must be uuid")
+            raise UUIDError("Annotation_id must be uuid")
 
         key_type = get_type(key)
         if key not in self.relationships:
@@ -436,14 +457,14 @@ class ImageAnnotation(CategoryAnnotation):
             box = self.bounding_box
         if box:
             return box
-        raise ValueError(f"bounding_box has not been initialized for {self.annotation_id}")
+        raise AnnotationError(f"bounding_box has not been initialized for {self.annotation_id}")
 
     def get_summary(self, key: ObjectTypes) -> CategoryAnnotation:
         """Get summary sub categories from `image`. Raises `ValueError` if `key` is not available"""
         if self.image:
             if self.image.summary:
                 return self.image.summary.get_sub_category(key)
-        raise ValueError(f"Summary does not exist for {self.annotation_id} and key: {key}")
+        raise AnnotationError(f"Summary does not exist for {self.annotation_id} and key: {key}")
 
 
 @dataclass

{deepdoctection-0.30 → deepdoctection-0.31}/deepdoctection/datapoint/box.py

@@ -28,6 +28,7 @@ import numpy.typing as npt
 from numpy import float32
 
 from ..utils.detection_types import ImageType
+from ..utils.error import BoundingBoxError
 from ..utils.file_utils import cocotools_available
 from ..utils.logger import LoggingRecord, logger
 
@@ -140,10 +141,6 @@ def iou(boxes1: npt.NDArray[float32], boxes2: npt.NDArray[float32]) -> npt.NDArr
     return np_iou(boxes1, boxes2)
 
 
-class BoundingBoxError(BaseException):
-    """Special exception only for `BoundingBox`"""
-
-
 @dataclass
 class BoundingBox:
     """

{deepdoctection-0.30 → deepdoctection-0.31}/deepdoctection/datapoint/convert.py

@@ -32,6 +32,7 @@ from pypdf import PdfReader
 
 from ..utils.detection_types import ImageType
 from ..utils.develop import deprecated
+from ..utils.error import DependencyError
 from ..utils.pdf_utils import pdf_to_np_array
 from ..utils.viz import viz_handler
 
@@ -121,7 +122,8 @@ def convert_pdf_bytes_to_np_array(pdf_bytes: bytes, dpi: Optional[int] = None) -
     """
     from pdf2image import convert_from_bytes  # type: ignore # pylint: disable=C0415, E0401
 
-    assert which("pdftoppm") is not None, "convert_pdf_bytes_to_np_array requires poppler to be installed"
+    if which("pdftoppm") is None:
+        raise DependencyError("convert_pdf_bytes_to_np_array requires poppler to be installed")
 
     with BytesIO(pdf_bytes) as pdf_file:
         pdf = PdfReader(pdf_file).pages[0]