docling 2.21.0__py3-none-any.whl → 2.23.0__py3-none-any.whl

docling/cli/main.py

@@ -234,6 +234,12 @@ def convert(
         Optional[Path],
         typer.Option(..., help="If provided, the location of the model artifacts."),
     ] = None,
+    enable_remote_services: Annotated[
+        bool,
+        typer.Option(
+            ..., help="Must be enabled when using models connecting to remote services."
+        ),
+    ] = False,
     abort_on_error: Annotated[
         bool,
         typer.Option(
@@ -380,6 +386,7 @@ def convert(
 
         accelerator_options = AcceleratorOptions(num_threads=num_threads, device=device)
         pipeline_options = PdfPipelineOptions(
+            enable_remote_services=enable_remote_services,
             accelerator_options=accelerator_options,
             do_ocr=ocr,
             ocr_options=ocr_options,

docling/datamodel/base_models.py

@@ -34,13 +34,14 @@ class InputFormat(str, Enum):
     DOCX = "docx"
     PPTX = "pptx"
     HTML = "html"
-    XML_PUBMED = "xml_pubmed"
     IMAGE = "image"
     PDF = "pdf"
     ASCIIDOC = "asciidoc"
     MD = "md"
+    CSV = "csv"
     XLSX = "xlsx"
     XML_USPTO = "xml_uspto"
+    XML_JATS = "xml_jats"
     JSON_DOCLING = "json_docling"
 
 
@@ -58,9 +59,10 @@ FormatToExtensions: Dict[InputFormat, List[str]] = {
     InputFormat.PDF: ["pdf"],
     InputFormat.MD: ["md"],
     InputFormat.HTML: ["html", "htm", "xhtml"],
-    InputFormat.XML_PUBMED: ["xml", "nxml"],
+    InputFormat.XML_JATS: ["xml", "nxml"],
     InputFormat.IMAGE: ["jpg", "jpeg", "png", "tif", "tiff", "bmp"],
     InputFormat.ASCIIDOC: ["adoc", "asciidoc", "asc"],
+    InputFormat.CSV: ["csv"],
     InputFormat.XLSX: ["xlsx"],
     InputFormat.XML_USPTO: ["xml", "txt"],
     InputFormat.JSON_DOCLING: ["json"],
@@ -77,7 +79,7 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
         "application/vnd.openxmlformats-officedocument.presentationml.presentation",
     ],
     InputFormat.HTML: ["text/html", "application/xhtml+xml"],
-    InputFormat.XML_PUBMED: ["application/xml"],
+    InputFormat.XML_JATS: ["application/xml"],
     InputFormat.IMAGE: [
         "image/png",
         "image/jpeg",
@@ -88,6 +90,7 @@ FormatToMimeType: Dict[InputFormat, List[str]] = {
     InputFormat.PDF: ["application/pdf"],
     InputFormat.ASCIIDOC: ["text/asciidoc"],
     InputFormat.MD: ["text/markdown", "text/x-markdown"],
+    InputFormat.CSV: ["text/csv"],
     InputFormat.XLSX: [
         "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
     ],

docling/datamodel/document.py

@@ -1,3 +1,4 @@
+import csv
 import logging
 import re
 from enum import Enum
@@ -296,6 +297,7 @@ class _DocumentConversionInput(BaseModel):
                 mime = _DocumentConversionInput._mime_from_extension(ext)
 
         mime = mime or _DocumentConversionInput._detect_html_xhtml(content)
+        mime = mime or _DocumentConversionInput._detect_csv(content)
         mime = mime or "text/plain"
         formats = MimeTypeToFormat.get(mime, [])
         if formats:
@@ -331,11 +333,11 @@ class _DocumentConversionInput(BaseModel):
                 ):
                     input_format = InputFormat.XML_USPTO
 
-                if (
-                    InputFormat.XML_PUBMED in formats
-                    and "/NLM//DTD JATS" in xml_doctype
+                if InputFormat.XML_JATS in formats and (
+                    "JATS-journalpublishing" in xml_doctype
+                    or "JATS-archive" in xml_doctype
                 ):
-                    input_format = InputFormat.XML_PUBMED
+                    input_format = InputFormat.XML_JATS
 
         elif mime == "text/plain":
             if InputFormat.XML_USPTO in formats and content_str.startswith("PATN\r\n"):
@@ -352,6 +354,8 @@ class _DocumentConversionInput(BaseModel):
             mime = FormatToMimeType[InputFormat.HTML][0]
         elif ext in FormatToExtensions[InputFormat.MD]:
             mime = FormatToMimeType[InputFormat.MD][0]
+        elif ext in FormatToExtensions[InputFormat.CSV]:
+            mime = FormatToMimeType[InputFormat.CSV][0]
         elif ext in FormatToExtensions[InputFormat.JSON_DOCLING]:
             mime = FormatToMimeType[InputFormat.JSON_DOCLING][0]
         elif ext in FormatToExtensions[InputFormat.PDF]:
@@ -392,3 +396,32 @@ class _DocumentConversionInput(BaseModel):
             return "application/xml"
 
         return None
+
+    @staticmethod
+    def _detect_csv(
+        content: bytes,
+    ) -> Optional[Literal["text/csv"]]:
+        """Guess the mime type of a CSV file from its content.
+
+        Args:
+            content: A short piece of a document from its beginning.
+
+        Returns:
+            The mime type of a CSV file, or None if the content does
+              not match any of the format.
+        """
+        content_str = content.decode("ascii", errors="ignore").strip()
+
+        # Ensure there's at least one newline (CSV is usually multi-line)
+        if "\n" not in content_str:
+            return None
+
+        # Use csv.Sniffer to detect CSV characteristics
+        try:
+            dialect = csv.Sniffer().sniff(content_str)
+            if dialect.delimiter in {",", ";", "\t", "|"}:  # Common delimiters
+                return "text/csv"
+        except csv.Error:
+            return None
+
+        return None

docling/datamodel/pipeline_options.py

@@ -1,11 +1,26 @@
 import logging
 import os
+import re
+import warnings
 from enum import Enum
 from pathlib import Path
 from typing import Annotated, Any, Dict, List, Literal, Optional, Union
 
-from pydantic import AnyUrl, BaseModel, ConfigDict, Field, model_validator
-from pydantic_settings import BaseSettings, SettingsConfigDict
+from pydantic import (
+    AnyUrl,
+    BaseModel,
+    ConfigDict,
+    Field,
+    field_validator,
+    model_validator,
+    validator,
+)
+from pydantic_settings import (
+    BaseSettings,
+    PydanticBaseSettingsSource,
+    SettingsConfigDict,
+)
+from typing_extensions import deprecated
 
 _log = logging.getLogger(__name__)
 
@@ -25,7 +40,18 @@ class AcceleratorOptions(BaseSettings):
     )
 
     num_threads: int = 4
-    device: AcceleratorDevice = AcceleratorDevice.AUTO
+    device: Union[str, AcceleratorDevice] = "auto"
+
+    @field_validator("device")
+    def validate_device(cls, value):
+        # "auto", "cpu", "cuda", "mps", or "cuda:N"
+        if value in {d.value for d in AcceleratorDevice} or re.match(
+            r"^cuda(:\d+)?$", value
+        ):
+            return value
+        raise ValueError(
+            "Invalid device option. Use 'auto', 'cpu', 'mps', 'cuda', or 'cuda:N'."
+        )
 
     @model_validator(mode="before")
     @classmethod
@@ -41,7 +67,6 @@ class AcceleratorOptions(BaseSettings):
         """
         if isinstance(data, dict):
             input_num_threads = data.get("num_threads")
-
             # Check if to set the num_threads from the alternative envvar
             if input_num_threads is None:
                 docling_num_threads = os.getenv("DOCLING_NUM_THREADS")
@@ -257,6 +282,7 @@ class PipelineOptions(BaseModel):
     )
     document_timeout: Optional[float] = None
     accelerator_options: AcceleratorOptions = AcceleratorOptions()
+    enable_remote_services: bool = False
 
 
 class PdfPipelineOptions(PipelineOptions):

docling/datamodel/settings.py

@@ -1,6 +1,6 @@
 import sys
 from pathlib import Path
-from typing import Annotated, Tuple
+from typing import Annotated, Optional, Tuple
 
 from pydantic import BaseModel, PlainValidator
 from pydantic_settings import BaseSettings, SettingsConfigDict
@@ -62,6 +62,7 @@ class AppSettings(BaseSettings):
     debug: DebugSettings
 
     cache_dir: Path = Path.home() / ".cache" / "docling"
+    artifacts_path: Optional[Path] = None
 
 
 settings = AppSettings(perf=BatchConcurrencySettings(), debug=DebugSettings())

docling/document_converter.py

@@ -10,6 +10,7 @@ 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.html_backend import HTMLDocumentBackend
 from docling.backend.json.docling_json_backend import DoclingJSONBackend
@@ -17,7 +18,7 @@ from docling.backend.md_backend import MarkdownDocumentBackend
 from docling.backend.msexcel_backend import MsExcelDocumentBackend
 from docling.backend.mspowerpoint_backend import MsPowerpointDocumentBackend
 from docling.backend.msword_backend import MsWordDocumentBackend
-from docling.backend.xml.pubmed_backend import PubMedDocumentBackend
+from docling.backend.xml.jats_backend import JatsDocumentBackend
 from docling.backend.xml.uspto_backend import PatentUsptoDocumentBackend
 from docling.datamodel.base_models import (
     ConversionStatus,
@@ -61,6 +62,11 @@ class FormatOption(BaseModel):
         return self
 
 
+class CsvFormatOption(FormatOption):
+    pipeline_cls: Type = SimplePipeline
+    backend: Type[AbstractDocumentBackend] = CsvDocumentBackend
+
+
 class ExcelFormatOption(FormatOption):
     pipeline_cls: Type = SimplePipeline
     backend: Type[AbstractDocumentBackend] = MsExcelDocumentBackend
@@ -96,9 +102,9 @@ class PatentUsptoFormatOption(FormatOption):
     backend: Type[PatentUsptoDocumentBackend] = PatentUsptoDocumentBackend
 
 
-class XMLPubMedFormatOption(FormatOption):
+class XMLJatsFormatOption(FormatOption):
     pipeline_cls: Type = SimplePipeline
-    backend: Type[AbstractDocumentBackend] = PubMedDocumentBackend
+    backend: Type[AbstractDocumentBackend] = JatsDocumentBackend
 
 
 class ImageFormatOption(FormatOption):
@@ -113,6 +119,9 @@ class PdfFormatOption(FormatOption):
 
 def _get_default_option(format: InputFormat) -> FormatOption:
     format_to_default_options = {
+        InputFormat.CSV: FormatOption(
+            pipeline_cls=SimplePipeline, backend=CsvDocumentBackend
+        ),
         InputFormat.XLSX: FormatOption(
             pipeline_cls=SimplePipeline, backend=MsExcelDocumentBackend
         ),
@@ -134,8 +143,8 @@ def _get_default_option(format: InputFormat) -> FormatOption:
         InputFormat.XML_USPTO: FormatOption(
             pipeline_cls=SimplePipeline, backend=PatentUsptoDocumentBackend
         ),
-        InputFormat.XML_PUBMED: FormatOption(
-            pipeline_cls=SimplePipeline, backend=PubMedDocumentBackend
+        InputFormat.XML_JATS: FormatOption(
+            pipeline_cls=SimplePipeline, backend=JatsDocumentBackend
         ),
         InputFormat.IMAGE: FormatOption(
             pipeline_cls=StandardPdfPipeline, backend=DoclingParseV2DocumentBackend

docling/exceptions.py

@@ -4,3 +4,7 @@ class BaseError(RuntimeError):
 
 class ConversionError(BaseError):
     pass
+
+
+class OperationNotAllowed(BaseError):
+    pass

docling/models/picture_description_api_model.py

@@ -8,6 +8,7 @@ from PIL import Image
 from pydantic import BaseModel, ConfigDict
 
 from docling.datamodel.pipeline_options import PictureDescriptionApiOptions
+from docling.exceptions import OperationNotAllowed
 from docling.models.picture_description_base_model import PictureDescriptionBaseModel
 
 _log = logging.getLogger(__name__)
@@ -45,14 +46,20 @@ class ApiResponse(BaseModel):
 class PictureDescriptionApiModel(PictureDescriptionBaseModel):
     # elements_batch_size = 4
 
-    def __init__(self, enabled: bool, options: PictureDescriptionApiOptions):
+    def __init__(
+        self,
+        enabled: bool,
+        enable_remote_services: bool,
+        options: PictureDescriptionApiOptions,
+    ):
         super().__init__(enabled=enabled, options=options)
         self.options: PictureDescriptionApiOptions
 
         if self.enabled:
-            if options.url.host != "localhost":
-                raise NotImplementedError(
-                    "The options try to connect to remote APIs which are not yet allowed."
+            if not enable_remote_services:
+                raise OperationNotAllowed(
+                    "Connections to remote services is only allowed when set explicitly. "
+                    "pipeline_options.enable_remote_services=True."
                 )
 
     def _annotate_images(self, images: Iterable[Image.Image]) -> Iterable[str]:

docling/models/tesseract_ocr_model.py

@@ -22,6 +22,7 @@ class TesseractOcrModel(BaseOcrModel):
         self.scale = 3  # multiplier for 72 dpi == 216 dpi.
         self.reader = None
         self.osd_reader = None
+        self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
 
         if self.enabled:
             install_errmsg = (
@@ -57,8 +58,6 @@ class TesseractOcrModel(BaseOcrModel):
             _log.debug("Initializing TesserOCR: %s", tesseract_version)
             lang = "+".join(self.options.lang)
 
-            self.script_readers: dict[str, tesserocr.PyTessBaseAPI] = {}
-
             if any([l.startswith("script/") for l in self._tesserocr_languages]):
                 self.script_prefix = "script/"
             else:

docling/pipeline/standard_pdf_pipeline.py

@@ -61,6 +61,14 @@ class StandardPdfPipeline(PaginatedPipeline):
         artifacts_path: Optional[Path] = None
         if pipeline_options.artifacts_path is not None:
             artifacts_path = Path(pipeline_options.artifacts_path).expanduser()
+        elif settings.artifacts_path is not None:
+            artifacts_path = Path(settings.artifacts_path).expanduser()
+
+        if artifacts_path is not None and not artifacts_path.is_dir():
+            raise RuntimeError(
+                f"The value of {artifacts_path=} is not valid. "
+                "When defined, it must point to a folder containing all models required by the pipeline."
+            )
 
         self.keep_images = (
             self.pipeline_options.generate_page_images
@@ -201,6 +209,7 @@ class StandardPdfPipeline(PaginatedPipeline):
         ):
             return PictureDescriptionApiModel(
                 enabled=self.pipeline_options.do_picture_description,
+                enable_remote_services=self.pipeline_options.enable_remote_services,
                 options=self.pipeline_options.picture_description_options,
             )
         elif isinstance(

docling/utils/accelerator_utils.py

@@ -7,36 +7,62 @@ from docling.datamodel.pipeline_options import AcceleratorDevice
 _log = logging.getLogger(__name__)
 
 
-def decide_device(accelerator_device: AcceleratorDevice) -> str:
+def decide_device(accelerator_device: str) -> str:
     r"""
-    Resolve the device based on the acceleration options and the available devices in the system
+    Resolve the device based on the acceleration options and the available devices in the system.
+
     Rules:
     1. AUTO: Check for the best available device on the system.
     2. User-defined: Check if the device actually exists, otherwise fall-back to CPU
     """
-    cuda_index = 0
     device = "cpu"
 
     has_cuda = torch.backends.cuda.is_built() and torch.cuda.is_available()
     has_mps = torch.backends.mps.is_built() and torch.backends.mps.is_available()
 
-    if accelerator_device == AcceleratorDevice.AUTO:
+    if accelerator_device == AcceleratorDevice.AUTO.value:  # Handle 'auto'
         if has_cuda:
-            device = f"cuda:{cuda_index}"
+            device = "cuda:0"
         elif has_mps:
             device = "mps"
 
-    else:
-        if accelerator_device == AcceleratorDevice.CUDA:
-            if has_cuda:
-                device = f"cuda:{cuda_index}"
-            else:
-                _log.warning("CUDA is not available in the system. Fall back to 'CPU'")
-        elif accelerator_device == AcceleratorDevice.MPS:
-            if has_mps:
-                device = "mps"
+    elif accelerator_device.startswith("cuda"):
+        if has_cuda:
+            # if cuda device index specified extract device id
+            parts = accelerator_device.split(":")
+            if len(parts) == 2 and parts[1].isdigit():
+                # select cuda device's id
+                cuda_index = int(parts[1])
+                if cuda_index < torch.cuda.device_count():
+                    device = f"cuda:{cuda_index}"
+                else:
+                    _log.warning(
+                        "CUDA device 'cuda:%d' is not available. Fall back to 'CPU'.",
+                        cuda_index,
+                    )
+            elif len(parts) == 1:  # just "cuda"
+                device = "cuda:0"
             else:
-                _log.warning("MPS is not available in the system. Fall back to 'CPU'")
+                _log.warning(
+                    "Invalid CUDA device format '%s'. Fall back to 'CPU'",
+                    accelerator_device,
+                )
+        else:
+            _log.warning("CUDA is not available in the system. Fall back to 'CPU'")
+
+    elif accelerator_device == AcceleratorDevice.MPS.value:
+        if has_mps:
+            device = "mps"
+        else:
+            _log.warning("MPS is not available in the system. Fall back to 'CPU'")
+
+    elif accelerator_device == AcceleratorDevice.CPU.value:
+        device = "cpu"
+
+    else:
+        _log.warning(
+            "Unknown device option '%s'. Fall back to 'CPU'", accelerator_device
+        )
 
     _log.info("Accelerator device: '%s'", device)
     return device

{docling-2.21.0.dist-info → docling-2.23.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.21.0
+Version: 2.23.0
 Summary: SDK and CLI for parsing PDF, DOCX, HTML, and more, to a unified document representation for powering downstream workflows such as gen AI applications.
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -28,7 +28,7 @@ Provides-Extra: vlm
 Requires-Dist: beautifulsoup4 (>=4.12.3,<4.13.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=1.0.0,<2.0.0)
-Requires-Dist: docling-core[chunking] (>=2.18.0,<3.0.0)
+Requires-Dist: docling-core[chunking] (>=2.19.0,<3.0.0)
 Requires-Dist: docling-ibm-models (>=3.3.0,<4.0.0)
 Requires-Dist: docling-parse (>=3.3.0,<4.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
@@ -41,7 +41,7 @@ Requires-Dist: onnxruntime (>=1.7.0,<1.20.0) ; (python_version < "3.10") and (ex
 Requires-Dist: onnxruntime (>=1.7.0,<2.0.0) ; (python_version >= "3.10") and (extra == "rapidocr")
 Requires-Dist: openpyxl (>=3.1.5,<4.0.0)
 Requires-Dist: pandas (>=2.1.4,<3.0.0)
-Requires-Dist: pillow (>=10.0.0,<11.0.0)
+Requires-Dist: pillow (>=10.0.0,<12.0.0)
 Requires-Dist: pydantic (>=2.0.0,<3.0.0)
 Requires-Dist: pydantic-settings (>=2.3.0,<3.0.0)
 Requires-Dist: pypdfium2 (>=4.30.0,<5.0.0)

{docling-2.21.0.dist-info → docling-2.23.0.dist-info}/RECORD

@@ -2,6 +2,7 @@ docling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/abstract_backend.py,sha256=1lNxzwDTn303aXduPDVmTyXn-5ZIoWMLYqNxANGWmQQ,1658
 docling/backend/asciidoc_backend.py,sha256=zyHxlG_BvlLwvpdNca3P6aopxOJZw8wbDFkJQQknNXk,14050
+docling/backend/csv_backend.py,sha256=xuId4JGEXjoyPgO9Fy9hQ5C-ezXvJwv0TGB8fyFHgWM,4533
 docling/backend/docling_parse_backend.py,sha256=hEEJibI1oJS0LAnFoIs6gMshS3bCqGtVxHnDNvBGZuA,7649
 docling/backend/docling_parse_v2_backend.py,sha256=IpwrBrtLGwNRl5AYO-o3NjEfNRsAkuMhzvDt2HXb9Ko,8655
 docling/backend/html_backend.py,sha256=YTPLZiEEEuGaP6G62skK3wXJ0KftuqBCl8erNXeJyoE,15893
@@ -14,20 +15,20 @@ docling/backend/msword_backend.py,sha256=V4miLIcOH8DDlSCm25F_DALBW60Uf9JoSS0TB4y
 docling/backend/pdf_backend.py,sha256=17Pr8dWsD1C4FYUprrwMM9trDGW-JYLjrcScx1Ul4io,2048
 docling/backend/pypdfium2_backend.py,sha256=QSPfp903ZtSpoNqPmcIek0HmvETrJ1kkwrdxnF5pjS0,9014
 docling/backend/xml/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/xml/pubmed_backend.py,sha256=LMnpowjnxa5SydfNC00Ll840BYraL8dCJu-FfC9iSKk,20447
+docling/backend/xml/jats_backend.py,sha256=JI1iibmrob9Gv9y7zoFncavQ0oJaGWnQoLkozAIiTQU,27513
 docling/backend/xml/uspto_backend.py,sha256=a5GxWLj2SUR5Of8TWJinhef1gKyaQSjHPVXvGiN8yG8,70324
 docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/cli/main.py,sha256=T9Tibi1z7YaU8jyl0HrN3h4y0cALvFVg3-4sanWd35M,16590
+docling/cli/main.py,sha256=pCJ_GFgxsgZ0soz32OhMl-CWi7YXIrvax_m9Qw4UhMs,16839
 docling/cli/models.py,sha256=Z4IEuaXE9el5PuI6_6mR4D5Sn3y8WZzBtoIJPi6jL_s,3188
 docling/cli/tools.py,sha256=QhtRxQG0TVrfsMqdv5i7J0_qQy1ZZyWYnHPwJl7b5oY,322
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=vewP1X99qfAwiUsiC2m8CBDGiQPsGyp_WkKJHYPoYn4,7026
-docling/datamodel/document.py,sha256=HkmvQKW3QSx3tAqPTnXiJbD_y1EVwR-WE3n6Gq8g1NY,13428
-docling/datamodel/pipeline_options.py,sha256=SRlZYIXdmpFO_vyziOonttZvftRQMiFvltxNlolzYW8,9642
-docling/datamodel/settings.py,sha256=pJi9OBqZQhsNi7RwJWQFRDKGhm3u679iN76psA3VtsY,1817
-docling/document_converter.py,sha256=qaldb7Thqk59RdE-RTGtj1M7l5UzaBdnxIvGoQ7lTeo,12876
-docling/exceptions.py,sha256=-FoP46rFJgz_jn5uDv2V052udEEg8gckk6uhoItchXc,85
+docling/datamodel/base_models.py,sha256=b_8LiDCC4MkpqnKfsJjduH2DSsjADCllBLNB83Tpamw,7099
+docling/datamodel/document.py,sha256=DbJifyMgBEkAk80BMYXTuSgqH2vijDENDkU7Fmr6j_g,14567
+docling/datamodel/pipeline_options.py,sha256=5jXSVNGyOy6Ha18Wd80e7pYFmvRZk-2Lkgx0bwMOuq8,10234
+docling/datamodel/settings.py,sha256=bNMdowIKv7RUchabQTo4rFNEsxfB6pGg2LoZSY634zo,1869
+docling/document_converter.py,sha256=AeiSmKzWcnOkZm8O-KIBG72g3l4W2CAsq3yEbfC1tiE,13184
+docling/exceptions.py,sha256=K1WnCS1leK2JtMB5ewZWKkb0EaijFgl-tRzrO9ntgPM,134
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/base_model.py,sha256=q_lKeQ0FT70idXlZ3JgyAv8dA8J3bZWBSDBkqTzy0lo,2679
 docling/models/base_ocr_model.py,sha256=YiUMvdjnHw9SHjnfJKT5INrPMoIGEf_Z2OApfl_VRTE,6919
@@ -39,20 +40,20 @@ docling/models/layout_model.py,sha256=7fQWipGV1HDrvbP4uOKa9QAicQl89jp7lailQmbFL3
 docling/models/ocr_mac_model.py,sha256=bLP14UUmZcSzjDe-HLj-mtksTuBmsCTg2C1wCxUpan0,4502
 docling/models/page_assemble_model.py,sha256=c5KLKwkUIdW0JcDHizWsqrpb5x_3DK28x82Q8o-3VJM,5968
 docling/models/page_preprocessing_model.py,sha256=1gVrZjObKxAvXkkKvXnIFApPOggzgiTFPtt1CGbMbSs,2763
-docling/models/picture_description_api_model.py,sha256=Tw4B92_5Fa5FKZeGmgUWmSFMAw5D58uzQM2XRTIXOXI,3003
+docling/models/picture_description_api_model.py,sha256=SKNoHpqzbfM8iO-DJJ4ccyNVqO0B2d9neLBnXqt50FY,3186
 docling/models/picture_description_base_model.py,sha256=rZLIW1_CaRAw_EP3zuI8ktC0ZxwO7yubhh2RkaC_8e8,1910
 docling/models/picture_description_vlm_model.py,sha256=a2vYUdlcA0--_8neY0tTiU8reCf29NCbVMKwWdMy2QQ,3653
 docling/models/rapid_ocr_model.py,sha256=2HXmurNRPP6qyqn7U5h9NQIs8zi0TMHf56CpcKQk0fU,5038
 docling/models/table_structure_model.py,sha256=UIqWlw_9JNfGsO86c00rPb4GCg-yNliKEwyhCqlsZbM,11225
 docling/models/tesseract_ocr_cli_model.py,sha256=b2Is5x2gZLS6mQWnKe0y7p6UU6hRTHDfoH4D2RQ5mx0,9310
-docling/models/tesseract_ocr_model.py,sha256=BN85u-4a-xzUY7Iw21Ib8L8kx4mgbDGiUtxBelLiJm8,8513
+docling/models/tesseract_ocr_model.py,sha256=ikGu6QNknLG64c9yYIb0Ix6MGhBzOoa1ODbNc8MT5r8,8508
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/pipeline/base_pipeline.py,sha256=9ABK-Cr235bxE5vweoIA5rgBZV_EF8qFxAqLI27H_Pg,8749
 docling/pipeline/simple_pipeline.py,sha256=mZqANqUtAOFAyqQEShErQnAUz6tJFOl6zVoazEDJ_wE,2254
-docling/pipeline/standard_pdf_pipeline.py,sha256=UKB9COXmVGvUhTVwsKsQTjNKi86TRdGLJjknwNZPwNo,12366
+docling/pipeline/standard_pdf_pipeline.py,sha256=Zoe8GGPujha16_TGYBAxcPriEwgYPaJPkp3BwG5XowU,12862
 docling/py.typed,sha256=AbpHGcgLb-kRsJGnwFEktk7uzpZOCcBY74-YBdrKVGs,1
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/utils/accelerator_utils.py,sha256=ZjULCn-qhxqx3frF-rJmAlWdzqgUMxH5utLHbSPev80,1367
+docling/utils/accelerator_utils.py,sha256=ONNRrC8fH-8E93WUCNhfOq1t7WrQ1T7-YsmExTOY5f0,2292
 docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
 docling/utils/glm_utils.py,sha256=W4JRoP0xQ6SJmhhIoAfcKxm5dr1CFvLHp8pqI1kdhxs,12250
 docling/utils/layout_postprocessor.py,sha256=urRzeF9PrKiMBvA6DdHHwyLxG06CMhelgJeV5B1l6l0,24258
@@ -61,8 +62,8 @@ docling/utils/ocr_utils.py,sha256=F7iOOjqolUcImUzir4qjDQd4QWSO3s6JC4WRn3U7uY4,26
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=0ozCk7zUkYzxRVmYoIB2zA1lqjQOuaQzxfGuf1wmKW4,1866
 docling/utils/visualization.py,sha256=4pn-80fVuE04ken7hUg5Ar47ndRSL9MWBgdHM-1g1zU,2735
-docling-2.21.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.21.0.dist-info/METADATA,sha256=HX1DmAVvGHCA61nnfg2pjFOEtMPVV_0ou9YWgfGEVhU,8720
-docling-2.21.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-docling-2.21.0.dist-info/entry_points.txt,sha256=cFrINXsORijdm2EWJzf1m9_rDxH9G9W1fP385-9atY4,84
-docling-2.21.0.dist-info/RECORD,,
+docling-2.23.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.23.0.dist-info/METADATA,sha256=O4EJYC_yjLCFfKnhnzgSW4qGLOHaatDWDXsQS2EJDjU,8720
+docling-2.23.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+docling-2.23.0.dist-info/entry_points.txt,sha256=cFrINXsORijdm2EWJzf1m9_rDxH9G9W1fP385-9atY4,84
+docling-2.23.0.dist-info/RECORD,,