docling 2.22.0__py3-none-any.whl → 2.23.1__py3-none-any.whl

docling/backend/xml/uspto_backend.py

@@ -14,7 +14,7 @@ from abc import ABC, abstractmethod
 from enum import Enum, unique
 from io import BytesIO
 from pathlib import Path
-from typing import Any, Final, Optional, Union
+from typing import Final, Optional, Union
 
 from bs4 import BeautifulSoup, Tag
 from docling_core.types.doc import (
@@ -1406,6 +1406,10 @@ class XmlTable:
     http://oasis-open.org/specs/soextblx.dtd
     """
 
+    class ColInfo(TypedDict):
+        ncols: int
+        colinfo: list[dict]
+
     class MinColInfoType(TypedDict):
         offset: list[int]
         colwidth: list[int]
@@ -1425,7 +1429,7 @@ class XmlTable:
         self.empty_text = ""
         self._soup = BeautifulSoup(input, features="xml")
 
-    def _create_tg_range(self, tgs: list[dict[str, Any]]) -> dict[int, ColInfoType]:
+    def _create_tg_range(self, tgs: list[ColInfo]) -> dict[int, ColInfoType]:
         """Create a unified range along the table groups.
 
         Args:
@@ -1532,19 +1536,26 @@ class XmlTable:
         Returns:
             A docling table object.
         """
-        tgs_align = []
-        tg_secs = table.find_all("tgroup")
+        tgs_align: list[XmlTable.ColInfo] = []
+        tg_secs = table("tgroup")
         if tg_secs:
             for tg_sec in tg_secs:
-                ncols = tg_sec.get("cols", None)
-                if ncols:
-                    ncols = int(ncols)
-                tg_align = {"ncols": ncols, "colinfo": []}
-                cs_secs = tg_sec.find_all("colspec")
+                if not isinstance(tg_sec, Tag):
+                    continue
+                col_val = tg_sec.get("cols")
+                ncols = (
+                    int(col_val)
+                    if isinstance(col_val, str) and col_val.isnumeric()
+                    else 1
+                )
+                tg_align: XmlTable.ColInfo = {"ncols": ncols, "colinfo": []}
+                cs_secs = tg_sec("colspec")
                 if cs_secs:
                     for cs_sec in cs_secs:
-                        colname = cs_sec.get("colname", None)
-                        colwidth = cs_sec.get("colwidth", None)
+                        if not isinstance(cs_sec, Tag):
+                            continue
+                        colname = cs_sec.get("colname")
+                        colwidth = cs_sec.get("colwidth")
                         tg_align["colinfo"].append(
                             {"colname": colname, "colwidth": colwidth}
                         )
@@ -1565,16 +1576,23 @@ class XmlTable:
         table_data: list[TableCell] = []
         i_row_global = 0
         is_row_empty: bool = True
-        tg_secs = table.find_all("tgroup")
+        tg_secs = table("tgroup")
         if tg_secs:
             for itg, tg_sec in enumerate(tg_secs):
+                if not isinstance(tg_sec, Tag):
+                    continue
                 tg_range = tgs_range[itg]
-                row_secs = tg_sec.find_all(["row", "tr"])
+                row_secs = tg_sec(["row", "tr"])
 
                 if row_secs:
                     for row_sec in row_secs:
-                        entry_secs = row_sec.find_all(["entry", "td"])
-                        is_header: bool = row_sec.parent.name in ["thead"]
+                        if not isinstance(row_sec, Tag):
+                            continue
+                        entry_secs = row_sec(["entry", "td"])
+                        is_header: bool = (
+                            row_sec.parent is not None
+                            and row_sec.parent.name == "thead"
+                        )
 
                         ncols = 0
                         local_row: list[TableCell] = []
@@ -1582,23 +1600,26 @@ class XmlTable:
                         if entry_secs:
                             wrong_nbr_cols = False
                             for ientry, entry_sec in enumerate(entry_secs):
+                                if not isinstance(entry_sec, Tag):
+                                    continue
                                 text = entry_sec.get_text().strip()
 
                                 # start-end
-                                namest = entry_sec.attrs.get("namest", None)
-                                nameend = entry_sec.attrs.get("nameend", None)
-                                if isinstance(namest, str) and namest.isnumeric():
-                                    namest = int(namest)
-                                else:
-                                    namest = ientry + 1
+                                namest = entry_sec.get("namest")
+                                nameend = entry_sec.get("nameend")
+                                start = (
+                                    int(namest)
+                                    if isinstance(namest, str) and namest.isnumeric()
+                                    else ientry + 1
+                                )
                                 if isinstance(nameend, str) and nameend.isnumeric():
-                                    nameend = int(nameend)
+                                    end = int(nameend)
                                     shift = 0
                                 else:
-                                    nameend = ientry + 2
+                                    end = ientry + 2
                                     shift = 1
 
-                                if nameend > len(tg_range["cell_offst"]):
+                                if end > len(tg_range["cell_offst"]):
                                     wrong_nbr_cols = True
                                     self.nbr_messages += 1
                                     if self.nbr_messages <= self.max_nbr_messages:
@@ -1608,8 +1629,8 @@ class XmlTable:
                                     break
 
                                 range_ = [
-                                    tg_range["cell_offst"][namest - 1],
-                                    tg_range["cell_offst"][nameend - 1] - shift,
+                                    tg_range["cell_offst"][start - 1],
+                                    tg_range["cell_offst"][end - 1] - shift,
                                 ]
 
                                 # add row and replicate cell if needed
@@ -1668,7 +1689,7 @@ class XmlTable:
             A docling table data.
         """
         section = self._soup.find("table")
-        if section is not None:
+        if isinstance(section, Tag):
             table = self._parse_table(section)
             if table.num_rows == 0 or table.num_cols == 0:
                 _log.warning("The parsed USPTO table is empty")

docling/datamodel/base_models.py

@@ -34,7 +34,6 @@ class InputFormat(str, Enum):
     DOCX = "docx"
     PPTX = "pptx"
     HTML = "html"
-    XML_PUBMED = "xml_pubmed"
     IMAGE = "image"
     PDF = "pdf"
     ASCIIDOC = "asciidoc"
@@ -42,6 +41,7 @@ class InputFormat(str, Enum):
     CSV = "csv"
     XLSX = "xlsx"
     XML_USPTO = "xml_uspto"
+    XML_JATS = "xml_jats"
     JSON_DOCLING = "json_docling"
 
 
@@ -59,7 +59,7 @@ 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"],
@@ -79,7 +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",

docling/datamodel/document.py

@@ -333,11 +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"):

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")

docling/document_converter.py

@@ -18,7 +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,
@@ -102,9 +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):
@@ -143,8 +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/models/tesseract_ocr_cli_model.py

@@ -114,7 +114,9 @@ class TesseractOcrCliModel(BaseOcrModel):
         # _log.info("df: ", df.head())
 
         # Filter rows that contain actual text (ignore header or empty rows)
-        df_filtered = df[df["text"].notnull() & (df["text"].str.strip() != "")]
+        df_filtered = df[
+            df["text"].notnull() & (df["text"].apply(str).str.strip() != "")
+        ]
 
         return df_filtered
 

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-2.22.0.dist-info → docling-2.23.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.22.0
+Version: 2.23.1
 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
@@ -25,10 +25,10 @@ Provides-Extra: ocrmac
 Provides-Extra: rapidocr
 Provides-Extra: tesserocr
 Provides-Extra: vlm
-Requires-Dist: beautifulsoup4 (>=4.12.3,<4.13.0)
+Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 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)

{docling-2.22.0.dist-info → docling-2.23.1.dist-info}/RECORD

@@ -5,7 +5,7 @@ docling/backend/asciidoc_backend.py,sha256=zyHxlG_BvlLwvpdNca3P6aopxOJZw8wbDFkJQ
 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
+docling/backend/html_backend.py,sha256=BxYvYmgcio6IqROMFKgyYyoankcNUccalCeYlmTE4fk,16094
 docling/backend/json/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/json/docling_json_backend.py,sha256=LlFMVoZrrCfVwbDuRbNN4Xg96Lujh4xxrTBt9jGhY9I,1984
 docling/backend/md_backend.py,sha256=NaVfcnEH-5bwVovjn76EobF6B6Wm8AhaTZ4E8k0TUPo,16826
@@ -15,19 +15,19 @@ 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/uspto_backend.py,sha256=a5GxWLj2SUR5Of8TWJinhef1gKyaQSjHPVXvGiN8yG8,70324
+docling/backend/xml/jats_backend.py,sha256=HXailrDjiwu4swwFnXy3lNfRtLZmkBBp4yqafCvdr7s,24945
+docling/backend/xml/uspto_backend.py,sha256=IGUNeF2xpLeaVrX6nKb-jXgtSYD2ozULsrDPcrI1IbQ,71040
 docling/chunking/__init__.py,sha256=h83TDs0AuOV6oEPLAPrn9dpGKiU-2Vg6IRNo4cv6GDA,346
 docling/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 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=_TPj-ADts3Qsc6vx1dpwZZnrOQCelqXOYIBCkK7A8FM,7107
-docling/datamodel/document.py,sha256=Aeqpm7d_CCV_2mwMhvNGVeGPWtWN9DJ5WAE4sjqN-dw,14530
-docling/datamodel/pipeline_options.py,sha256=pWCGtK0HEfltTR9Z14BYdS1-Zg6gZq9RlIHA014DpAk,9683
+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=DX_bMqYyVO6rQvpf2JEy95HDR1QXT51v3T3Xn40pwjE,13196
+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
@@ -45,7 +45,7 @@ docling/models/picture_description_base_model.py,sha256=rZLIW1_CaRAw_EP3zuI8ktC0
 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_cli_model.py,sha256=F5EhS4NDEmLkPq-a0P7o2LrzjmJgACzlYXTDvtD3NtY,9343
 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
@@ -53,7 +53,7 @@ docling/pipeline/simple_pipeline.py,sha256=mZqANqUtAOFAyqQEShErQnAUz6tJFOl6zVoaz
 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
@@ -62,8 +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-2.22.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.22.0.dist-info/METADATA,sha256=eKFbLHbqOA9xMt4c0Pdqwh7tVBOXSqdSWh_MP4ztkeU,8720
-docling-2.22.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-docling-2.22.0.dist-info/entry_points.txt,sha256=cFrINXsORijdm2EWJzf1m9_rDxH9G9W1fP385-9atY4,84
-docling-2.22.0.dist-info/RECORD,,
+docling-2.23.1.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.23.1.dist-info/METADATA,sha256=PDA1FnXkfCr0QYxO_s4bVRhACiGkXzpycTLTmqKmJ6c,8719
+docling-2.23.1.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+docling-2.23.1.dist-info/entry_points.txt,sha256=cFrINXsORijdm2EWJzf1m9_rDxH9G9W1fP385-9atY4,84
+docling-2.23.1.dist-info/RECORD,,