docling 2.18.0__py3-none-any.whl → 2.20.0__py3-none-any.whl

docling/pipeline/standard_pdf_pipeline.py

@@ -1,5 +1,6 @@
 import logging
 import sys
+import warnings
 from pathlib import Path
 from typing import Optional
 
@@ -13,10 +14,13 @@ from docling.datamodel.pipeline_options import (
     EasyOcrOptions,
     OcrMacOptions,
     PdfPipelineOptions,
+    PictureDescriptionApiOptions,
+    PictureDescriptionVlmOptions,
     RapidOcrOptions,
     TesseractCliOcrOptions,
     TesseractOcrOptions,
 )
+from docling.datamodel.settings import settings
 from docling.models.base_ocr_model import BaseOcrModel
 from docling.models.code_formula_model import CodeFormulaModel, CodeFormulaModelOptions
 from docling.models.document_picture_classifier import (
@@ -32,28 +36,31 @@ from docling.models.page_preprocessing_model import (
     PagePreprocessingModel,
     PagePreprocessingOptions,
 )
+from docling.models.picture_description_api_model import PictureDescriptionApiModel
+from docling.models.picture_description_base_model import PictureDescriptionBaseModel
+from docling.models.picture_description_vlm_model import PictureDescriptionVlmModel
 from docling.models.rapid_ocr_model import RapidOcrModel
 from docling.models.table_structure_model import TableStructureModel
 from docling.models.tesseract_ocr_cli_model import TesseractOcrCliModel
 from docling.models.tesseract_ocr_model import TesseractOcrModel
 from docling.pipeline.base_pipeline import PaginatedPipeline
+from docling.utils.model_downloader import download_models
 from docling.utils.profiling import ProfilingScope, TimeRecorder
 
 _log = logging.getLogger(__name__)
 
 
 class StandardPdfPipeline(PaginatedPipeline):
-    _layout_model_path = "model_artifacts/layout"
-    _table_model_path = "model_artifacts/tableformer"
+    _layout_model_path = LayoutModel._model_path
+    _table_model_path = TableStructureModel._model_path
 
     def __init__(self, pipeline_options: PdfPipelineOptions):
         super().__init__(pipeline_options)
         self.pipeline_options: PdfPipelineOptions
 
-        if pipeline_options.artifacts_path is None:
-            self.artifacts_path = self.download_models_hf()
-        else:
-            self.artifacts_path = Path(pipeline_options.artifacts_path)
+        artifacts_path: Optional[Path] = None
+        if pipeline_options.artifacts_path is not None:
+            artifacts_path = Path(pipeline_options.artifacts_path).expanduser()
 
         self.keep_images = (
             self.pipeline_options.generate_page_images
@@ -63,7 +70,7 @@ class StandardPdfPipeline(PaginatedPipeline):
 
         self.glm_model = GlmModel(options=GlmOptions())
 
-        if (ocr_model := self.get_ocr_model()) is None:
+        if (ocr_model := self.get_ocr_model(artifacts_path=artifacts_path)) is None:
             raise RuntimeError(
                 f"The specified OCR kind is not supported: {pipeline_options.ocr_options.kind}."
             )
@@ -79,15 +86,13 @@ class StandardPdfPipeline(PaginatedPipeline):
             ocr_model,
             # Layout model
             LayoutModel(
-                artifacts_path=self.artifacts_path
-                / StandardPdfPipeline._layout_model_path,
+                artifacts_path=artifacts_path,
                 accelerator_options=pipeline_options.accelerator_options,
             ),
             # Table structure model
             TableStructureModel(
                 enabled=pipeline_options.do_table_structure,
-                artifacts_path=self.artifacts_path
-                / StandardPdfPipeline._table_model_path,
+                artifacts_path=artifacts_path,
                 options=pipeline_options.table_structure_options,
                 accelerator_options=pipeline_options.accelerator_options,
             ),
@@ -95,13 +100,22 @@ class StandardPdfPipeline(PaginatedPipeline):
             PageAssembleModel(options=PageAssembleOptions()),
         ]
 
+        # Picture description model
+        if (
+            picture_description_model := self.get_picture_description_model(
+                artifacts_path=artifacts_path
+            )
+        ) is None:
+            raise RuntimeError(
+                f"The specified picture description kind is not supported: {pipeline_options.picture_description_options.kind}."
+            )
+
         self.enrichment_pipe = [
-            # Other models working on `NodeItem` elements in the DoclingDocument
             # Code Formula Enrichment Model
             CodeFormulaModel(
                 enabled=pipeline_options.do_code_enrichment
                 or pipeline_options.do_formula_enrichment,
-                artifacts_path=pipeline_options.artifacts_path,
+                artifacts_path=artifacts_path,
                 options=CodeFormulaModelOptions(
                     do_code_enrichment=pipeline_options.do_code_enrichment,
                     do_formula_enrichment=pipeline_options.do_formula_enrichment,
@@ -111,15 +125,18 @@ class StandardPdfPipeline(PaginatedPipeline):
             # Document Picture Classifier
             DocumentPictureClassifier(
                 enabled=pipeline_options.do_picture_classification,
-                artifacts_path=pipeline_options.artifacts_path,
+                artifacts_path=artifacts_path,
                 options=DocumentPictureClassifierOptions(),
                 accelerator_options=pipeline_options.accelerator_options,
             ),
+            # Document Picture description
+            picture_description_model,
         ]
 
         if (
             self.pipeline_options.do_formula_enrichment
             or self.pipeline_options.do_code_enrichment
+            or self.pipeline_options.do_picture_description
         ):
             self.keep_backend = True
 
@@ -127,23 +144,24 @@ class StandardPdfPipeline(PaginatedPipeline):
     def download_models_hf(
         local_dir: Optional[Path] = None, force: bool = False
     ) -> Path:
-        from huggingface_hub import snapshot_download
-        from huggingface_hub.utils import disable_progress_bars
-
-        disable_progress_bars()
-        download_path = snapshot_download(
-            repo_id="ds4sd/docling-models",
-            force_download=force,
-            local_dir=local_dir,
-            revision="v2.1.0",
+        warnings.warn(
+            "The usage of StandardPdfPipeline.download_models_hf() is deprecated "
+            "use instead the utility `docling-tools models download`, or "
+            "the upstream method docling.utils.models_downloader.download_all()",
+            DeprecationWarning,
+            stacklevel=3,
         )
 
-        return Path(download_path)
+        output_dir = download_models(output_dir=local_dir, force=force, progress=False)
+        return output_dir
 
-    def get_ocr_model(self) -> Optional[BaseOcrModel]:
+    def get_ocr_model(
+        self, artifacts_path: Optional[Path] = None
+    ) -> Optional[BaseOcrModel]:
         if isinstance(self.pipeline_options.ocr_options, EasyOcrOptions):
             return EasyOcrModel(
                 enabled=self.pipeline_options.do_ocr,
+                artifacts_path=artifacts_path,
                 options=self.pipeline_options.ocr_options,
                 accelerator_options=self.pipeline_options.accelerator_options,
             )
@@ -174,6 +192,29 @@ class StandardPdfPipeline(PaginatedPipeline):
             )
         return None
 
+    def get_picture_description_model(
+        self, artifacts_path: Optional[Path] = None
+    ) -> Optional[PictureDescriptionBaseModel]:
+        if isinstance(
+            self.pipeline_options.picture_description_options,
+            PictureDescriptionApiOptions,
+        ):
+            return PictureDescriptionApiModel(
+                enabled=self.pipeline_options.do_picture_description,
+                options=self.pipeline_options.picture_description_options,
+            )
+        elif isinstance(
+            self.pipeline_options.picture_description_options,
+            PictureDescriptionVlmOptions,
+        ):
+            return PictureDescriptionVlmModel(
+                enabled=self.pipeline_options.do_picture_description,
+                artifacts_path=artifacts_path,
+                options=self.pipeline_options.picture_description_options,
+                accelerator_options=self.pipeline_options.accelerator_options,
+            )
+        return None
+
     def initialize_page(self, conv_res: ConversionResult, page: Page) -> Page:
         with TimeRecorder(conv_res, "page_init"):
             page._backend = conv_res.input._backend.load_page(page.page_no)  # type: ignore

docling/utils/model_downloader.py

@@ -0,0 +1,84 @@
+import logging
+from pathlib import Path
+from typing import Optional
+
+from docling.datamodel.pipeline_options import smolvlm_picture_description
+from docling.datamodel.settings import settings
+from docling.models.code_formula_model import CodeFormulaModel
+from docling.models.document_picture_classifier import DocumentPictureClassifier
+from docling.models.easyocr_model import EasyOcrModel
+from docling.models.layout_model import LayoutModel
+from docling.models.picture_description_vlm_model import PictureDescriptionVlmModel
+from docling.models.table_structure_model import TableStructureModel
+
+_log = logging.getLogger(__name__)
+
+
+def download_models(
+    output_dir: Optional[Path] = None,
+    *,
+    force: bool = False,
+    progress: bool = False,
+    with_layout: bool = True,
+    with_tableformer: bool = True,
+    with_code_formula: bool = True,
+    with_picture_classifier: bool = True,
+    with_smolvlm: bool = True,
+    with_easyocr: bool = True,
+):
+    if output_dir is None:
+        output_dir = settings.cache_dir / "models"
+
+    # Make sure the folder exists
+    output_dir.mkdir(exist_ok=True, parents=True)
+
+    if with_layout:
+        _log.info(f"Downloading layout model...")
+        LayoutModel.download_models(
+            local_dir=output_dir / LayoutModel._model_repo_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_tableformer:
+        _log.info(f"Downloading tableformer model...")
+        TableStructureModel.download_models(
+            local_dir=output_dir / TableStructureModel._model_repo_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_picture_classifier:
+        _log.info(f"Downloading picture classifier model...")
+        DocumentPictureClassifier.download_models(
+            local_dir=output_dir / DocumentPictureClassifier._model_repo_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_code_formula:
+        _log.info(f"Downloading code formula model...")
+        CodeFormulaModel.download_models(
+            local_dir=output_dir / CodeFormulaModel._model_repo_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_smolvlm:
+        _log.info(f"Downloading SmolVlm model...")
+        PictureDescriptionVlmModel.download_models(
+            repo_id=smolvlm_picture_description.repo_id,
+            local_dir=output_dir / smolvlm_picture_description.repo_cache_folder,
+            force=force,
+            progress=progress,
+        )
+
+    if with_easyocr:
+        _log.info(f"Downloading easyocr models...")
+        EasyOcrModel.download_models(
+            local_dir=output_dir / EasyOcrModel._model_repo_folder,
+            force=force,
+            progress=progress,
+        )
+
+    return output_dir

docling/utils/utils.py

@@ -4,6 +4,9 @@ from itertools import islice
 from pathlib import Path
 from typing import List, Union
 
+import requests
+from tqdm import tqdm
+
 
 def chunkify(iterator, chunk_size):
     """Yield successive chunks of chunk_size from the iterable."""
@@ -39,3 +42,24 @@ def create_hash(string: str):
     hasher.update(string.encode("utf-8"))
 
     return hasher.hexdigest()
+
+
+def download_url_with_progress(url: str, progress: bool = False) -> BytesIO:
+    buf = BytesIO()
+    with requests.get(url, stream=True, allow_redirects=True) as response:
+        total_size = int(response.headers.get("content-length", 0))
+        progress_bar = tqdm(
+            total=total_size,
+            unit="B",
+            unit_scale=True,
+            unit_divisor=1024,
+            disable=(not progress),
+        )
+
+        for chunk in response.iter_content(10 * 1024):
+            buf.write(chunk)
+            progress_bar.update(len(chunk))
+        progress_bar.close()
+
+    buf.seek(0)
+    return buf

{docling-2.18.0.dist-info → docling-2.20.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.18.0
+Version: 2.20.0
 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
@@ -24,12 +24,13 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: ocrmac
 Provides-Extra: rapidocr
 Provides-Extra: tesserocr
-Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
+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] (>=2.17.0,<3.0.0)
+Requires-Dist: docling-core[chunking] (>=2.17.2,<3.0.0)
 Requires-Dist: docling-ibm-models (>=3.3.0,<4.0.0)
-Requires-Dist: docling-parse (>=3.1.0,<4.0.0)
+Requires-Dist: docling-parse (>=3.3.0,<4.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -52,6 +53,9 @@ Requires-Dist: rtree (>=1.3.0,<2.0.0)
 Requires-Dist: scipy (>=1.6.0,<1.14.0) ; python_version < "3.10"
 Requires-Dist: scipy (>=1.6.0,<2.0.0) ; python_version >= "3.10"
 Requires-Dist: tesserocr (>=2.7.1,<3.0.0) ; extra == "tesserocr"
+Requires-Dist: tqdm (>=4.65.0,<5.0.0)
+Requires-Dist: transformers (>=4.42.0,<4.43.0) ; (sys_platform == "darwin" and platform_machine == "x86_64") and (extra == "vlm")
+Requires-Dist: transformers (>=4.46.0,<5.0.0) ; (sys_platform != "darwin" or platform_machine != "x86_64") and (extra == "vlm")
 Requires-Dist: typer (>=0.12.5,<0.13.0)
 Project-URL: Repository, https://github.com/DS4SD/docling
 Description-Content-Type: text/markdown

{docling-2.18.0.dist-info → docling-2.20.0.dist-info}/RECORD

@@ -7,10 +7,10 @@ docling/backend/docling_parse_v2_backend.py,sha256=IpwrBrtLGwNRl5AYO-o3NjEfNRsAk
 docling/backend/html_backend.py,sha256=YTPLZiEEEuGaP6G62skK3wXJ0KftuqBCl8erNXeJyoE,15893
 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=d7XAFHzFO9qhrCJA3raWEmZ8WXSYyy3KOE57oMeqKGc,16502
+docling/backend/md_backend.py,sha256=NaVfcnEH-5bwVovjn76EobF6B6Wm8AhaTZ4E8k0TUPo,16826
 docling/backend/msexcel_backend.py,sha256=lyJc4ShJGAN2ZfNTTuhdYTF-44cZsGyn_8Djstp3IEU,12700
 docling/backend/mspowerpoint_backend.py,sha256=esAyaaQe17BQFweGAGJHvImKETefY0BpvfpUSECC49w,16424
-docling/backend/msword_backend.py,sha256=0iR1l3eLplPv3CPT7iGwQb50LIVf3C32KZFzwAkARrc,20573
+docling/backend/msword_backend.py,sha256=V4miLIcOH8DDlSCm25F_DALBW60Uf9JoSS0TB4yrQBw,20591
 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
@@ -18,45 +18,51 @@ docling/backend/xml/pubmed_backend.py,sha256=LMnpowjnxa5SydfNC00Ll840BYraL8dCJu-
 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=K5C2yQIoM40_W3YU8a7SmneY-hWbNp_JOFPLk0NPcDI,16098
+docling/cli/main.py,sha256=T9Tibi1z7YaU8jyl0HrN3h4y0cALvFVg3-4sanWd35M,16590
+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=f9-VQFgOdahyclGQgH_T8ZYBopkWsF_fbWbxo39ux3g,7888
-docling/datamodel/settings.py,sha256=uN9jeXMwx--tJb-DFU7nr77g0Iou13YAVDzsymTvbHg,1759
+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/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/models/base_model.py,sha256=H5X-exVaAN-XMTzxpgUc-rwH-D8Uk7-VuZtq2soNGXI,2567
+docling/models/base_model.py,sha256=q_lKeQ0FT70idXlZ3JgyAv8dA8J3bZWBSDBkqTzy0lo,2679
 docling/models/base_ocr_model.py,sha256=YiUMvdjnHw9SHjnfJKT5INrPMoIGEf_Z2OApfl_VRTE,6919
-docling/models/code_formula_model.py,sha256=bOIKJvckZ0QpnDZ-CDiYv-CvuGvaGzJgp2PiYAidKBQ,8422
-docling/models/document_picture_classifier.py,sha256=RLB80ueqWZ86hdXtTKmSynCU13nT-T10vUp2sky9110,6078
+docling/models/code_formula_model.py,sha256=6grbRPWaLljadheT5s4omdT6hmXfin4gJU17csWvhjY,8611
+docling/models/document_picture_classifier.py,sha256=6I_j6fG5fnhIV6rqN31LYikNTZyg5isXrVs0GIqHDaY,6235
 docling/models/ds_glm_model.py,sha256=CkhsP0cEWwm4wb1g3cLFriVGpVtELiUK3REDMkPwAMw,13028
-docling/models/easyocr_model.py,sha256=Kakb20ioBxDmNsIqoGvSSs_vbqAWN3QQNHYtEi-eErg,4990
-docling/models/layout_model.py,sha256=3Fw7OM6g0j7NgItKsQOgFOCd1q6lp1DacN_db7f6QCw,6090
+docling/models/easyocr_model.py,sha256=ePg1exAXeOzkBRBT-6PBSmqKFmnNFkCEd4HNDsGVgLM,6860
+docling/models/layout_model.py,sha256=7fQWipGV1HDrvbP4uOKa9QAicQl89jp7lailQmbFL3w,7804
 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_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=qZgoBrBh7H-RJGCTtaRGcj79g2WzZiUBTPnHqJZ-bLA,9557
+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/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/pipeline/base_pipeline.py,sha256=lK8PQiydWJ9M16kIVL7U1A2iryTRFrN5WSucVo2ohFQ,8757
+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=Qefg1JSiFwipypi8TZPJ50WgXTLjwkC0wvYAl02RM2o,10480
+docling/pipeline/standard_pdf_pipeline.py,sha256=UKB9COXmVGvUhTVwsKsQTjNKi86TRdGLJjknwNZPwNo,12366
 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/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
 docling/utils/glm_utils.py,sha256=uyCoFTX9FbS1Ke0aSlkdzGLUt08dZfkgriWadkyLiiA,11856
 docling/utils/layout_postprocessor.py,sha256=urRzeF9PrKiMBvA6DdHHwyLxG06CMhelgJeV5B1l6l0,24258
+docling/utils/model_downloader.py,sha256=XK3ozGXyQcNPvrSsevTwR9VnY41JWovlsGk_ZBnu6FU,2787
 docling/utils/ocr_utils.py,sha256=F7iOOjqolUcImUzir4qjDQd4QWSO3s6JC4WRn3U7uY4,263
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
-docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
+docling/utils/utils.py,sha256=0ozCk7zUkYzxRVmYoIB2zA1lqjQOuaQzxfGuf1wmKW4,1866
 docling/utils/visualization.py,sha256=4pn-80fVuE04ken7hUg5Ar47ndRSL9MWBgdHM-1g1zU,2735
-docling-2.18.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.18.0.dist-info/METADATA,sha256=rBP1Z7m0HMpC-HjR360i2JNuIA9lqknRPjUab1mtVic,8403
-docling-2.18.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
-docling-2.18.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.18.0.dist-info/RECORD,,
+docling-2.20.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.20.0.dist-info/METADATA,sha256=9g0XmFk8hxdswqwT5jWnrUPKswGA26JDlyV5hqJ_tCc,8720
+docling-2.20.0.dist-info/WHEEL,sha256=Nq82e9rUAnEjt98J6MlVmMCZb-t9cYE2Ir1kpBmnWfs,88
+docling-2.20.0.dist-info/entry_points.txt,sha256=cFrINXsORijdm2EWJzf1m9_rDxH9G9W1fP385-9atY4,84
+docling-2.20.0.dist-info/RECORD,,

{docling-2.18.0.dist-info → docling-2.20.0.dist-info}/entry_points.txt

@@ -1,3 +1,4 @@
 [console_scripts]
 docling=docling.cli.main:app
+docling-tools=docling.cli.tools:app