docling 2.3.0__py3-none-any.whl → 2.3.1__py3-none-any.whl

docling/document_converter.py

@@ -139,6 +139,10 @@ class DocumentConverter:
 
         self.initialized_pipelines: Dict[Type[BasePipeline], BasePipeline] = {}
 
+    def initialize_pipeline(self, format: InputFormat):
+        """Initialize the conversion pipeline for the selected format."""
+        self._get_pipeline(doc_format=format)
+
     @validate_call(config=ConfigDict(strict=True))
     def convert(
         self,
@@ -219,13 +223,13 @@ class DocumentConverter:
                 else:
                     _log.info(f"Skipped a document. We lost {elapsed:.2f} sec.")
 
-    def _get_pipeline(self, doc: InputDocument) -> Optional[BasePipeline]:
+    def _get_pipeline(self, doc_format: InputFormat) -> Optional[BasePipeline]:
         assert self.format_to_options is not None
 
-        fopt = self.format_to_options.get(doc.format)
+        fopt = self.format_to_options.get(doc_format)
 
         if fopt is None:
-            raise RuntimeError(f"Could not get pipeline for document {doc.file}")
+            raise RuntimeError(f"Could not get pipeline for {doc_format}")
         else:
             pipeline_class = fopt.pipeline_cls
             pipeline_options = fopt.pipeline_options
@@ -256,7 +260,7 @@ class DocumentConverter:
         self, in_doc: InputDocument, raises_on_error: bool
     ) -> ConversionResult:
         if in_doc.valid:
-            pipeline = self._get_pipeline(in_doc)
+            pipeline = self._get_pipeline(in_doc.format)
             if pipeline is None:  # Can't find a default pipeline. Should this raise?
                 if raises_on_error:
                     raise RuntimeError(

{docling-2.3.0.dist-info → docling-2.3.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 2.3.0
+Version: 2.3.1
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -23,9 +23,9 @@ Provides-Extra: tesserocr
 Requires-Dist: beautifulsoup4 (>=4.12.3,<5.0.0)
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.26.1,<0.27.0)
-Requires-Dist: docling-core (>=2.2.3,<3.0.0)
-Requires-Dist: docling-ibm-models (>=2.0.1,<3.0.0)
-Requires-Dist: docling-parse (>=2.0.0,<3.0.0)
+Requires-Dist: docling-core (>=2.3.0,<3.0.0)
+Requires-Dist: docling-ibm-models (>=2.0.3,<3.0.0)
+Requires-Dist: docling-parse (>=2.0.2,<3.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -41,10 +41,6 @@ Requires-Dist: requests (>=2.32.3,<3.0.0)
 Requires-Dist: rtree (>=1.3.0,<2.0.0)
 Requires-Dist: scipy (>=1.14.1,<2.0.0)
 Requires-Dist: tesserocr (>=2.7.1,<3.0.0) ; extra == "tesserocr"
-Requires-Dist: torch (>=2.2.2,<2.3.0) ; sys_platform == "darwin" and platform_machine == "x86_64"
-Requires-Dist: torch (>=2.2.2,<3.0.0) ; sys_platform != "darwin" or platform_machine != "x86_64"
-Requires-Dist: torchvision (>=0,<1) ; sys_platform != "darwin" or platform_machine != "x86_64"
-Requires-Dist: torchvision (>=0.17.2,<0.18.0) ; sys_platform == "darwin" and platform_machine == "x86_64"
 Requires-Dist: typer (>=0.12.5,<0.13.0)
 Project-URL: Repository, https://github.com/DS4SD/docling
 Description-Content-Type: text/markdown

{docling-2.3.0.dist-info → docling-2.3.1.dist-info}/RECORD

@@ -17,7 +17,7 @@ docling/datamodel/base_models.py,sha256=fmkS6iTxGZCTtNCo2zsgMmBC11Ogf2Ht-mNIlZ9G
 docling/datamodel/document.py,sha256=9dQf_J18X_MEWs-Mg3Ed6BykFPJ79ETmkkxcssY-vYo,20698
 docling/datamodel/pipeline_options.py,sha256=WNjluKC-Ww63ifkGMHwws8zIDHnOS1z5Hw7_j3S0qao,2446
 docling/datamodel/settings.py,sha256=2-sYEnKLV_giGygUlBtiBd4CJYN5T9-3BdL6NpWkUYw,1155
-docling/document_converter.py,sha256=Y0Tngh-seNSty7Ov71DDAJzbBgruoEdwYPunVn7DT00,10413
+docling/document_converter.py,sha256=U52_rZQDm2wzrnsuUrvsfX2MnmOWFFhjBzfS8tEvt6Y,10595
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/base_model.py,sha256=Yq_-FmUhqhE20vXYG3WiQXDRTIPjik1CyuEZ8iYTGAY,701
 docling/models/base_ocr_model.py,sha256=Ti0glL-_DVRfmP3MpywYVmkNf5RP6qhRg_UKzJuV1Dc,5663
@@ -38,8 +38,8 @@ docling/utils/export.py,sha256=KyGF1BVDHPFfHVXZc8vegsWlFfOgGPP2YckWpTadyI8,4694
 docling/utils/layout_utils.py,sha256=vlN0rc8i0ayRGn3WnaG-pdmqEL00KKGl2zez3Gj-hrk,32074
 docling/utils/profiling.py,sha256=YaMGoB9MMZpagF9mb5ndoHj8Lpb9aIdb7El-Pl7IcFs,1753
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-2.3.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-2.3.0.dist-info/METADATA,sha256=e3LTQgbktuUHzQlI4qXDhIDMGOX0duC1EJWws6j6_y8,6373
-docling-2.3.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-2.3.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-2.3.0.dist-info/RECORD,,
+docling-2.3.1.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-2.3.1.dist-info/METADATA,sha256=_FXRLyE1Uy6RobmdLb244I5vg7KEi3ogolWBQvDOvx4,5977
+docling-2.3.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-2.3.1.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-2.3.1.dist-info/RECORD,,