docling 1.2.0__py3-none-any.whl → 1.3.0__py3-none-any.whl

docling/backend/abstract_backend.py

@@ -35,7 +35,7 @@ class PdfPageBackend(ABC):
 
 class PdfDocumentBackend(ABC):
     @abstractmethod
-    def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
         pass
 
     @abstractmethod

docling/backend/docling_parse_backend.py

@@ -146,11 +146,12 @@ class DoclingParsePageBackend(PdfPageBackend):
 
 
 class DoclingParseDocumentBackend(PdfDocumentBackend):
-    def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
         super().__init__(path_or_stream)
         self._pdoc = pdfium.PdfDocument(path_or_stream)
         # Parsing cells with docling_parser call
-        print("PARSING WITH DOCLING PARSE")
+        if isinstance(path_or_stream, BytesIO):
+            raise NotImplemented("This backend does not support byte streams yet.")
         parser = pdf_parser()
         self._parser_doc = parser.find_cells(str(path_or_stream))
 

docling/backend/pypdfium2_backend.py

@@ -199,7 +199,7 @@ class PyPdfiumPageBackend(PdfPageBackend):
 
 
 class PyPdfiumDocumentBackend(PdfDocumentBackend):
-    def __init__(self, path_or_stream: Iterable[Union[BytesIO, Path]]):
+    def __init__(self, path_or_stream: Union[BytesIO, Path]):
         super().__init__(path_or_stream)
         self._pdoc = pdfium.PdfDocument(path_or_stream)
 

docling/datamodel/base_models.py

@@ -265,3 +265,9 @@ class PipelineOptions(BaseModel):
     do_ocr: bool = False  # True: perform OCR, replace programmatic PDF text
 
     table_structure_options: TableStructureOptions = TableStructureOptions()
+
+
+class AssembleOptions(BaseModel):
+    keep_page_images: bool = (
+        False  # False: page images are removed in the assemble step
+    )

docling/document_converter.py

@@ -14,6 +14,7 @@ from pydantic import AnyHttpUrl, TypeAdapter, ValidationError
 from docling.backend.abstract_backend import PdfDocumentBackend
 from docling.datamodel.base_models import (
     AssembledUnit,
+    AssembleOptions,
     ConversionStatus,
     Page,
     PipelineOptions,
@@ -44,6 +45,7 @@ class DocumentConverter:
         pipeline_options: PipelineOptions = PipelineOptions(),
         pdf_backend: Type[PdfDocumentBackend] = DocumentConversionInput.DEFAULT_BACKEND,
         pipeline_cls: Type[BaseModelPipeline] = StandardModelPipeline,
+        assemble_options: AssembleOptions = AssembleOptions(),
     ):
         if not artifacts_path:
             artifacts_path = self.download_models_hf()
@@ -57,6 +59,7 @@ class DocumentConverter:
         self.page_assemble_model = PageAssembleModel(config={})
         self.glm_model = GlmModel(config={})
         self.pdf_backend = pdf_backend
+        self.assemble_options = assemble_options
 
     @staticmethod
     def download_models_hf(
@@ -174,17 +177,23 @@ class DocumentConverter:
                     pages_with_images,
                 )
 
+                # 4. Run pipeline stages
                 pipeline_pages = self.model_pipeline.apply(pages_with_cells)
 
-                # 7. Assemble page elements (per page)
+                # 5. Assemble page elements (per page)
                 assembled_pages = self.page_assemble_model(pipeline_pages)
 
                 # exhaust assembled_pages
                 for assembled_page in assembled_pages:
                     # Free up mem resources before moving on with next batch
-                    assembled_page.image = (
-                        None  # Comment this if you want to visualize page images
-                    )
+
+                    # Remove page images (can be disabled)
+                    if not self.assemble_options.keep_page_images:
+                        assembled_page.image = (
+                            None  # Comment this if you want to visualize page images
+                        )
+
+                    # Unload backend
                     assembled_page._backend.unload()
 
                     all_assembled_pages.append(assembled_page)

{docling-1.2.0.dist-info → docling-1.3.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.2.0
+Version: 1.3.0
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -21,6 +21,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: easyocr
 Provides-Extra: ocr
+Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.19.0,<1)
 Requires-Dist: docling-core (>=1.1.2,<2.0.0)
 Requires-Dist: docling-ibm-models (>=1.1.0,<2.0.0)
@@ -93,17 +94,21 @@ print(doc.export_to_markdown())  # output: "## DocLayNet: A Large Human-Annotate
 
 ### Convert a batch of documents
 
-For an example of batch-converting documents, see [convert.py](https://github.com/DS4SD/docling/blob/main/examples/convert.py).
+For an example of batch-converting documents, see [batch_convert.py](https://github.com/DS4SD/docling/blob/main/examples/batch_convert.py).
 
 From a local repo clone, you can run it with:
 
 ```
-python examples/convert.py
+python examples/batch_convert.py
 ```
 The output of the above command will be written to `./scratch`.
 
 ### Adjust pipeline features
 
+The example file [custom_convert.py](https://github.com/DS4SD/docling/blob/main/examples/custom_convert.py) contains multiple ways
+one can adjust the conversion pipeline and features.
+
+
 #### Control pipeline options
 
 You can control if table structure recognition or OCR should be performed by arguments passed to `DocumentConverter`:

{docling-1.2.0.dist-info → docling-1.3.0.dist-info}/RECORD

@@ -1,13 +1,13 @@
 docling/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/backend/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/backend/abstract_backend.py,sha256=dINr8oTax9Fq31Y1AR0CGWNZtAHN5aqB_M7TAPkJNVQ,1122
-docling/backend/docling_parse_backend.py,sha256=cupeYC1evzM31lXskH-mbXnZhw1_JHyUiJ-cpTmlrM4,5834
-docling/backend/pypdfium2_backend.py,sha256=cIQGFkwzceN57PzmACt06CytRo0A_t-im6rW804RC3M,7421
+docling/backend/abstract_backend.py,sha256=swwmXzNueZSHqEOvw4j-IFhP2OUJhBeB--gV7NtzKgo,1112
+docling/backend/docling_parse_backend.py,sha256=mGuJCpMVqyrZK-cXKRWrELPz0Wt1h6uydx4QwWI1rew,5912
+docling/backend/pypdfium2_backend.py,sha256=tv6JxyTkTdT2qr2ghsQgYA2zgpCDxKYSdHVBTAR7FSk,7411
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=k7gLFPnq3ArEMAFz6qUcp5qemlYzVhOmR9qtBTkAiX4,6862
+docling/datamodel/base_models.py,sha256=irZLAHdsROOOwRbywKIA0mk3H8GrLwtGjOgTV6G0QoU,7004
 docling/datamodel/document.py,sha256=FG_ntDFRBWj-MhV52D0sC8XaZOwN3yryyXahsVHGnyI,12517
 docling/datamodel/settings.py,sha256=t5g6wrEJnPa9gBzMMl8ppgBRUYz-8xgopEtfMS0ZH28,733
-docling/document_converter.py,sha256=I9vjTLCLahsMrcs9ozM3C5r_CtBN-9qHk7-ANma7fkc,9895
+docling/document_converter.py,sha256=dMucsq6M_nwPsC1ChogVwJgNDv8sJuFklQWWinDZaug,10246
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/ds_glm_model.py,sha256=wmb--2JKFQby-kvidw6PyM8wURPXYPQ_Z_eKKCBAdYQ,3192
 docling/models/easyocr_model.py,sha256=NaHVs8IN0eW9KB076E2Kae1s-bq74_4IMWueze9QqtE,2290
@@ -20,7 +20,7 @@ docling/pipeline/standard_model_pipeline.py,sha256=UTwodKUKrisLoVcntbNUBDhjzRyFv
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/utils/layout_utils.py,sha256=FOFbL0hKzUoWXdZaeUvEtFqKv0IkPifIr4sdGW4suKs,31804
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-1.2.0.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
-docling-1.2.0.dist-info/METADATA,sha256=9ZWFckdLpf45avuDgZgyzQK6J2oLCK0_oCW9T9Rx4iU,6802
-docling-1.2.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-1.2.0.dist-info/RECORD,,
+docling-1.3.0.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
+docling-1.3.0.dist-info/METADATA,sha256=wi2DOn77z_BIMSLsrmzebYZUgpjHYWbNTOIVEY3A4-o,7042
+docling-1.3.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-1.3.0.dist-info/RECORD,,