docling 1.2.0__tar.gz → 1.3.0__tar.gz

{docling-1.2.0 → docling-1.3.0}/PKG-INFO

@@ -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 → docling-1.3.0}/README.md

@@ -56,17 +56,21 @@ 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 → docling-1.3.0}/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-1.2.0 → docling-1.3.0}/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-1.2.0 → docling-1.3.0}/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-1.2.0 → docling-1.3.0}/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-1.2.0 → docling-1.3.0}/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 → docling-1.3.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.2.0"  # DO NOT EDIT, updated automatically
+version = "1.3.0"  # DO NOT EDIT, updated automatically
 description = "Docling PDF conversion package"
 authors = ["Christoph Auer <cau@zurich.ibm.com>", "Michele Dolfi <dol@zurich.ibm.com>", "Maxim Lysak <mly@zurich.ibm.com>", "Nikos Livathinos <nli@zurich.ibm.com>", "Ahmed Nassar <ahn@zurich.ibm.com>", "Peter Staar <taa@zurich.ibm.com>"]
 license = "MIT"
@@ -33,6 +33,7 @@ huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = { version = "^1.7", optional = true }
 docling-parse = "^0.0.1"
+certifi = ">=2024.7.4"
 
 [tool.poetry.group.dev.dependencies]
 black = {extras = ["jupyter"], version = "^24.4.2"}