docling 1.8.3__py3-none-any.whl → 1.8.5__py3-none-any.whl

docling/datamodel/base_models.py

@@ -238,9 +238,9 @@ class EquationPrediction(BaseModel):
 
 class PagePredictions(BaseModel):
     layout: LayoutPrediction = None
-    tablestructure: TableStructurePrediction = None
-    figures_classification: FigureClassificationPrediction = None
-    equations_prediction: EquationPrediction = None
+    tablestructure: Optional[TableStructurePrediction] = None
+    figures_classification: Optional[FigureClassificationPrediction] = None
+    equations_prediction: Optional[EquationPrediction] = None
 
 
 PageElement = Union[TextElement, TableElement, FigureElement]

docling/datamodel/document.py

@@ -222,6 +222,8 @@ class ConvertedDocument(BaseModel):
                                 celltype = "col_header"
                             elif cell.row_header:
                                 celltype = "row_header"
+                            elif cell.row_section:
+                                celltype = "row_section"
 
                             def make_spans(cell):
                                 for rspan in range(

docling/models/ds_glm_model.py

@@ -16,8 +16,12 @@ from docling.datamodel.document import ConversionResult
 class GlmModel:
     def __init__(self, config):
         self.config = config
+        self.model_names = self.config.get(
+            "model_names", ""
+        )  # "language;term;reference"
         load_pretrained_nlp_models()
-        model = init_nlp_model(model_names="language;term;reference")
+        # model = init_nlp_model(model_names="language;term;reference")
+        model = init_nlp_model(model_names=self.model_names)
         self.model = model
 
     def __call__(self, conv_res: ConversionResult) -> DsDocument:

docling/models/table_structure_model.py

@@ -44,7 +44,16 @@ class TableStructureModel:
 
             for tc in table_element.table_cells:
                 x0, y0, x1, y1 = tc.bbox.as_tuple()
-                draw.rectangle([(x0, y0), (x1, y1)], outline="blue")
+                if tc.column_header:
+                    width = 3
+                else:
+                    width = 1
+                draw.rectangle([(x0, y0), (x1, y1)], outline="blue", width=width)
+                draw.text(
+                    (x0 + 3, y0 + 3),
+                    text=f"{tc.start_row_offset_idx}, {tc.start_col_offset_idx}",
+                    fill="black",
+                )
 
         image.show()
 

{docling-1.8.3.dist-info → docling-1.8.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.8.3
+Version: 1.8.5
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -20,10 +20,10 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Dist: certifi (>=2024.7.4)
-Requires-Dist: deepsearch-glm (>=0.19.0,<1)
+Requires-Dist: deepsearch-glm (>=0.19.1,<0.20.0)
 Requires-Dist: docling-core (>=1.1.2,<2.0.0)
 Requires-Dist: docling-ibm-models (>=1.1.3,<2.0.0)
-Requires-Dist: docling-parse (>=1.1.1,<2.0.0)
+Requires-Dist: docling-parse (>=1.1.3,<2.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
 Requires-Dist: huggingface_hub (>=0.23,<1)
@@ -72,6 +72,23 @@ pip install docling
 > [!NOTE]
 > Works on macOS and Linux environments. Windows platforms are currently not tested.
 
+
+### Use alternative PyTorch distributions
+
+The Docling models depend on the [PyTorch](https://pytorch.org/) library.
+Depending on your architecture, you might want to use a different distribution of `torch`.
+For example, you might want support for different accelerator or for a cpu-only version.
+All the different ways for installing `torch` are listed on their website <https://pytorch.org/>.
+
+One common situation is the installation on Linux systems with cpu-only support.
+In this case, we suggest the installation of Docling with the following options
+
+```bash
+# Example for installing on the Linux cpu-only version
+pip install docling --extra-index-url https://download.pytorch.org/whl/cpu
+```
+
+
 ### Development setup
 
 To develop for Docling, you need Python 3.10 / 3.11 / 3.12 and Poetry. You can then install from your local clone's root dir:

{docling-1.8.3.dist-info → docling-1.8.5.dist-info}/RECORD

@@ -4,24 +4,24 @@ docling/backend/abstract_backend.py,sha256=xfNNiZKksPPa9KAiA-fHD86flg0It4n_29ccp
 docling/backend/docling_parse_backend.py,sha256=r3aJwsWR7qG47ElhOa9iQJJQauHMt950FfCsf6fhlP4,7480
 docling/backend/pypdfium2_backend.py,sha256=FggVFitmyMMmLar6vk6XQsavGOPQx95TD14opWYRMAY,8837
 docling/datamodel/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-docling/datamodel/base_models.py,sha256=F3iF7cQRvdO5RaPnrXballaTvnWkPTXnX-n9N4cpCGo,8842
-docling/datamodel/document.py,sha256=D-uG2-ChUfq_M5APzwprQ3Mf71qXQh9-9lFmZqua9s0,13541
+docling/datamodel/base_models.py,sha256=K2lb2itk_VtJ7Zjz9a5zXgsCQ4PCTwf2blT-gI4UIRs,8872
+docling/datamodel/document.py,sha256=cG9RuAkFXCCGZqCHmhUtYeOA5PV6gjO3Y4i5lf2IM6I,13649
 docling/datamodel/settings.py,sha256=t5g6wrEJnPa9gBzMMl8ppgBRUYz-8xgopEtfMS0ZH28,733
 docling/document_converter.py,sha256=5OiNafoaVcQhZ8ATF69xRp2KyFyKeSMhmwEFUoCzP-k,10980
 docling/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/models/base_ocr_model.py,sha256=Ipl82a3AV2OsgMQSMEMpnWJ6MXcmyIQzmp52PmTaB0g,4465
-docling/models/ds_glm_model.py,sha256=BszxBcUZPUFgDqngGLbS5pSRyOCkPxRrCi4zP7Vm8DY,3191
+docling/models/ds_glm_model.py,sha256=inNsmlriiDuqe3Q4LWL2DbqPTScP-3-dFgFoaJprFtQ,3367
 docling/models/easyocr_model.py,sha256=ABIqALvtNNrDQ47fXaZ0lDFhOwKsYGUUlAPnIsFZgZA,2232
 docling/models/layout_model.py,sha256=ZFmaLXlRWUfsT1pJCiYVxhQFrBBsiz6Aw0m9GM3UvVM,11249
 docling/models/page_assemble_model.py,sha256=8eoG2WiFxPxq9TPvM-wkngb2gkr0tdtCRVXg1JcTETo,5550
-docling/models/table_structure_model.py,sha256=5jzTlpM-GdCSq4l0vD1W6aSPTJXeTcXEnNuPxnw-DlA,5437
+docling/models/table_structure_model.py,sha256=0wOeiRoma6et7FtoJZw2SA3wBd9-R9ivp5uvXBQqeM4,5768
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/pipeline/base_model_pipeline.py,sha256=AC5NTR0xLy5JIZqsTINkKEHeCPqpyvJpuE_bcnZhyvI,529
 docling/pipeline/standard_model_pipeline.py,sha256=UTjyaEXvz9htYZz-IMTkn11cZwNjgvo_Fl2dfBVnRQs,1442
 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-1.8.3.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
-docling-1.8.3.dist-info/METADATA,sha256=Fu6pbBLgaPyap2al5TA6SKn5xYUDquVHD8VODfGmVAM,7180
-docling-1.8.3.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-1.8.3.dist-info/RECORD,,
+docling-1.8.5.dist-info/LICENSE,sha256=ACwmltkrXIz5VsEQcrqljq-fat6ZXAMepjXGoe40KtE,1069
+docling-1.8.5.dist-info/METADATA,sha256=-H_jbB493OWBMNwkFqmb8KNqXcv7p32AykV_biiFNPA,7888
+docling-1.8.5.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-1.8.5.dist-info/RECORD,,