docling 1.16.1__py3-none-any.whl → 1.18.0__py3-none-any.whl

docling/document_converter.py

@@ -67,7 +67,10 @@ class DocumentConverter:
         from huggingface_hub import snapshot_download
 
         download_path = snapshot_download(
-            repo_id="ds4sd/docling-models", force_download=force, local_dir=local_dir
+            repo_id="ds4sd/docling-models",
+            force_download=force,
+            local_dir=local_dir,
+            revision="v2.0.0",
         )
 
         return Path(download_path)

docling/models/layout_model.py

@@ -33,6 +33,7 @@ class LayoutModel:
         "Page-footer",
         "Code",
         "List-item",
+        # "Title"
         # "Formula",
     ]
     PAGE_HEADER_LABELS = ["Page-header", "Page-footer"]
@@ -69,9 +70,7 @@ class LayoutModel:
             "Key-Value Region": 0.45,
         }
 
-        CLASS_REMAPPINGS = {
-            "Document Index": "Table",
-        }
+        CLASS_REMAPPINGS = {"Document Index": "Table", "Title": "Section-header"}
 
         _log.debug("================= Start postprocess function ====================")
         start_time = time.time()
@@ -277,6 +276,7 @@ class LayoutModel:
                     bbox=BoundingBox.model_validate(pred_item),
                     cells=[],
                 )
+
                 clusters.append(cluster)
 
             # Map cells to clusters

docling/pipeline/standard_model_pipeline.py

@@ -8,7 +8,7 @@ from docling.pipeline.base_model_pipeline import BaseModelPipeline
 
 
 class StandardModelPipeline(BaseModelPipeline):
-    _layout_model_path = "model_artifacts/layout/beehive_v0.0.5"
+    _layout_model_path = "model_artifacts/layout/beehive_v0.0.5_pt"
     _table_model_path = "model_artifacts/tableformer"
 
     def __init__(self, artifacts_path: Path, pipeline_options: PipelineOptions):

{docling-1.16.1.dist-info → docling-1.18.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.16.1
+Version: 1.18.0
 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 (>=0.21.1,<0.22.0)
+Requires-Dist: deepsearch-glm (>=0.22.0,<0.23.0)
 Requires-Dist: docling-core (>=1.6.2,<2.0.0)
-Requires-Dist: docling-ibm-models (>=1.3.1,<2.0.0)
-Requires-Dist: docling-parse (>=1.2.0,<2.0.0)
+Requires-Dist: docling-ibm-models (>=2.0.0,<3.0.0)
+Requires-Dist: docling-parse (>=1.4.1,<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)
@@ -77,8 +77,7 @@ To use Docling, simply install `docling` from your package manager, e.g. pip:
 pip install docling
 ```
 
-> [!NOTE]
-> Works on macOS and Linux environments. Windows platforms are currently not tested.
+Works on macOS, Linux and Windows environments. Both x86_64 and arm64 architectures.
 
 <details>
   <summary><b>Alternative PyTorch distributions</b></summary>

{docling-1.16.1.dist-info → docling-1.18.0.dist-info}/RECORD

@@ -10,23 +10,23 @@ docling/datamodel/base_models.py,sha256=b2FXRhfHrJiBGr5OdlSJ1ssUzvU2rVjelfY5_0Yo
 docling/datamodel/document.py,sha256=8iHylLaty-ZVYGzYmP61dZPtduzEyiRM79Tx3gS9UEU,16195
 docling/datamodel/pipeline_options.py,sha256=SuJzaLHTR_-ZZz8KB0wwYRxULTcnfQESiilOGCY0fpc,773
 docling/datamodel/settings.py,sha256=t5g6wrEJnPa9gBzMMl8ppgBRUYz-8xgopEtfMS0ZH28,733
-docling/document_converter.py,sha256=bk345OKkHbBngc3QS6BevT8068yEt1cS-PtAH3k_tCo,11022
+docling/document_converter.py,sha256=teQajQorH-SKBJWuPeqQXAscGGDT9_-wtn2nsPThH00,11078
 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=VXGmj8cW0WKMz1He4tp1lZhXHkS8Z39U1G-ujkc7deU,3368
 docling/models/easyocr_model.py,sha256=ABIqALvtNNrDQ47fXaZ0lDFhOwKsYGUUlAPnIsFZgZA,2232
-docling/models/layout_model.py,sha256=ZFmaLXlRWUfsT1pJCiYVxhQFrBBsiz6Aw0m9GM3UvVM,11249
+docling/models/layout_model.py,sha256=5wCohyzGK1p5F5cTRY5QWbW2AI4eevXobJDJdSLhX7k,11272
 docling/models/page_assemble_model.py,sha256=8eoG2WiFxPxq9TPvM-wkngb2gkr0tdtCRVXg1JcTETo,5550
 docling/models/table_structure_model.py,sha256=iHJjWdKCpTcH3l_ElMWnC5pt6tkUpIuByed304Fdq9w,6009
 docling/pipeline/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/pipeline/base_model_pipeline.py,sha256=rrMog3EuiR5Gx9OWtfMj24rQvHCrWkxZ3g9OIr7LPSQ,607
-docling/pipeline/standard_model_pipeline.py,sha256=9HdUq9TjNOsE9ixA_MpWNmyQUaTg7SS-aVE0zP7Ujys,1522
+docling/pipeline/standard_model_pipeline.py,sha256=u-0llxQCTqK0qZxVcoqcyPb8V09nbUy9nEH9d-xNlzk,1525
 docling/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 docling/utils/export.py,sha256=bKLdbeUcR-rQsGPV1IqJkCHKMCv7X2QOHyxmjNuH3HE,4655
 docling/utils/layout_utils.py,sha256=FOFbL0hKzUoWXdZaeUvEtFqKv0IkPifIr4sdGW4suKs,31804
 docling/utils/utils.py,sha256=llhXSbIDNZ1MHOwBEfLHBAoJIAYI7QlPIonlI1jLUJ0,1208
-docling-1.16.1.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-1.16.1.dist-info/METADATA,sha256=vWzWfsormCgPWMFxCeQ0nMwPnbn0T3tc7yTLsiNz95s,13908
-docling-1.16.1.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-1.16.1.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-1.16.1.dist-info/RECORD,,
+docling-1.18.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
+docling-1.18.0.dist-info/METADATA,sha256=RhDTszEvg9lbUg0PDmlXUvE1277zONpQNHBhR8uFE84,13898
+docling-1.18.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+docling-1.18.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
+docling-1.18.0.dist-info/RECORD,,