docling 1.16.1__tar.gz → 1.18.0__tar.gz

{docling-1.16.1 → docling-1.18.0}/PKG-INFO

@@ -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 → docling-1.18.0}/README.md

@@ -33,8 +33,7 @@ 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 → docling-1.18.0}/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-1.16.1 → docling-1.18.0}/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-1.16.1 → docling-1.18.0}/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 → docling-1.18.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.16.1"  # DO NOT EDIT, updated automatically
+version = "1.18.0"  # 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"
@@ -38,15 +38,15 @@ torchvision = [
 python = "^3.10"
 pydantic = "^2.0.0"
 docling-core = "^1.6.2"
-docling-ibm-models = "^1.3.1"
-deepsearch-glm = "^0.21.1"
+docling-ibm-models = "^2.0.0"
+deepsearch-glm = "^0.22.0"
 filetype = "^1.2.0"
 pypdfium2 = "^4.30.0"
 pydantic-settings = "^2.3.0"
 huggingface_hub = ">=0.23,<1"
 requests = "^2.32.3"
 easyocr = "^1.7"
-docling-parse = "^1.2.0"
+docling-parse = "^1.4.1"
 certifi = ">=2024.7.4"
 rtree = "^1.3.0"
 scipy = "^1.14.1"