docling 1.16.0__tar.gz → 1.17.0__tar.gz

{docling-1.16.0 → docling-1.17.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.16.0
+Version: 1.17.0
 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 (>=1.2.0,<2.0.0)
-Requires-Dist: docling-parse (>=1.2.0,<2.0.0)
+Requires-Dist: docling-ibm-models (>=1.3.1,<2.0.0)
+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>
@@ -251,6 +250,28 @@ results = doc_converter.convert(conv_input)
 
 You can limit the CPU threads used by Docling by setting the environment variable `OMP_NUM_THREADS` accordingly. The default setting is using 4 CPU threads.
 
+### Chunking
+
+You can perform a hierarchy-aware chunking of a Docling document as follows:
+
+```python
+from docling.document_converter import DocumentConverter
+from docling_core.transforms.chunker import HierarchicalChunker
+
+doc = DocumentConverter().convert_single("https://arxiv.org/pdf/2206.01062").output
+chunks = list(HierarchicalChunker().chunk(doc))
+# > [
+# >     ChunkWithMetadata(
+# >         path='$.main-text[0]',
+# >         text='DocLayNet: A Large Human-Annotated Dataset [...]',
+# >         page=1,
+# >         bbox=[107.30, 672.38, 505.19, 709.08]
+# >     ),
+# >     [...]
+# > ]
+```
+
+
 ## Technical report
 
 For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).

{docling-1.16.0 → docling-1.17.0}/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>
@@ -207,6 +206,28 @@ results = doc_converter.convert(conv_input)
 
 You can limit the CPU threads used by Docling by setting the environment variable `OMP_NUM_THREADS` accordingly. The default setting is using 4 CPU threads.
 
+### Chunking
+
+You can perform a hierarchy-aware chunking of a Docling document as follows:
+
+```python
+from docling.document_converter import DocumentConverter
+from docling_core.transforms.chunker import HierarchicalChunker
+
+doc = DocumentConverter().convert_single("https://arxiv.org/pdf/2206.01062").output
+chunks = list(HierarchicalChunker().chunk(doc))
+# > [
+# >     ChunkWithMetadata(
+# >         path='$.main-text[0]',
+# >         text='DocLayNet: A Large Human-Annotated Dataset [...]',
+# >         page=1,
+# >         bbox=[107.30, 672.38, 505.19, 709.08]
+# >     ),
+# >     [...]
+# > ]
+```
+
+
 ## Technical report
 
 For more details on Docling's inner workings, check out the [Docling Technical Report](https://arxiv.org/abs/2408.09869).

{docling-1.16.0 → docling-1.17.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "docling"
-version = "1.16.0"  # DO NOT EDIT, updated automatically
+version = "1.17.0"  # 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 = "^1.2.0"
-deepsearch-glm = "^0.21.1"
+docling-ibm-models = "^1.3.1"
+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"