docling 1.16.0__py3-none-any.whl → 1.16.1__py3-none-any.whl

{docling-1.16.0.dist-info → docling-1.16.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: docling
-Version: 1.16.0
+Version: 1.16.1
 Summary: Docling PDF conversion package
 Home-page: https://github.com/DS4SD/docling
 License: MIT
@@ -22,7 +22,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Dist: certifi (>=2024.7.4)
 Requires-Dist: deepsearch-glm (>=0.21.1,<0.22.0)
 Requires-Dist: docling-core (>=1.6.2,<2.0.0)
-Requires-Dist: docling-ibm-models (>=1.2.0,<2.0.0)
+Requires-Dist: docling-ibm-models (>=1.3.1,<2.0.0)
 Requires-Dist: docling-parse (>=1.2.0,<2.0.0)
 Requires-Dist: easyocr (>=1.7,<2.0)
 Requires-Dist: filetype (>=1.2.0,<2.0.0)
@@ -251,6 +251,28 @@ 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.dist-info → docling-1.16.1.dist-info}/RECORD

@@ -25,8 +25,8 @@ 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-1.16.0.dist-info/LICENSE,sha256=mBb7ErEcM8VS9OhiGHnQ2kk75HwPhr54W1Oiz3965MY,1088
-docling-1.16.0.dist-info/METADATA,sha256=AESUBe1Ea2pC0vJvvNwLW7l_z26k3iriJiicLFU3U7E,13308
-docling-1.16.0.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-docling-1.16.0.dist-info/entry_points.txt,sha256=VOSzV77znM52dz5ysaDuJ0ijl1cnfrh1ZPg8od5OcTs,48
-docling-1.16.0.dist-info/RECORD,,
+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,,