scale-nucleus 0.17.9__tar.gz → 0.17.10__tar.gz

{scale_nucleus-0.17.9 → scale_nucleus-0.17.10}/PKG-INFO

@@ -1,8 +1,7 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: scale-nucleus
-Version: 0.17.9
+Version: 0.17.10
 Summary: The official Python client library for Nucleus, the Data Platform for AI
-Home-page: https://scale.com/nucleus
 License: MIT
 Author: Scale AI Nucleus Team
 Author-email: nucleusapi@scaleapi.com
@@ -14,6 +13,8 @@ Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
 Provides-Extra: launch
 Provides-Extra: metrics
 Requires-Dist: Pillow (>=7.1.2)
@@ -36,6 +37,7 @@ Requires-Dist: scipy (>=1.4.1) ; extra == "metrics"
 Requires-Dist: shellingham (>=1.4.0,<2.0.0)
 Requires-Dist: tqdm (>=4.41.0,<5.0.0)
 Project-URL: Documentation, https://dashboard.scale.com/nucleus/docs/api
+Project-URL: Homepage, https://scale.com/nucleus
 Project-URL: Repository, https://github.com/scaleapi/nucleus-python-client
 Description-Content-Type: text/markdown
 

{scale_nucleus-0.17.9 → scale_nucleus-0.17.10}/nucleus/dataset.py

@@ -1518,6 +1518,7 @@ class Dataset:
         query: Optional[str] = None,
         use_mirrored_images: bool = False,
         only_most_recent_tasks: bool = True,
+        page_size=10000
     ) -> Iterable[Dict[str, Union[DatasetItem, Dict[str, List[Annotation]]]]]:
         """Provides a generator of all DatasetItems and Annotations in the dataset.
 
@@ -1525,6 +1526,7 @@ class Dataset:
             query: Structured query compatible with the `Nucleus query language <https://nucleus.scale.com/docs/query-language-reference>`_.
             use_mirrored_images: If True, returns the location of the mirrored image hosted in Scale S3. Useful when the original image is no longer available.
             only_most_recent_tasks: If True, only the annotations corresponding to the most recent task for each item is returned.
+            page_size: Number of items to fetch per page. Default is maximum ES page size of 10000.
 
         Returns:
             Generator where each element is a dict containing the DatasetItem
@@ -1548,7 +1550,7 @@ class Dataset:
             client=self._client,
             endpoint=f"dataset/{self.id}/exportForTrainingPage",
             result_key=EXPORT_FOR_TRAINING_KEY,
-            page_size=10000,  # max ES page size
+            page_size=page_size,  # default is max ES page size of 10000
             query=query,
             chip=use_mirrored_images,
             onlyMostRecentTask=only_most_recent_tasks,

{scale_nucleus-0.17.9 → scale_nucleus-0.17.10}/pyproject.toml

@@ -25,7 +25,7 @@ ignore = ["E501", "E741", "E731", "F401"]  # Easy ignore for getting it running
 
 [tool.poetry]
 name = "scale-nucleus"
-version = "0.17.9"
+version = "0.17.10"
 description = "The official Python client library for Nucleus, the Data Platform for AI"
 license =  "MIT"
 authors = ["Scale AI Nucleus Team <nucleusapi@scaleapi.com>"]