I think i fixed the errors in circleci

Author: Diego Ardila

nucleus/__init__.py

@@ -50,89 +50,83 @@
 geometry        |   dict    |   Representation of the bounding box in the Box2DGeometry format.\n
 metadata        |   dict    |   An arbitrary metadata blob for the annotation.\n
 """
-__version__ = "0.1.0"
-
 import json
 import logging
-import warnings
 import os
-from typing import List, Union, Dict, Callable, Any, Optional
-
-import tqdm
-import tqdm.notebook as tqdm_notebook
+import warnings
+from typing import Any, Callable, Dict, List, Optional, Union
 
 import grequests
+import pkg_resources
 import requests
+import tqdm
+import tqdm.notebook as tqdm_notebook
 from requests.adapters import HTTPAdapter
 
 # pylint: disable=E1101
 # TODO: refactor to reduce this file to under 1000 lines.
 # pylint: disable=C0302
 from requests.packages.urllib3.util.retry import Retry
 
-from .constants import REFERENCE_IDS_KEY, DATASET_ITEM_IDS_KEY, UPDATE_KEY
-from .dataset import Dataset
-from .dataset_item import DatasetItem
 from .annotation import (
     BoxAnnotation,
     PolygonAnnotation,
-    SegmentationAnnotation,
     Segment,
-)
-from .prediction import (
-    BoxPrediction,
-    PolygonPrediction,
-    SegmentationPrediction,
-)
-from .model_run import ModelRun
-from .slice import Slice
-from .upload_response import UploadResponse
-from .payload_constructor import (
-    construct_append_payload,
-    construct_annotation_payload,
-    construct_model_creation_payload,
-    construct_box_predictions_payload,
-    construct_segmentation_payload,
+    SegmentationAnnotation,
 )
 from .constants import (
-    NUCLEUS_ENDPOINT,
+    ANNOTATION_METADATA_SCHEMA_KEY,
+    ANNOTATIONS_IGNORED_KEY,
+    ANNOTATIONS_PROCESSED_KEY,
+    AUTOTAGS_KEY,
+    DATASET_ID_KEY,
+    DATASET_ITEM_IDS_KEY,
     DEFAULT_NETWORK_TIMEOUT_SEC,
-    ERRORS_KEY,
+    EMBEDDINGS_URL_KEY,
     ERROR_ITEMS,
     ERROR_PAYLOAD,
-    ITEMS_KEY,
-    ITEM_KEY,
+    ERRORS_KEY,
     IMAGE_KEY,
     IMAGE_URL_KEY,
-    DATASET_ID_KEY,
+    ITEM_METADATA_SCHEMA_KEY,
+    ITEMS_KEY,
     MODEL_RUN_ID_KEY,
-    DATASET_ITEM_ID_KEY,
-    SLICE_ID_KEY,
-    ANNOTATIONS_PROCESSED_KEY,
-    ANNOTATIONS_IGNORED_KEY,
-    PREDICTIONS_PROCESSED_KEY,
+    NAME_KEY,
+    NUCLEUS_ENDPOINT,
     PREDICTIONS_IGNORED_KEY,
+    PREDICTIONS_PROCESSED_KEY,
+    REFERENCE_IDS_KEY,
+    SLICE_ID_KEY,
     STATUS_CODE_KEY,
-    SUCCESS_STATUS_CODES,
-    DATASET_NAME_KEY,
-    DATASET_MODEL_RUNS_KEY,
-    DATASET_SLICES_KEY,
-    DATASET_LENGTH_KEY,
-    NAME_KEY,
-    ANNOTATIONS_KEY,
-    AUTOTAGS_KEY,
-    ANNOTATION_METADATA_SCHEMA_KEY,
-    ITEM_METADATA_SCHEMA_KEY,
-    EMBEDDINGS_URL_KEY,
+    UPDATE_KEY,
 )
-from .model import Model
+from .dataset import Dataset
+from .dataset_item import DatasetItem
 from .errors import (
+    DatasetItemRetrievalError,
     ModelCreationError,
     ModelRunCreationError,
-    DatasetItemRetrievalError,
     NotFoundError,
     NucleusAPIError,
 )
+from .model import Model
+from .model_run import ModelRun
+from .payload_constructor import (
+    construct_annotation_payload,
+    construct_append_payload,
+    construct_box_predictions_payload,
+    construct_model_creation_payload,
+    construct_segmentation_payload,
+)
+from .prediction import (
+    BoxPrediction,
+    PolygonPrediction,
+    SegmentationPrediction,
+)
+from .slice import Slice
+from .upload_response import UploadResponse
+
+__version__ = pkg_resources.get_distribution("scale-nucleus").version
 
 logger = logging.getLogger(__name__)
 logging.basicConfig()
@@ -236,6 +230,8 @@ def get_model_run(self, model_run_id: str, dataset_id: str) -> ModelRun:
         """
         Fetches a model_run for given id
         :param model_run_id: internally controlled model_run_id
+        :param dataset_id: the dataset id which may determine the prediction schema
+            for this model run if present on the dataset.
         :return: model_run
         """
         return ModelRun(model_run_id, dataset_id, self)

nucleus/dataset.py

@@ -23,6 +23,7 @@
 )
 from .dataset_item import (
     DatasetItem,
+    check_all_paths_remote,
     check_for_duplicate_reference_ids,
 )
 from .payload_constructor import construct_model_run_creation_payload
@@ -196,6 +197,7 @@ def append(
         check_for_duplicate_reference_ids(dataset_items)
 
         if asynchronous:
+            check_all_paths_remote(dataset_items)
             request_id = serialize_and_write_to_presigned_url(
                 dataset_items, self.id, self._client
             )

nucleus/model_run.py

@@ -8,9 +8,9 @@
     ANNOTATIONS_KEY,
     BOX_TYPE,
     DEFAULT_ANNOTATION_UPDATE_MODE,
-    MASK_TYPE,
     POLYGON_TYPE,
     REQUEST_ID_KEY,
+    SEGMENTATION_TYPE,
     UPDATE_KEY,
 )
 from .prediction import (
@@ -175,7 +175,7 @@ def _format_prediction_response(
         ] = {
             BOX_TYPE: BoxPrediction,
             POLYGON_TYPE: PolygonPrediction,
-            MASK_TYPE: SegmentationPrediction,
+            SEGMENTATION_TYPE: SegmentationPrediction,
         }
         for type_key in annotation_payload:
             type_class = type_key_to_class[type_key]

pyproject.toml

@@ -21,7 +21,7 @@ exclude = '''
 
 [tool.poetry]
 name = "scale-nucleus"
-version = "0.1.4"
+version = "0.1.5"
 description = "The official Python client library for Nucleus, the Data Platform for AI"
 license =  "MIT"
 authors = ["Scale AI Nucleus Team <nucleusapi@scaleapi.com>"]

tests/test_dataset.py

@@ -190,11 +190,11 @@ def test_dataset_append_async_with_1_bad_url(dataset: Dataset):
             "started_image_processing": f"Dataset: {dataset.id}, Job: {job.id}",
         },
     }
-    assert job.errors() == [
-        "One or more of the images you attempted to upload did not process correctly. Please see the status for an overview and the errors for more detailed messages.",
-        # Todo: figure out why this error isn't propagating from image upload.
-        'Failure when processing the image "https://looks.ok.but.is.not.accessible": {}',
-    ]
+    # The error is fairly detailed and subject to change. What's important is we surface which URLs failed.
+    assert (
+        'Failure when processing the image "https://looks.ok.but.is.not.accessible"'
+        in str(job.errors())
+    )
 
 
 def test_dataset_list_autotags(CLIENT, dataset):