Merge branch 'master' into dependabot/pip/requirements/extras/transformers-4.36.0

Author: mufaddal-rohawala

.github/ISSUE_TEMPLATE/bug_report.md

@@ -12,6 +12,7 @@ A clear and concise description of what the bug is.
 
 **To reproduce**
 A clear, step-by-step set of instructions to reproduce the bug.
+The provided code need to be **complete** and **runnable**, if additional data is needed, please include them in the issue.
 
 **Expected behavior**
 A clear and concise description of what you expected to happen.

CHANGELOG.md

@@ -1,5 +1,42 @@
 # Changelog
 
+## v2.203.0 (2023-12-28)
+
+### Features
+
+ * support local mode in SageMaker Studio (#1300)
+ * Supporting tbac in load_run
+
+### Bug Fixes and Other Changes
+
+ * update image_uri_configs  12-25-2023 06:17:33 PST
+ * Disable failed test in IR
+ * Raise Exception for debug
+ * create role if needed in `get_execution_role`
+
+## v2.202.1 (2023-12-22)
+
+### Bug Fixes and Other Changes
+
+ * update image_uri_configs  12-22-2023 06:17:35 PST
+ * update model path in local mode
+ * Using logging instead of prints
+
+### Documentation Changes
+
+ * update issue template.
+
+## v2.202.0 (2023-12-21)
+
+### Features
+
+ * support remote debug for sagemaker training job
+
+### Bug Fixes and Other Changes
+
+ * update image_uri_configs  12-21-2023 08:32:41 PST
+ * Update tblib constraint
+
 ## v2.201.0 (2023-12-20)
 
 ### Features

VERSION

@@ -1 +1 @@
-2.201.1.dev0
+2.203.1.dev0

setup.cfg

@@ -10,6 +10,3 @@ test=pytest
 [metadata]
 description_file = README.rst
 license_files = LICENSE.txt
-
-[wheel]
-universal = 1

setup.py

@@ -63,7 +63,7 @@ def read_requirements(filename):
     "PyYAML~=6.0",
     "jsonschema",
     "platformdirs",
-    "tblib==1.7.0",
+    "tblib>=1.7.0,<3",
     "urllib3<1.27",
     "uvicorn==0.22.0",
     "fastapi==0.95.2",

src/sagemaker/algorithm.py

@@ -28,6 +28,7 @@
 from sagemaker.session import Session
 from sagemaker.workflow.entities import PipelineVariable
 from sagemaker.workflow.pipeline_context import runnable_by_pipeline
+from sagemaker.utils import format_tags, Tags
 
 from sagemaker.workflow import is_pipeline_variable
 
@@ -58,7 +59,7 @@ def __init__(
         base_job_name: Optional[str] = None,
         sagemaker_session: Optional[Session] = None,
         hyperparameters: Optional[Dict[str, Union[str, PipelineVariable]]] = None,
-        tags: Optional[List[Dict[str, Union[str, PipelineVariable]]]] = None,
+        tags: Optional[Tags] = None,
         subnets: Optional[List[Union[str, PipelineVariable]]] = None,
         security_group_ids: Optional[List[Union[str, PipelineVariable]]] = None,
         model_uri: Optional[str] = None,
@@ -121,7 +122,7 @@ def __init__(
                 interactions with Amazon SageMaker APIs and any other AWS services needed. If
                 not specified, the estimator creates one using the default
                 AWS configuration chain.
-            tags (list[dict[str, str] or list[dict[str, PipelineVariable]]): List of tags for
+            tags (Union[Tags]): Tags for
                 labeling a training job. For more, see
                 https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html.
             subnets (list[str] or list[PipelineVariable]): List of subnet ids. If not specified
@@ -170,7 +171,7 @@ def __init__(
             output_kms_key=output_kms_key,
             base_job_name=base_job_name,
             sagemaker_session=sagemaker_session,
-            tags=tags,
+            tags=format_tags(tags),
             subnets=subnets,
             security_group_ids=security_group_ids,
             model_uri=model_uri,
@@ -391,7 +392,7 @@ def transformer(
             if self._is_marketplace():
                 transform_env = None
 
-            tags = tags or self.tags
+            tags = format_tags(tags) or self.tags
         else:
             raise RuntimeError("No finished training job found associated with this estimator")
 

src/sagemaker/apiutils/_base_types.py

@@ -14,6 +14,7 @@
 from __future__ import absolute_import
 
 from sagemaker.apiutils import _boto_functions, _utils
+from sagemaker.utils import format_tags
 
 
 class ApiObject(object):
@@ -194,13 +195,13 @@ def _set_tags(self, resource_arn=None, tags=None):
 
         Args:
             resource_arn (str): The arn of the Record
-            tags (dict): An array of Tag objects that set to Record
+            tags (Optional[Tags]): An array of Tag objects that set to Record
 
         Returns:
             A list of key, value pair objects. i.e. [{"key":"value"}]
         """
         tag_list = self.sagemaker_session.sagemaker_client.add_tags(
-            ResourceArn=resource_arn, Tags=tags
+            ResourceArn=resource_arn, Tags=format_tags(tags)
         )["Tags"]
         return tag_list
 

src/sagemaker/automl/automl.py

@@ -28,7 +28,7 @@
 )
 from sagemaker.job import _Job
 from sagemaker.session import Session
-from sagemaker.utils import name_from_base, resolve_value_from_config
+from sagemaker.utils import name_from_base, resolve_value_from_config, format_tags, Tags
 from sagemaker.workflow.entities import PipelineVariable
 from sagemaker.workflow.pipeline_context import runnable_by_pipeline
 
@@ -127,7 +127,7 @@ def __init__(
         total_job_runtime_in_seconds: Optional[int] = None,
         job_objective: Optional[Dict[str, str]] = None,
         generate_candidate_definitions_only: Optional[bool] = False,
-        tags: Optional[List[Dict[str, str]]] = None,
+        tags: Optional[Tags] = None,
         content_type: Optional[str] = None,
         s3_data_type: Optional[str] = None,
         feature_specification_s3_uri: Optional[str] = None,
@@ -167,8 +167,7 @@ def __init__(
                 In the format of: {"MetricName": str}
             generate_candidate_definitions_only (bool): Whether to generates
                 possible candidates without training the models.
-            tags (List[dict[str, str]]): The list of tags to attach to this
-                specific endpoint.
+            tags (Optional[Tags]): Tags to attach to this specific endpoint.
             content_type (str): The content type of the data from the input source.
             s3_data_type (str): The data type for S3 data source.
                 Valid values: ManifestFile or S3Prefix.
@@ -203,7 +202,7 @@ def __init__(
         self.target_attribute_name = target_attribute_name
         self.job_objective = job_objective
         self.generate_candidate_definitions_only = generate_candidate_definitions_only
-        self.tags = tags
+        self.tags = format_tags(tags)
         self.content_type = content_type
         self.s3_data_type = s3_data_type
         self.feature_specification_s3_uri = feature_specification_s3_uri
@@ -332,7 +331,7 @@ def attach(cls, auto_ml_job_name, sagemaker_session=None):
             total_job_runtime_in_seconds=auto_ml_job_desc.get("AutoMLJobConfig", {})
             .get("CompletionCriteria", {})
             .get("MaxAutoMLJobRuntimeInSeconds"),
-            job_objective=auto_ml_job_desc.get("AutoMLJobObjective", {}).get("MetricName"),
+            job_objective=auto_ml_job_desc.get("AutoMLJobObjective", {}),
             generate_candidate_definitions_only=auto_ml_job_desc.get(
                 "GenerateCandidateDefinitionsOnly", False
             ),
@@ -581,7 +580,7 @@ def deploy(
                 be selected on each ``deploy``.
             endpoint_name (str): The name of the endpoint to create (default:
                 None). If not specified, a unique endpoint name will be created.
-            tags (List[dict[str, str]]): The list of tags to attach to this
+            tags (Optional[Tags]): The list of tags to attach to this
                 specific endpoint.
             wait (bool): Whether the call should wait until the deployment of
                 model completes (default: True).
@@ -633,7 +632,7 @@ def deploy(
             deserializer=deserializer,
             endpoint_name=endpoint_name,
             kms_key=model_kms_key,
-            tags=tags,
+            tags=format_tags(tags),
             wait=wait,
             volume_size=volume_size,
             model_data_download_timeout=model_data_download_timeout,

src/sagemaker/base_predictor.py

@@ -53,7 +53,7 @@
     NumpySerializer,
 )
 from sagemaker.session import production_variant, Session
-from sagemaker.utils import name_from_base, stringify_object
+from sagemaker.utils import name_from_base, stringify_object, format_tags
 
 from sagemaker.model_monitor.model_monitoring import DEFAULT_REPOSITORY_NAME
 
@@ -63,6 +63,9 @@
 LOGGER = logging.getLogger("sagemaker")
 
 
+logger = logging.getLogger(__name__)
+
+
 class PredictorBase(abc.ABC):
     """An object that encapsulates a deployed model."""
 
@@ -406,7 +409,7 @@ def update_endpoint(
         self.sagemaker_session.create_endpoint_config_from_existing(
             current_endpoint_config_name,
             new_endpoint_config_name,
-            new_tags=tags,
+            new_tags=format_tags(tags),
             new_kms_key=kms_key,
             new_data_capture_config_dict=data_capture_config_dict,
             new_production_variants=production_variants,
@@ -714,7 +717,7 @@ def list_monitors(self):
             endpoint_name=self.endpoint_name
         )
         if len(monitoring_schedules_dict["MonitoringScheduleSummaries"]) == 0:
-            print("No monitors found for endpoint. endpoint: {}".format(self.endpoint_name))
+            logger.debug("No monitors found for endpoint. endpoint: %s", self.endpoint_name)
             return []
 
         monitors = []

src/sagemaker/clarify.py

@@ -33,6 +33,7 @@
 from sagemaker.session import Session
 from sagemaker.network import NetworkConfig
 from sagemaker.processing import ProcessingInput, ProcessingOutput, Processor
+from sagemaker.utils import format_tags, Tags
 
 logger = logging.getLogger(__name__)
 
@@ -1417,7 +1418,7 @@ def __init__(
         max_runtime_in_seconds: Optional[int] = None,
         sagemaker_session: Optional[Session] = None,
         env: Optional[Dict[str, str]] = None,
-        tags: Optional[List[Dict[str, str]]] = None,
+        tags: Optional[Tags] = None,
         network_config: Optional[NetworkConfig] = None,
         job_name_prefix: Optional[str] = None,
         version: Optional[str] = None,
@@ -1454,7 +1455,7 @@ def __init__(
                 using the default AWS configuration chain.
             env (dict[str, str]): Environment variables to be passed to
                 the processing jobs (default: None).
-            tags (list[dict]): List of tags to be passed to the processing job
+            tags (Optional[Tags]): Tags to be passed to the processing job
                 (default: None). For more, see
                 https://docs.aws.amazon.com/sagemaker/latest/dg/API_Tag.html.
             network_config (:class:`~sagemaker.network.NetworkConfig`):
@@ -1482,7 +1483,7 @@ def __init__(
             None,  # We set method-specific job names below.
             sagemaker_session,
             env,
-            tags,
+            format_tags(tags),
             network_config,
         )
 

src/sagemaker/cli/compatibility/v2/files.py

@@ -22,7 +22,8 @@
 
 from sagemaker.cli.compatibility.v2.ast_transformer import ASTTransformer
 
-LOGGER = logging.getLogger(__name__)
+# Setting LOGGER for backward compatibility, in case users import this...
+logger = LOGGER = logging.getLogger(__name__)
 
 
 class FileUpdater(object):
@@ -59,7 +60,7 @@ def _make_output_dirs_if_needed(self):
             os.makedirs(output_dir)
 
         if os.path.exists(self.output_path):
-            LOGGER.warning("Overwriting file %s", self.output_path)
+            logger.warning("Overwriting file %s", self.output_path)
 
 
 class PyFileUpdater(FileUpdater):

src/sagemaker/djl_inference/model.py

@@ -30,7 +30,7 @@
 from sagemaker.s3_utils import s3_path_join
 from sagemaker.serializers import JSONSerializer, BaseSerializer
 from sagemaker.session import Session
-from sagemaker.utils import _tmpdir, _create_or_update_code_dir
+from sagemaker.utils import _tmpdir, _create_or_update_code_dir, format_tags
 from sagemaker.workflow.entities import PipelineVariable
 from sagemaker.estimator import Estimator
 from sagemaker.s3 import S3Uploader
@@ -610,7 +610,7 @@ def deploy(
                 default deserializer is set by the ``predictor_cls``.
             endpoint_name (str): The name of the endpoint to create (default:
                 None). If not specified, a unique endpoint name will be created.
-            tags (List[dict[str, str]]): The list of tags to attach to this
+            tags (Optional[Tags]): The list of tags to attach to this
                 specific endpoint.
             kms_key (str): The ARN of the KMS key that is used to encrypt the
                 data on the storage volume attached to the instance hosting the
@@ -651,7 +651,7 @@ def deploy(
             serializer=serializer,
             deserializer=deserializer,
             endpoint_name=endpoint_name,
-            tags=tags,
+            tags=format_tags(tags),
             kms_key=kms_key,
             wait=wait,
             data_capture_config=data_capture_config,