Merge branch 'master' into PT113Release

Author: Qingzi-Lan

CHANGELOG.md

@@ -1,5 +1,17 @@
 # Changelog
 
+## v2.145.0 (2023-04-06)
+
+### Features
+
+ * add support for async inline error notifications
+ * Add methods for feature group to list feature metadata parameters and tags
+ * Support huggingface hub model_id for DJL Models
+
+### Bug Fixes and Other Changes
+
+ * load_sagemaker_config should lazy initialize a default S3 resource
+
 ## v2.144.0 (2023-04-05)
 
 ### Features

VERSION

@@ -1 +1 @@
-2.144.1.dev0
+2.145.1.dev0

doc/api/prep_data/feature_store.rst

@@ -1,7 +1,7 @@
 Feature Store APIs
 ------------------
 
-Feature group
+Feature Group
 *************
 
 .. autoclass:: sagemaker.feature_store.feature_group.FeatureGroup
@@ -18,7 +18,7 @@ Feature group
     :show-inheritance:
 
 
-Feature definition
+Feature Definition
 ******************
 
 .. autoclass:: sagemaker.feature_store.feature_definition.FeatureDefinition
@@ -77,10 +77,46 @@ Inputs
     :members:
     :show-inheritance:
 
+.. autoclass:: sagemaker.feature_store.inputs.ResourceEnum
+    :members:
+    :show-inheritance:
+
+.. autoclass:: sagemaker.feature_store.inputs.SearchOperatorEnum
+    :members:
+    :show-inheritance:
+
+.. autoclass:: sagemaker.feature_store.inputs.SortOrderEnum
+    :members:
+    :show-inheritance:
+
+.. autoclass:: sagemaker.feature_store.inputs.FilterOperatorEnum
+    :members:
+    :show-inheritance:
+
+.. autoclass:: sagemaker.feature_store.inputs.Filter
+    :members:
+    :show-inheritance:
+
+.. autoclass:: sagemaker.feature_store.inputs.Identifier
+    :members:
+    :show-inheritance:
+
+.. autoclass:: sagemaker.feature_store.inputs.FeatureParameter
+    :members:
+    :show-inheritance:
+
 
 Dataset Builder
 ***************
 
 .. autoclass:: sagemaker.feature_store.dataset_builder.DatasetBuilder
     :members:
     :show-inheritance:
+
+
+Feature Store
+*************
+
+.. autoclass:: sagemaker.feature_store.feature_store.FeatureStore
+    :members:
+    :show-inheritance:

doc/overview.rst

@@ -1164,7 +1164,8 @@ More information about SageMaker Asynchronous Inference can be found in the `AWS
 
 To deploy asynchronous inference endpoint, you will need to create a ``AsyncInferenceConfig`` object.
 If you create ``AsyncInferenceConfig`` without specifying its arguments, the default ``S3OutputPath`` will
-be ``s3://sagemaker-{REGION}-{ACCOUNTID}/async-endpoint-outputs/{UNIQUE-JOB-NAME}``. (example shown below):
+be ``s3://sagemaker-{REGION}-{ACCOUNTID}/async-endpoint-outputs/{UNIQUE-JOB-NAME}``, ``S3FailurePath`` will
+be ``s3://sagemaker-{REGION}-{ACCOUNTID}/async-endpoint-failures/{UNIQUE-JOB-NAME}`` (example shown below):
 
 .. code:: python
 
@@ -1174,18 +1175,21 @@ be ``s3://sagemaker-{REGION}-{ACCOUNTID}/async-endpoint-outputs/{UNIQUE-JOB-NAME
     async_config = AsyncInferenceConfig()
 
 Or you can specify configurations in ``AsyncInferenceConfig`` as you like. All of those configuration parameters
-are optional but if you don’t specify the ``output_path``, Amazon SageMaker will use the default ``S3OutputPath``
+are optional but if you don’t specify the ``output_path`` or ``failure_path``, Amazon SageMaker will use the
+default ``S3OutputPath`` or ``S3FailurePath``
 mentioned above (example shown below):
 
 .. code:: python
 
-    # Specify S3OutputPath, MaxConcurrentInvocationsPerInstance and NotificationConfig in the async config object
+    # Specify S3OutputPath, S3FailurePath, MaxConcurrentInvocationsPerInstance and NotificationConfig
+    # in the async config object
     async_config = AsyncInferenceConfig(
         output_path="s3://{s3_bucket}/{bucket_prefix}/output",
         max_concurrent_invocations_per_instance=10,
         notification_config = {
             "SuccessTopic": "arn:aws:sns:aws-region:account-id:topic-name",
             "ErrorTopic": "arn:aws:sns:aws-region:account-id:topic-name",
+            "IncludeInferenceResponseIn": ["SUCCESS_NOTIFICATION_TOPIC","ERROR_NOTIFICATION_TOPIC"],
         }
     )
 

src/sagemaker/async_inference/async_inference_config.py

@@ -31,6 +31,7 @@ def __init__(
         max_concurrent_invocations_per_instance=None,
         kms_key_id=None,
         notification_config=None,
+        failure_path=None,
     ):
         """Initialize an AsyncInferenceConfig object for async inference configuration.
 
@@ -45,6 +46,9 @@ def __init__(
             kms_key_id (str): Optional. The Amazon Web Services Key Management Service
                 (Amazon Web Services KMS) key that Amazon SageMaker uses to encrypt the
                 asynchronous inference output in Amazon S3. (Default: None)
+            failure_path (str): Optional. The Amazon S3 location that endpoints upload model
+                responses for failed requests. If no value is provided, Amazon SageMaker will
+                use default Amazon S3 Async Inference failure path. (Default: None)
             notification_config (dict): Optional. Specifies the configuration for notifications
                 of inference results for asynchronous inference. Only one notification is generated
                 per invocation request (Default: None):
@@ -54,17 +58,24 @@ def __init__(
                 * error_topic (str): Amazon SNS topic to post a notification to when inference
                 fails. If no topic is provided, no notification is sent on failure.
                 The key in notification_config is 'ErrorTopic'.
+                * include_inference_response_in (list): Optional. When provided the inference
+                response will be included in the notification topics. If not provided,
+                a notification will still be generated on success/error, but will not
+                contain the inference response.
+                Valid options are SUCCESS_NOTIFICATION_TOPIC, ERROR_NOTIFICATION_TOPIC
         """
         self.output_path = output_path
         self.max_concurrent_invocations_per_instance = max_concurrent_invocations_per_instance
         self.kms_key_id = kms_key_id
         self.notification_config = notification_config
+        self.failure_path = failure_path
 
     def _to_request_dict(self):
         """Generates a request dictionary using the parameters provided to the class."""
         request_dict = {
             "OutputConfig": {
                 "S3OutputPath": self.output_path,
+                "S3FailurePath": self.failure_path,
             },
         }
 

src/sagemaker/async_inference/async_inference_response.py

@@ -17,7 +17,11 @@
 from botocore.exceptions import ClientError
 from sagemaker.s3 import parse_s3_url
 from sagemaker.async_inference import WaiterConfig
-from sagemaker.exceptions import ObjectNotExistedError, UnexpectedClientError
+from sagemaker.exceptions import (
+    ObjectNotExistedError,
+    UnexpectedClientError,
+    AsyncInferenceModelError,
+)
 
 
 class AsyncInferenceResponse(object):
@@ -32,6 +36,7 @@ def __init__(
         self,
         predictor_async,
         output_path,
+        failure_path,
     ):
         """Initialize an AsyncInferenceResponse object.
 
@@ -43,10 +48,13 @@ def __init__(
                 that return this response.
             output_path (str): The Amazon S3 location that endpoints upload inference responses
                 to.
+            failure_path (str): The Amazon S3 location that endpoints upload model errors
+                for failed requests.
         """
         self.predictor_async = predictor_async
         self.output_path = output_path
         self._result = None
+        self.failure_path = failure_path
 
     def get_result(
         self,
@@ -71,28 +79,34 @@ def get_result(
 
         if self._result is None:
             if waiter_config is None:
-                self._result = self._get_result_from_s3(self.output_path)
+                self._result = self._get_result_from_s3(self.output_path, self.failure_path)
             else:
                 self._result = self.predictor_async._wait_for_output(
-                    self.output_path, waiter_config
+                    self.output_path, self.failure_path, waiter_config
                 )
         return self._result
 
-    def _get_result_from_s3(
-        self,
-        output_path,
-    ):
+    def _get_result_from_s3(self, output_path, failure_path):
         """Get inference result from the output Amazon S3 path"""
         bucket, key = parse_s3_url(output_path)
         try:
             response = self.predictor_async.s3_client.get_object(Bucket=bucket, Key=key)
             return self.predictor_async.predictor._handle_response(response)
-        except ClientError as ex:
-            if ex.response["Error"]["Code"] == "NoSuchKey":
-                raise ObjectNotExistedError(
-                    message="Inference could still be running",
-                    output_path=output_path,
-                )
-            raise UnexpectedClientError(
-                message=ex.response["Error"]["Message"],
-            )
+        except ClientError as e:
+            if e.response["Error"]["Code"] == "NoSuchKey":
+                try:
+                    failure_bucket, failure_key = parse_s3_url(failure_path)
+                    failure_response = self.predictor_async.s3_client.get_object(
+                        Bucket=failure_bucket, Key=failure_key
+                    )
+                    failure_response = self.predictor_async.predictor._handle_response(
+                        failure_response
+                    )
+                    raise AsyncInferenceModelError(message=failure_response)
+                except ClientError as ex:
+                    if ex.response["Error"]["Code"] == "NoSuchKey":
+                        raise ObjectNotExistedError(
+                            message="Inference could still be running", output_path=output_path
+                        )
+                    raise UnexpectedClientError(message=ex.response["Error"]["Message"])
+            raise UnexpectedClientError(message=e.response["Error"]["Message"])

src/sagemaker/config/config.py

@@ -43,17 +43,10 @@
 ENV_VARIABLE_ADMIN_CONFIG_OVERRIDE = "SAGEMAKER_ADMIN_CONFIG_OVERRIDE"
 ENV_VARIABLE_USER_CONFIG_OVERRIDE = "SAGEMAKER_USER_CONFIG_OVERRIDE"
 
-_BOTO_SESSION = boto3.DEFAULT_SESSION or boto3.Session()
-# The default Boto3 S3 Resource. This is constructed from the default Boto3 session. This will be
-# used to fetch SageMakerConfig from S3. Users can override this by passing their own S3 Resource
-# as the constructor parameter for SageMakerConfig.
-_DEFAULT_S3_RESOURCE = _BOTO_SESSION.resource("s3")
 S3_PREFIX = "s3://"
 
 
-def load_sagemaker_config(
-    additional_config_paths: List[str] = None, s3_resource=_DEFAULT_S3_RESOURCE
-) -> dict:
+def load_sagemaker_config(additional_config_paths: List[str] = None, s3_resource=None) -> dict:
     """Loads config files and merges them.
 
     By default, this method first searches for config files in the default locations
@@ -95,8 +88,9 @@ def load_sagemaker_config(
 
             Note: S3 URI follows the format ``s3://<bucket>/<Key prefix>``
         s3_resource (boto3.resource("s3")): The Boto3 S3 resource. This is used to fetch
-            config files from S3. If it is not provided, this method creates a default S3 resource.
-            See `Boto3 Session documentation <https://boto3.amazonaws.com/v1/documentation/api\
+            config files from S3. If it is not provided but config files are present in S3,
+            this method creates a default S3 resource. See `Boto3 Session documentation
+            <https://boto3.amazonaws.com/v1/documentation/api\
             /latest/reference/core/session.html#boto3.session.Session.resource>`__.
             This argument is not needed if the config files are present in the local file system.
     """
@@ -161,7 +155,15 @@ def _load_config_from_file(file_path: str) -> dict:
 def _load_config_from_s3(s3_uri, s3_resource_for_config) -> dict:
     """Placeholder docstring"""
     if not s3_resource_for_config:
-        raise RuntimeError("No S3 client found. Provide a S3 client to load the config file.")
+        # Constructing a default Boto3 S3 Resource from a default Boto3 session.
+        boto_session = boto3.DEFAULT_SESSION or boto3.Session()
+        boto_region_name = boto_session.region_name
+        if boto_region_name is None:
+            raise ValueError(
+                "Must setup local AWS configuration with a region supported by SageMaker."
+            )
+        s3_resource_for_config = boto_session.resource("s3", region_name=boto_region_name)
+
     logger.debug("Fetching config file from the S3 URI: %s", s3_uri)
     inferred_s3_uri = _get_inferred_s3_uri(s3_uri, s3_resource_for_config)
     parsed_url = urlparse(inferred_s3_uri)

src/sagemaker/exceptions.py

@@ -77,3 +77,12 @@ def __init__(self, **kwargs):
         msg = self.fmt.format(**kwargs)
         Exception.__init__(self, msg)
         self.kwargs = kwargs
+
+
+class AsyncInferenceModelError(AsyncInferenceError):
+    """Raised when model returns errors for failed requests"""
+
+    fmt = "Model returned error: {message} "
+
+    def __init__(self, message):
+        super().__init__(message=message)

src/sagemaker/feature_store/feature_group.py

@@ -690,6 +690,32 @@ def describe_feature_metadata(self, feature_name: str) -> Dict[str, Any]:
             feature_group_name=self.name, feature_name=feature_name
         )
 
+    def list_tags(self) -> Sequence[Dict[str, str]]:
+        """List all tags for a feature group.
+
+        Returns:
+            list of key, value pair of the tags.
+        """
+
+        feature_group_arn = self.sagemaker_session.describe_feature_group(
+            feature_group_name=self.name
+        ).get("FeatureGroupArn")
+
+        return self.sagemaker_session.list_tags(resource_arn=feature_group_arn)
+
+    def list_parameters_for_feature_metadata(self, feature_name: str) -> Sequence[Dict[str, str]]:
+        """List all parameters for a feature metadata.
+
+        Args:
+            feature_name (str): name of the feature.
+        Returns:
+            list of key, value pair of the parameters.
+        """
+
+        return self.sagemaker_session.describe_feature_metadata(
+            feature_group_name=self.name, feature_name=feature_name
+        ).get("Parameters")
+
     def load_feature_definitions(
         self,
         data_frame: DataFrame,

src/sagemaker/local/local_session.py

@@ -674,22 +674,19 @@ def _initialize(
         self.sagemaker_client = LocalSagemakerClient(self)
         self.sagemaker_runtime_client = LocalSagemakerRuntimeClient(self.config)
         self.local_mode = True
-        sagemaker_config = kwargs.get("sagemaker_config", None)
-        if sagemaker_config:
-            validate_sagemaker_config(sagemaker_config)
 
         if self.s3_endpoint_url is not None:
             self.s3_resource = boto_session.resource("s3", endpoint_url=self.s3_endpoint_url)
             self.s3_client = boto_session.client("s3", endpoint_url=self.s3_endpoint_url)
-            self.sagemaker_config = (
-                sagemaker_config
-                if sagemaker_config
-                else load_sagemaker_config(s3_resource=self.s3_resource)
-            )
+
+        sagemaker_config = kwargs.get("sagemaker_config", None)
+        if sagemaker_config:
+            validate_sagemaker_config(sagemaker_config)
+            self.sagemaker_config = sagemaker_config
         else:
-            self.sagemaker_config = (
-                sagemaker_config if sagemaker_config else load_sagemaker_config()
-            )
+            # self.s3_resource might be None. If it is None, load_sagemaker_config will
+            # create a default S3 resource, but only if it needs to fetch from S3
+            self.sagemaker_config = load_sagemaker_config(s3_resource=self.s3_resource)
 
         sagemaker_config_file = os.path.join(os.path.expanduser("~"), ".sagemaker", "config.yaml")
         if os.path.exists(sagemaker_config_file):