change: bump jinja2 to 3.1.3 in doc/requirments.txt (#4421) (#4423)

* change: bump jinja2 to 3.1.3 in doc/requirments.txt (#4421) * change: bump jinja2 to 3.1.3 in doc/requirments.txt * Update requirements.txt * feature: TGI 1.4.0 (#4424) * documentation: fix the ClarifyCheckStep documentation to mention PDP (#4259) * documentation: fix the ClarifyCheckStep documentation to mention PDP support * fix: break the lines to meet pylint requirement --------- Co-authored-by: Shing Lyu <shinglyu@amazon.nl> * documentation: Explain the ClarifyCheckStep and QualityCheckStep parameters (#4261) * documentation: explain the ClarifyCheckStep and QualityCheckStep parameters * fix: remove trailing space --------- Co-authored-by: Shing Lyu <shinglyu@amazon.nl> * feat: Telemetry metrics (#4414) * Emit additional telemetry metrics * Fix unit tests * Emit endpoint failure to telemetry * Address PR Comments * Emit latency in telemetry * Address PR Comments * Addressed PR Comments * Address PR Comments * Fix tests * Fix integ tests --------- Co-authored-by: Jonathan Makunga <makung@amazon.com> Co-authored-by: Erick Benitez-Ramos <141277478+benieric@users.noreply.github.com> * documentation: change order of pipelines topics (#4427) * prepare release v2.208.0 * update development version to v2.208.1.dev0 * feature: AutoGluon 1.0.0 image_uris update (#4426) --------- Co-authored-by: Erick Benitez-Ramos <141277478+benieric@users.noreply.github.com> Co-authored-by: Jinyoung Lim <jj.lim418@gmail.com> Co-authored-by: Shing Lyu <shing.lyu@gmail.com> Co-authored-by: Shing Lyu <shinglyu@amazon.nl> Co-authored-by: Jonathan Makunga <54963715+makungaj1@users.noreply.github.com> Co-authored-by: Jonathan Makunga <makung@amazon.com> Co-authored-by: stacicho <stacicho@amazon.com> Co-authored-by: ci <ci> Co-authored-by: tonyhu <tonyhoo@users.noreply.github.com>
aws · Feb 16, 2024 · b3a72fd · b3a72fd
1 parent bf698e7
commit b3a72fd
Show file tree

Hide file tree

Showing 13 changed files with 229 additions and 13 deletions.
diff --git a/.gitignore b/.gitignore
@@ -34,4 +34,4 @@ env/
 **/_repack_script_launcher.sh
 tests/data/**/_repack_model.py
 tests/data/experiment/sagemaker-dev-1.0.tar.gz
-src/sagemaker/serve/tmp_workspace
+src/sagemaker/serve/tmp_workspace
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,5 +1,27 @@
 # Changelog
 
+## v2.208.0 (2024-02-15)
+
+### Features
+
+ * Telemetry metrics
+ * TGI 1.4.0
+ * Support collection type and target store for feature store ingestion.
+
+### Bug Fixes and Other Changes
+
+ * bump jinja2 to 3.1.3 in doc/requirments.txt
+ * chore(deps): bump jinja2 from 3.0.3 to 3.1.3 in /requirements/extras
+ * Fix dependabot alert in transformers package
+ * Bump Apache Airflow version to 2.8.0
+ * skip failing mxnet tests
+
+### Documentation Changes
+
+ * change order of pipelines topics
+ * Explain the ClarifyCheckStep and QualityCheckStep parameters
+ * fix the ClarifyCheckStep documentation to mention PDP
+
 ## v2.207.1 (2024-02-06)
 
 ### Bug Fixes and Other Changes

diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-2.207.2.dev0
+2.208.1.dev0
diff --git a/doc/requirements.txt b/doc/requirements.txt
@@ -2,5 +2,5 @@ sphinx==5.1.1
 sphinx-rtd-theme==0.5.0
 docutils==0.15.2
 packaging==20.9
-jinja2<3.1
+jinja2==3.1.3
 schema==0.7.5
diff --git a/doc/workflows/index.rst b/doc/workflows/index.rst
@@ -7,7 +7,7 @@ The SageMaker Python SDK supports managed training and inference for a variety o
 .. toctree::
     :maxdepth: 2
 
+    pipelines/index
     airflow/index
     step_functions/index
-    pipelines/index
     lineage/index
diff --git a/src/sagemaker/image_uri_config/autogluon.json b/src/sagemaker/image_uri_config/autogluon.json
@@ -10,7 +10,8 @@
             "0.5": "0.5.2",
             "0.6": "0.6.2",
             "0.7": "0.7.0",
-            "0.8": "0.8.2"
+            "0.8": "0.8.2",
+            "1.0": "1.0.0"
         },
         "versions": {
             "0.3.1": {
@@ -438,6 +439,47 @@
                 "py_versions": [
                     "py39"
                 ]
+            },
+            "1.0.0": {
+                "registries": {
+                    "af-south-1": "626614931356",
+                    "il-central-1": "780543022126",
+                    "ap-east-1": "871362719292",
+                    "ap-northeast-1": "763104351884",
+                    "ap-northeast-2": "763104351884",
+                    "ap-northeast-3": "364406365360",
+                    "ap-south-1": "763104351884",
+                    "ap-southeast-1": "763104351884",
+                    "ap-southeast-2": "763104351884",
+                    "ap-southeast-3": "907027046896",
+                    "ap-southeast-4": "457447274322",
+                    "ca-central-1": "763104351884",
+                    "eu-central-1": "763104351884",
+                    "eu-north-1": "763104351884",
+                    "eu-west-1": "763104351884",
+                    "eu-west-2": "763104351884",
+                    "eu-west-3": "763104351884",
+                    "eu-south-1": "692866216735",
+                    "me-south-1": "217643126080",
+                    "sa-east-1": "763104351884",
+                    "us-east-1": "763104351884",
+                    "us-east-2": "763104351884",
+                    "us-gov-east-1": "446045086412",
+                    "us-gov-west-1": "442386744353",
+                    "us-iso-east-1": "886529160074",
+                    "us-isob-east-1": "094389454867",
+                    "us-west-1": "763104351884",
+                    "us-west-2": "763104351884",
+                    "ca-west-1": "204538143572"
+                },
+                "repository": "autogluon-training",
+                "processors": [
+                    "cpu",
+                    "gpu"
+                ],
+                "py_versions": [
+                    "py310"
+                ]
             }
         }
     },
@@ -448,7 +490,8 @@
             "0.5": "0.5.2",
             "0.6": "0.6.2",
             "0.7": "0.7.0",
-            "0.8": "0.8.2"
+            "0.8": "0.8.2",
+            "1.0": "1.0.0"
         },
         "versions": {
             "0.3.1": {
@@ -901,6 +944,49 @@
                 "py_versions": [
                     "py39"
                 ]
+            },
+            "1.0.0": {
+                "registries": {
+                    "af-south-1": "626614931356",
+                    "il-central-1": "780543022126",
+                    "ap-east-1": "871362719292",
+                    "ap-northeast-1": "763104351884",
+                    "ap-northeast-2": "763104351884",
+                    "ap-northeast-3": "364406365360",
+                    "ap-south-1": "763104351884",
+                    "ap-southeast-1": "763104351884",
+                    "ap-southeast-2": "763104351884",
+                    "ap-southeast-3": "907027046896",
+                    "ap-southeast-4": "457447274322",
+                    "ca-central-1": "763104351884",
+                    "cn-north-1": "727897471807",
+                    "cn-northwest-1": "727897471807",
+                    "eu-central-1": "763104351884",
+                    "eu-north-1": "763104351884",
+                    "eu-west-1": "763104351884",
+                    "eu-west-2": "763104351884",
+                    "eu-west-3": "763104351884",
+                    "eu-south-1": "692866216735",
+                    "me-south-1": "217643126080",
+                    "sa-east-1": "763104351884",
+                    "us-east-1": "763104351884",
+                    "us-east-2": "763104351884",
+                    "us-gov-east-1": "446045086412",
+                    "us-gov-west-1": "442386744353",
+                    "us-iso-east-1": "886529160074",
+                    "us-isob-east-1": "094389454867",
+                    "us-west-1": "763104351884",
+                    "us-west-2": "763104351884",
+                    "ca-west-1": "204538143572"
+                },
+                "repository": "autogluon-inference",
+                "processors": [
+                    "cpu",
+                    "gpu"
+                ],
+                "py_versions": [
+                    "py310"
+                ]
             }
         }
     }

diff --git a/src/sagemaker/image_uri_config/huggingface-llm.json b/src/sagemaker/image_uri_config/huggingface-llm.json
@@ -10,7 +10,8 @@
             "1.0": "1.0.3",
             "1.1": "1.1.0",
             "1.2": "1.2.0",
-            "1.3": "1.3.3"
+            "1.3": "1.3.3",
+            "1.4": "1.4.0"
         },
         "versions": {
             "0.6.0": {
@@ -388,6 +389,53 @@
                 "container_version": {
                     "gpu": "cu121-ubuntu20.04"
                 }
+            },
+            "1.4.0": {
+                "py_versions": [
+                    "py310"
+                ],
+                "registries": {
+                    "af-south-1": "626614931356",
+                    "il-central-1": "780543022126",
+                    "ap-east-1": "871362719292",
+                    "ap-northeast-1": "763104351884",
+                    "ap-northeast-2": "763104351884",
+                    "ap-northeast-3": "364406365360",
+                    "ap-south-1": "763104351884",
+                    "ap-south-2": "772153158452",
+                    "ap-southeast-1": "763104351884",
+                    "ap-southeast-2": "763104351884",
+                    "ap-southeast-3": "907027046896",
+                    "ap-southeast-4": "457447274322",
+                    "ca-central-1": "763104351884",
+                    "cn-north-1": "727897471807",
+                    "cn-northwest-1": "727897471807",
+                    "eu-central-1": "763104351884",
+                    "eu-central-2": "380420809688",
+                    "eu-north-1": "763104351884",
+                    "eu-west-1": "763104351884",
+                    "eu-west-2": "763104351884",
+                    "eu-west-3": "763104351884",      
+                    "eu-south-1": "692866216735",
+                    "eu-south-2": "503227376785",
+                    "me-south-1": "217643126080",
+                    "me-central-1": "914824155844",
+                    "sa-east-1": "763104351884",
+                    "us-east-1": "763104351884",
+                    "us-east-2": "763104351884",
+                    "us-gov-east-1": "446045086412",
+                    "us-gov-west-1": "442386744353",
+                    "us-iso-east-1": "886529160074",
+                    "us-isob-east-1": "094389454867",
+                    "us-west-1": "763104351884",
+                    "us-west-2": "763104351884",
+                    "ca-west-1": "204538143572"
+                },
+                "tag_prefix": "2.1.1-tgi1.4.0",
+                "repository": "huggingface-pytorch-tgi-inference",
+                "container_version": {
+                    "gpu": "cu121-ubuntu20.04"
+                }
             }
         }
     }

diff --git a/src/sagemaker/serve/utils/telemetry_logger.py b/src/sagemaker/serve/utils/telemetry_logger.py
@@ -13,12 +13,15 @@
 """Placeholder docstring"""
 from __future__ import absolute_import
 import logging
+from time import perf_counter
+
 import requests
 
-from sagemaker import Session
+from sagemaker import Session, exceptions
 from sagemaker.serve.mode.function_pointers import Mode
 from sagemaker.serve.utils.exceptions import ModelBuilderException
 from sagemaker.serve.utils.types import ModelServer
+from sagemaker.user_agent import SDK_VERSION
 
 logger = logging.getLogger(__name__)
 
@@ -63,13 +66,21 @@ def wrapper(self, *args, **kwargs):
                 f"{func_name}"
                 f"&x-modelServer={MODEL_SERVER_TO_CODE[str(self.model_server)]}"
                 f"&x-imageTag={image_uri_tail}"
+                f"&x-sdkVersion={SDK_VERSION}"
             )
 
             if self.model_server == ModelServer.DJL_SERVING or self.model_server == ModelServer.TGI:
                 extra += f"&x-modelName={self.model}"
 
+            if self.sagemaker_session and self.sagemaker_session.endpoint_arn:
+                extra += f"&x-endpointArn={self.sagemaker_session.endpoint_arn}"
+
+            start_timer = perf_counter()
             try:
                 response = func(self, *args, **kwargs)
+                stop_timer = perf_counter()
+                elapsed = stop_timer - start_timer
+                extra += f"&x-latency={round(elapsed, 2)}"
                 if not self.serve_settings.telemetry_opt_out:
                     _send_telemetry(
                         "1",
@@ -79,7 +90,15 @@ def wrapper(self, *args, **kwargs):
                         None,
                         extra,
                     )
-            except ModelBuilderException as e:
+            except (
+                ModelBuilderException,
+                exceptions.CapacityError,
+                exceptions.UnexpectedStatusException,
+                exceptions.AsyncInferenceError,
+            ) as e:
+                stop_timer = perf_counter()
+                elapsed = stop_timer - start_timer
+                extra += f"&x-latency={round(elapsed, 2)}"
                 if not self.serve_settings.telemetry_opt_out:
                     _send_telemetry(
                         "0",

diff --git a/src/sagemaker/session.py b/src/sagemaker/session.py
@@ -243,6 +243,7 @@ def __init__(
         # sagemaker_config is validated and initialized inside :func:`_initialize`,
         # so if default_bucket is None and the sagemaker_config has a default S3 bucket configured,
         # _default_bucket_name_override will be set again inside :func:`_initialize`.
+        self.endpoint_arn = None
         self._default_bucket = None
         self._default_bucket_name_override = default_bucket
         # this may also be set again inside :func:`_initialize` if it is None
@@ -4284,9 +4285,12 @@ def create_endpoint(self, endpoint_name, config_name, tags=None, wait=True, live
             tags, "{}.{}.{}".format(SAGEMAKER, ENDPOINT, TAGS)
         )
 
-        self.sagemaker_client.create_endpoint(
+        res = self.sagemaker_client.create_endpoint(
             EndpointName=endpoint_name, EndpointConfigName=config_name, Tags=tags
         )
+        if res:
+            self.endpoint_arn = res["EndpointArn"]
+
         if wait:
             self.wait_for_endpoint(endpoint_name, live_logging=live_logging)
         return endpoint_name
@@ -4344,9 +4348,11 @@ def update_endpoint(self, endpoint_name, endpoint_config_name, wait=True):
                 "existing endpoint name".format(endpoint_name)
             )
 
-        self.sagemaker_client.update_endpoint(
+        res = self.sagemaker_client.update_endpoint(
             EndpointName=endpoint_name, EndpointConfigName=endpoint_config_name
         )
+        if res:
+            self.endpoint_arn = res["EndpointArn"]
 
         if wait:
             self.wait_for_endpoint(endpoint_name)

diff --git a/src/sagemaker/workflow/clarify_check_step.py b/src/sagemaker/workflow/clarify_check_step.py
@@ -132,8 +132,10 @@ class ModelExplainabilityCheckConfig(ClarifyCheckConfig):
 
     Attributes:
         model_config (ModelConfig): Config of the model and its endpoint to be created.
-        explainability_config (SHAPConfig): Config of the specific explainability method.
-            Currently, only SHAP is supported.
+        explainability_config (SHAPConfig or PDPConfig): Config of the explainability method.
+            Supports SHAP or PDP.
+            For `PDPConfig`, `features` must be specified.
+            `top_k_features` based on SHAP is currently not supported.
         model_scores (str or int or ModelPredictedLabelConfig): Index or JMESPath expression
             to locate the predicted scores in the model output (default: None).
             This is not required if the model output is a single score. Alternatively,
@@ -166,6 +168,10 @@ def __init__(
     ):
         """Constructs a ClarifyCheckStep.
 
+        To understand the `skip_check`, `fail_on_violation`, `register_new_baseline`
+        and `supplied_baseline_constraints` parameters, check the following documentation:
+        https://docs.aws.amazon.com/sagemaker/latest/dg/pipelines-quality-clarify-baseline-lifecycle.html
+
         Args:
             name (str): The name of the ClarifyCheckStep step.
             clarify_check_config (ClarifyCheckConfig): A ClarifyCheckConfig instance.

diff --git a/src/sagemaker/workflow/quality_check_step.py b/src/sagemaker/workflow/quality_check_step.py
@@ -135,6 +135,11 @@ def __init__(
     ):
         """Constructs a QualityCheckStep.
 
+        To understand the `skip_check`, `fail_on_violation`, `register_new_baseline`,
+        `supplied_baseline_constraints` and `supplied_baseline_constraints` parameters,
+        check the following documentation:
+        https://docs.aws.amazon.com/sagemaker/latest/dg/pipelines-quality-clarify-baseline-lifecycle.html
+
         Args:
             name (str): The name of the QualityCheckStep step.
             quality_check_config (QualityCheckConfig): A QualityCheckConfig instance.

diff --git a/tests/unit/sagemaker/image_uris/test_huggingface_llm.py b/tests/unit/sagemaker/image_uris/test_huggingface_llm.py
@@ -28,6 +28,7 @@
         "1.2.0": "2.1.1-tgi1.2.0-gpu-py310-cu121-ubuntu20.04",
         "1.3.1": "2.1.1-tgi1.3.1-gpu-py310-cu121-ubuntu20.04",
         "1.3.3": "2.1.1-tgi1.3.3-gpu-py310-cu121-ubuntu20.04",
+        "1.4.0": "2.1.1-tgi1.4.0-gpu-py310-cu121-ubuntu20.04",
     },
     "inf2": {
         "0.0.16": "1.13.1-optimum0.0.16-neuronx-py310-ubuntu22.04",