AWS sagemaker documentation change

Service: sagemaker · 2026-06-28 · Documentation low

File: sagemaker/latest/dg/inference-pipeline-real-time.md

Summary

Added SageMaker Python SDK v3 examples for creating/deploying inference pipelines and making real-time predictions

Security assessment

Changes purely add new code samples for SDK v3 usage without addressing security vulnerabilities or adding security features documentation

Diff

diff --git a/sagemaker/latest/dg/inference-pipeline-real-time.md b/sagemaker/latest/dg/inference-pipeline-real-time.md
index 4959fb704..d73136108 100644
--- a//sagemaker/latest/dg/inference-pipeline-real-time.md
+++ b//sagemaker/latest/dg/inference-pipeline-real-time.md
@@ -29,0 +30,26 @@ The following code creates and deploys a real-time inference pipeline model with
+SageMaker Python SDK v3
+    
+    
+    
+    from sagemaker.serve import ModelBuilder
+    
+    sparkml_data = 's3://{}/{}/{}'.format(s3_model_bucket, s3_model_key_prefix, 'model.tar.gz')
+    
+    model_name = 'serial-inference-' + timestamp_prefix
+    endpoint_name = 'serial-inference-ep-' + timestamp_prefix
+    
+    model_builder = ModelBuilder(
+        s3_model_data_url=sparkml_data,
+        role_arn=role,
+        instance_type='ml.c4.xlarge',
+        pipeline_models=[sparkml_data, xgb_model.s3_model_data_url],
+    )
+    endpoint = model_builder.build().deploy(
+        initial_instance_count=1,
+        instance_type='ml.c4.xlarge',
+        endpoint_name=endpoint_name
+    )
+
+SageMaker Python SDK v2 (Legacy)
+    
+    
@@ -47,0 +74,55 @@ The following example shows how to make real-time predictions by calling an infe
+SageMaker Python SDK v3
+    
+    
+    
+    import json
+    from sagemaker.core.resources import Endpoint
+    
+    payload = {
+            "input": [
+                {
+                    "name": "Pclass",
+                    "type": "float",
+                    "val": "1.0"
+                },
+                {
+                    "name": "Embarked",
+                    "type": "string",
+                    "val": "Q"
+                },
+                {
+                    "name": "Age",
+                    "type": "double",
+                    "val": "48.0"
+                },
+                {
+                    "name": "Fare",
+                    "type": "double",
+                    "val": "100.67"
+                },
+                {
+                    "name": "SibSp",
+                    "type": "double",
+                    "val": "1.0"
+                },
+                {
+                    "name": "Sex",
+                    "type": "string",
+                    "val": "male"
+                }
+            ],
+            "output": {
+                "name": "features",
+                "type": "double",
+                "struct": "vector"
+            }
+        }
+    
+    endpoint = Endpoint(endpoint_name=endpoint_name)
+    
+    response = endpoint.invoke(body=json.dumps(payload), content_type='application/json', accept='application/json')
+    print(response)
+
+SageMaker Python SDK v2 (Legacy)
+    
+    
@@ -97 +178 @@ The following example shows how to make real-time predictions by calling an infe
-The response you get from `predictor.predict(payload)` is the model's inference result.
+The response you get is the model's inference result.