AWS sagemaker documentation change
Summary
Major update adding SDK v3/v2 code examples, modifying deployment/invocation patterns, adding EULA acceptance, and updating documentation links
Security assessment
Added 'accept_eula=True' parameter to deployment examples indicates new security documentation about license compliance. While not addressing vulnerabilities, it documents a security-related requirement for model deployment. No evidence of vulnerability fixes.
Diff
diff --git a/sagemaker/latest/dg/model-optimize-create-job.md b/sagemaker/latest/dg/model-optimize-create-job.md index d5b869b0a..9dabd2823 100644 --- a//sagemaker/latest/dg/model-optimize-create-job.md +++ b//sagemaker/latest/dg/model-optimize-create-job.md @@ -203 +203 @@ You can create an inference optimization job by using the SageMaker AI Python SD -For more information about the classes and methods used in the following examples, see [APIs](https://sagemaker.readthedocs.io/en/stable/api/index.html) in the SageMaker AI Python SDK documentation. +For more information about the classes and methods used in the following examples, see [APIs](https://sagemaker.readthedocs.io/en/stable/) in the SageMaker AI Python SDK documentation. @@ -208,0 +209,12 @@ For more information about the classes and methods used in the following example +SageMaker Python SDK v3 + + + import boto3 + from sagemaker.serve.model_builder import ModelBuilder + from sagemaker.serve.builder.schema_builder import SchemaBuilder + from sagemaker.core.helper.session_helper import Session + from pathlib import Path + +SageMaker Python SDK v2 (Legacy) + + @@ -280,0 +293,11 @@ The `optimize()` method returns a `Model` object, which you can use to deploy yo +SageMaker Python SDK v3 + + + endpoint = model_builder.deploy( + instance_type="instance-type", + accept_eula=True, + ) + +SageMaker Python SDK v2 (Legacy) + + @@ -288 +311 @@ In this example, replace ``instance-type`` with an ML instance, such as `ml.p4d. -The `deploy()` method returns a predictor object, which you can use to send inference requests to the endpoint that hosts the model. +The `deploy()` method returns an `Endpoint` object, which you can use to send inference requests to the endpoint that hosts the model. @@ -316,0 +340,8 @@ The `optimize()` method returns a `Model` object, which you can use to deploy yo +SageMaker Python SDK v3 + + + endpoint = model_builder.deploy(accept_eula=True) + +SageMaker Python SDK v2 (Legacy) + + @@ -319 +350 @@ The `optimize()` method returns a `Model` object, which you can use to deploy yo -The `deploy()` method returns a predictor object, which you can use to send inference requests to the endpoint that hosts the model. +The `deploy()` method returns an `Endpoint` object, which you can use to send inference requests to the endpoint that hosts the model. @@ -372,0 +404,8 @@ The `optimize()` method returns a `Model` object, which you can use to deploy yo +SageMaker Python SDK v3 + + + endpoint = model_builder.deploy(accept_eula=True) + +SageMaker Python SDK v2 (Legacy) + + @@ -375 +414 @@ The `optimize()` method returns a `Model` object, which you can use to deploy yo -The `deploy()` method returns a predictor object, which you can use to send inference requests to the endpoint that hosts the model. +The `deploy()` method returns an `Endpoint` object, which you can use to send inference requests to the endpoint that hosts the model. @@ -403,0 +443,8 @@ In this example, set ``instance-type`` to an ML instance type with accelerated h +SageMaker Python SDK v3 + + + endpoint = model_builder.deploy(accept_eula=True) + +SageMaker Python SDK v2 (Legacy) + + @@ -406 +453 @@ In this example, set ``instance-type`` to an ML instance type with accelerated h -The `deploy()` method returns a predictor object, which you can use to send inference requests to the endpoint that hosts the model. +The `deploy()` method returns an `Endpoint` object, which you can use to send inference requests to the endpoint that hosts the model. @@ -413 +460,12 @@ The `deploy()` method returns a predictor object, which you can use to send infe - * To send a test inference request to your deployed model, use the `predict()` method of a predictor object. The following example passes the `sample_input` variable that was also passed to the `SchemaBuilder` class in the examples to define your model: + * To send a test inference request to your deployed model, use the `invoke()` method of the `Endpoint` object. The following example passes the `sample_input` variable that was also passed to the `SchemaBuilder` class in the examples to define your model: + +SageMaker Python SDK v3 + + + import json + + response = endpoint.invoke(body=json.dumps(sample_input), content_type="application/json") + result = json.loads(response.body.read().decode('utf-8')) + +SageMaker Python SDK v2 (Legacy) + @@ -417 +475 @@ The `deploy()` method returns a predictor object, which you can use to send infe -The sample input has the prompt, `"What is the largest planet in the solar system?"`. The `predict()` method returns the response that the model generated, as shown by the following example: +The sample input has the prompt, `"What is the largest planet in the solar system?"`. The `invoke()` method returns the response that the model generated, as shown by the following example: @@ -633 +691 @@ You can't do the following: -For more information about local mode, see [Local Mode](https://sagemaker.readthedocs.io/en/stable/overview.html#local-mode) in the SageMaker AI Python SDK documentation. +For more information about local mode, see [Local Mode](https://sagemaker.readthedocs.io/en/stable/api/sagemaker_train.html) in the SageMaker AI Python SDK documentation.