deleting comments and simplifying mirror traffic limitation

msakande · msakande · commit ee55ccabb01e · 2023-03-27T11:46:49.000-05:00
diff --git a/articles/machine-learning/how-to-safely-rollout-online-endpoints.md b/articles/machine-learning/how-to-safely-rollout-online-endpoints.md
@@ -187,7 +187,7 @@ The following table lists key attributes to specify when you define an endpoint.
 | Authentication mode      | The authentication method for the endpoint. Choose between key-based authentication `key` and Azure Machine Learning token-based authentication `aml_token`. A key doesn't expire, but a token does expire. For more information on authenticating, see [Authenticate to an online endpoint](how-to-authenticate-online-endpoint.md).                                                                                                                                                                                                                                                                                         |
 | Description    | Description of the endpoint.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  |
 | Tags           | Dictionary of tags for the endpoint.                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                          |
-| Traffic        | Traffic rules on how the traffic will be routed across deployments. Represent the traffic as a dictionary of key-value pairs, where key represents the deployment name and value represents the percentage of traffic to that deployment. You can set the traffic only when the deployments under an endpoint have been created. You can also update the traffic for an online endpoint after the deployments have been created. For more information on how to use mirrored traffic, see [Allocate a small percentage of live traffic to the new deployment](#allocate-a-small-percentage-of-live-traffic-to-the-new-deployment). |
+| Traffic        | Rules on how to route traffic across deployments. Represent the traffic as a dictionary of key-value pairs, where key represents the deployment name and value represents the percentage of traffic to that deployment. You can set the traffic only when the deployments under an endpoint have been created. You can also update the traffic for an online endpoint after the deployments have been created. For more information on how to use mirrored traffic, see [Allocate a small percentage of live traffic to the new deployment](#allocate-a-small-percentage-of-live-traffic-to-the-new-deployment). |
 | Mirror traffic (preview) | Percentage of live traffic to mirror to a deployment. For more information on how to use mirrored traffic, see [Test the deployment with mirrored traffic (preview)](#test-the-deployment-with-mirrored-traffic-preview).                                                                                                                                                                                                                                                                                                                                                                                                     |
 
 To see a full list of attributes that you can specify when you create an endpoint, see [CLI (v2) online endpoint YAML schema](/azure/machine-learning/reference-yaml-endpoint-online) or [SDK (v2) ManagedOnlineEndpoint Class](/python/api/azure-ai-ml/azure.ai.ml.entities.managedonlineendpoint).
@@ -269,13 +269,6 @@ For more information on registering your model as an asset, see [Register your m
 
 To create a managed online endpoint, use the `ManagedOnlineEndpoint` class. This class allows users to configure the key aspects of the endpoint.
 
-<!-- * `name` - Name of the endpoint. Needs to be unique at the Azure region level
-* `auth_mode` - The authentication method for the endpoint. Key-based authentication and Azure Machine Learning token-based authentication are supported. Key-based authentication doesn't expire but Azure Machine Learning token-based authentication does. Possible values are `key` or `aml_token`.
-* `identity`- The managed identity configuration for accessing Azure resources for endpoint provisioning and inference.
-    * `type`- The type of managed identity. Azure Machine Learning supports `system_assigned` or `user_assigned` identity.
-    * `user_assigned_identities` - List (array) of fully qualified resource IDs of the user-assigned identities. This property is required if `identity.type` is user_assigned.
-* `description`- Description of the endpoint. -->
-
 1. Configure the endpoint:
 
     [!notebook-python[](~/azureml-examples-main/sdk/python/endpoints/online/managed/online-endpoints-safe-rollout.ipynb?name=configure_endpoint)]
@@ -581,11 +574,9 @@ Mirroring has the following limitations:
 Also note the following behaviors:
 
 * A deployment can be configured to receive only live traffic or mirrored traffic, not both.
-* You can send traffic directly to the shadow deployment (that is, the deployment that is set to receive mirrored traffic) by specifying the shadow deployment when you invoke the endpoint. In our example, where the green deployment is the shadow deployment, you can invoke the endpoint with the specification that it sends back the response of the green deployment.
-* You can send traffic directly to a deployment that is already configured to receive live traffic by specifying the deployment when you invoke the endpoint. However, specifying a deployment to receive live traffic will prevent Azure Machine Learning from mirroring traffic to the shadow deployment. Azure Machine Learning routes mirrored traffic to the shadow deployment from traffic sent to the endpoint when you don't specify a deployment.
-
-> [!TIP]
-> You can use `--deployment-name` option [for CLI v2](/cli/azure/ml/online-endpoint#az-ml-online-endpoint-invoke-optional-parameters), or `deployment_name` option [for SDK v2](/python/api/azure-ai-ml/azure.ai.ml.operations.onlineendpointoperations#azure-ai-ml-operations-onlineendpointoperations-invoke) to specify the deployment to be routed to.
+* When you invoke an endpoint, you can send traffic directly to a deployment by specifying the deployment's name, so that the endpoint returns the output of the deployment—whether it has been configured to receive mirrored traffic or live traffic. You can use the `--deployment-name` option [for CLI v2](/cli/azure/ml/online-endpoint#az-ml-online-endpoint-invoke-optional-parameters), or `deployment_name` option [for SDK v2](/python/api/azure-ai-ml/azure.ai.ml.operations.onlineendpointoperations#azure-ai-ml-operations-onlineendpointoperations-invoke) to specify the deployment.
+    > [!NOTE]
+    > When you specify the deployment to receive traffic, Azure Machine Learning will not mirror traffic to the shadow deployment. Azure Machine Learning mirrors traffic to the shadow deployment from traffic sent to the endpoint when you don't specify a deployment.
 
 Now, let's set the green deployment to receive 10% of mirrored traffic. Clients will still receive predictions from the blue deployment only.
 
