You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/machine-learning/how-to-access-resources-from-endpoints-managed-identities.md
+10-10Lines changed: 10 additions & 10 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -1,5 +1,5 @@
1
1
---
2
-
title: Access Azure resources from managed endpoint
2
+
title: Access Azure resources from an online endpoint
3
3
titleSuffix: Azure Machine Learning
4
4
description: Securely access Azure resources for your machine learning model deployment from an online endpoint with a system-assigned or user-assigned managed identity.
5
5
services: machine-learning
@@ -8,7 +8,7 @@ ms.subservice: core
8
8
ms.author: seramasu
9
9
ms.reviewer: laobri
10
10
author: rsethur
11
-
ms.date: 12/22/2021
11
+
ms.date: 01/11/2022
12
12
ms.topic: how-to
13
13
ms.custom: devplatv2
14
14
@@ -53,7 +53,7 @@ This guide assumes you don't have a managed identity, a storage account or an on
53
53
54
54
## Define configuration YAML file for deployment
55
55
56
-
To deploy a managed endpoint with the CLI, you need to define the configuration in a YAML file. For more information on the YAML schema, see [online endpoint YAML reference](reference-yaml-endpoint-managed-online.md) document.
56
+
To deploy an online endpoint with the CLI, you need to define the configuration in a YAML file. For more information on the YAML schema, see [online endpoint YAML reference](reference-yaml-endpoint-managed-online.md) document.
57
57
58
58
The YAML files in the following examples are used to create online endpoints.
59
59
@@ -131,7 +131,7 @@ Decide on the name of your user identity name, and export that value as an envir
131
131
---
132
132
133
133
## Create the managed identity
134
-
To access Azure resources, create a system-assigned or user-assigned managed identity for your endpoint.
134
+
To access Azure resources, create a system-assigned or user-assigned managed identity for your online endpoint.
When you create a managed endpoint, a system-assigned managed identity is created for the endpoint by default.
192
+
When you create an online endpoint, a system-assigned managed identity is created for the endpoint by default.
193
193
194
194
>[!IMPORTANT]
195
195
> System assigned managed identities are immutable and can't be changed once created.
@@ -219,7 +219,7 @@ If you encounter any issues, see [Troubleshooting online endpoints deployment an
219
219
>[!IMPORTANT]
220
220
> Online endpoints require Azure Container Registry pull permission, AcrPull permission, to the container registry and Storage Blob Data Reader permission to the default datastore of the workspace.
221
221
222
-
You can allow the managed endpoint permission to access your storage via its system-assigned managed identity or give permission to the user-assigned managed identity to access the storage account created in the previous section.
222
+
You can allow the online endpoint permission to access your storage via its system-assigned managed identity or give permission to the user-assigned managed identity to access the storage account created in the previous section.
@@ -271,7 +271,7 @@ Refer to the following script to understand how to use your identity token to ac
271
271
272
272
## Create a deployment with your configuration
273
273
274
-
Create a deployment that's associated with the managed endpoint. [Learn more about deploying to online endpoints](how-to-deploy-managed-online-endpoints.md).
274
+
Create a deployment that's associated with the online endpoint. [Learn more about deploying to online endpoints](how-to-deploy-managed-online-endpoints.md).
275
275
276
276
>[!WARNING]
277
277
> This deployment can take approximately 8-14 minutes depending on whether the underlying environment/image is being built for the first time. Subsequent deployments using the same environment will go quicker.
@@ -325,7 +325,7 @@ When your deployment completes, the model, the environment, and the endpoint ar
325
325
326
326
## Confirm your endpoint deployed successfully
327
327
328
-
Once your endpoint is deployed, confirm its operation. Details of inferencing vary from model to model. For this guide, the JSON query parameters look like:
328
+
Once your online endpoint is deployed, confirm its operation. Details of inferencing vary from model to model. For this guide, the JSON query parameters look like:
If you don't plan to continue using the deployed endpoint and storage, delete them to reduce costs. When you delete the endpoint, all of its associated deployments are deleted as well.
346
+
If you don't plan to continue using the deployed online endpoint and storage, delete them to reduce costs. When you delete the endpoint, all of its associated deployments are deleted as well.
0 commit comments