Skip to content

Commit 5639062

Browse files
authored
Update how-to-secure-online-endpoint.md
1 parent ac0cc82 commit 5639062

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

articles/machine-learning/how-to-secure-online-endpoint.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -125,7 +125,7 @@ To restrict communication between a deployment and external resources, including
125125
> You cannot update (enable or disable) the `egress_public_network_access` flag after creating the deployment. Attempting to change the flag while updating the deployment will fail with an error.
126126
127127
> [!NOTE]
128-
> For online deployments with `egress_public_network_access` flag set to `disabled`, access from the deployments to Microsoft Container Registry (MCR) is restricted. If you want to leverage container images from MCR (such as when using curated environment or mlflow no-code deployment), recommendation is to build the image locally inside the VNET ([docker build](https://docs.docker.com/engine/reference/commandline/build/)) and push the image into the private Azure Container Registry (ACR) which is attached with the workspace (for instance, using [docker push](../container-registry/container-registry-get-started-docker-cli.md#push-the-image-to-your-registry)). The images in this ACR is accessible to secured deployments via the private endpoints which are automatically created on behalf of you when you set `egress_public_network_access` flag to `disabled`. For a quick example, please refer to [build image under VNET](https://github.com/Azure/azureml-examples/blob/main/cli/endpoints/online/managed/vnet/setup_vm/scripts/build_image.sh) and [end to end example for model deployment under VNET](https://github.com/Azure/azureml-examples/blob/main/cli/deploy-moe-vnet.sh).
128+
> For online deployments with `egress_public_network_access` flag set to `disabled`, access from the deployments to Microsoft Container Registry (MCR) is restricted. If you want to leverage container images from MCR (such as when using curated environment or mlflow no-code deployment), recommendation is to build the image locally inside the VNET ([docker build](https://docs.docker.com/engine/reference/commandline/build/)) and push the image into the private Azure Container Registry (ACR) which is attached with the workspace (for instance, using [docker push](../container-registry/container-registry-get-started-docker-cli.md#push-the-image-to-your-registry)). The images in this ACR is accessible to secured deployments via the private endpoints which are automatically created on behalf of you when you set `egress_public_network_access` flag to `disabled`. For a quick example, please refer to [build image under virtual network](https://github.com/Azure/azureml-examples/blob/main/cli/endpoints/online/managed/vnet/setup_vm/scripts/build_image.sh) and [end to end example for model deployment under virtual network](https://github.com/Azure/azureml-examples/blob/main/cli/deploy-moe-vnet.sh).
129129
130130
# [Azure CLI](#tab/cli)
131131

0 commit comments

Comments
 (0)