Open ashish-jain-microsoft opened 1 year ago
$ az ml online-deployment create --local -n blue --endpoint $ENDPOINT_NAME -f endpoints/online/managed/sample/blue-deployment.yml
Command group 'ml online-deployment' is in preview and under development. Reference and support levels: https://aka.ms/CLI_refstatus
Validation for ManagedOnlineDeploymentSchema failed:
{
"model": [
{
"_schema": [
"In order to specify an existing models, please provide either of the following prefixed with 'azureml:':\n1. The full ARM ID for the resource, e.g.azureml:/subscriptions/<subscription_id>/resourceGroups/<resource_group>/providers/Microsoft.MachineLearningServices/workspaces/<workspace_name>/models/<resource_name>/<version-if applicable>)\n2. The short-hand name of the resource registered in the workspace, eg: azureml:<short-hand-name>:<version-if applicable>. For example, version 1 of the environment registered as 'my-env' in the workspace can be referenced as 'azureml:my-env:1'"
]
},
{
"path": [
"Unknown field."
]
}
],
"code_configuration": {
"code": [
{
"_schema": [
"In order to specify an existing codes, please provide either of the following prefixed with 'azureml:':\n1. The full ARM ID for the resource, e.g.azureml:/subscriptions/<subscription_id>/resourceGroups/<resource_group>/providers/Microsoft.MachineLearningServices/workspaces/<workspace_name>/codes/<resource_name>/<version-if applicable>)\n2. The short-hand name of the resource registered in the workspace, eg: azureml:<short-hand-name>:<version-if applicable>. For example, version 1 of the environment registered as 'my-env' in the workspace can be referenced as 'azureml:my-env:1'"
]
},
{
"_schema": [
"Invalid input type."
]
}
]
}
}
@ashish-jain-microsoft Thanks for your feedback! We will investigate and update as appropriate.
@dem108 Could you please review and add your comments on this, update as appropriate.
@ashish-jain-microsoft Thank you for bringing this to our attention. I've assigned this issue to the author who will investigate and update as appropriate.
When I try the steps as per the document, I get an error when I try to create an AML Online Deployment. I tried both --local and regular option. The instructions and the repo worked great back in February 2022. I am from the Azure Cognitive Services team.
`$ az ml online-deployment create --local -n blue --endpoint $ENDPOINT_NAME -f endpoints/online/managed/sample/blue-deployment.yml Command group 'ml online-deployment' is in preview and under development. Reference and support levels: https://aka.ms/CLI_refstatus Validation for ManagedOnlineDeploymentSchema failed:
{ "model": [ { "_schema": [ "In order to specify an existing models, please provide either of the following prefixed with 'azureml:':\n1. The full ARM ID for the resource, e.g.azureml:/subscriptions//resourceGroups//providers/Microsoft.MachineLearningServices/workspaces//models//)\n2. The short-hand name of the resource registered in the workspace, eg: azureml::. For example, version 1 of the environment registered as 'my-env' in the workspace can be referenced as 'azureml:my-env:1'"
]
},
{
"path": [
"Unknown field."
]
}
],
"code_configuration": {
"code": [
{
"_schema": [
"In order to specify an existing codes, please provide either of the following prefixed with 'azureml:':\n1. The full ARM ID for the resource, e.g.azureml:/subscriptions//resourceGroups//providers/Microsoft.MachineLearningServices/workspaces//codes//)\n2. The short-hand name of the resource registered in the workspace, eg: azureml::. For example, version 1 of the environment registered as 'my-env' in the workspace can be referenced as 'azureml:my-env:1'"
]
},
{
"_schema": [
"Invalid input type."
]
}
]
}
}`
Document Details
⚠ Do not edit this section. It is required for learn.microsoft.com ➟ GitHub issue linking.