Create and manage models

This page shows you how to create and manage AML AI models. Create a model to start AML AI's ML training pipeline. You can use a model to run predictions or backtest across various datasets.

You only need to create the model and export the associated metadata at this point.The other model methods are provided for completeness.

Before you begin

• To get the permissions that you need to create and manage engine models, ask your administrator to grant you the Financial Services Admin ( financialservices.admin ) IAM role on your project. For more information about granting roles, see Manage access to projects, folders, and organizations .

  You might also be able to get the required permissions through custom roles or other predefined roles .

• Create an instance
• Create an engine config
• Create a dataset

Create a model

Some API methods return a long-running operation (LRO). These methods are asynchronous and return an Operation object; for details, see REST Reference . The operation might not be completed when the method returns a response. For these methods, send the request and then check for the result. In general, all POST, PUT, UPDATE, and DELETE operations are long-running.

Send the request

To create a model, use the projects.locations.instances.models.create method.

Before using any of the request data, make the following replacements:

• PROJECT_ID : your Google Cloud project ID listed in the IAM Settings
• LOCATION : the location of the instance; use one of the supported regions
  Show locations
  • us-central1
  • us-east1
  • asia-south1
  • europe-west1
  • europe-west2
  • europe-west4
  • northamerica-northeast1
  • southamerica-east1
  • australia-southeast1
• INSTANCE_ID : the user-defined identifier for the instance
• MODEL_ID : a user-defined identifier for the model
• ENGINE_CONFIG_ID : a user-defined identifier for the engine config
• DATASET_ID : the user-defined identifier for the primary dataset used for training this model
• TRAINING_END_DATE : The latest time from which data is used to generate features for training. This date should be the same or earlier than the end time of the primary dataset. Use RFC3339 UTC "Zulu" format (for example, 2014-10-02T15:01:23Z ).

Request JSON body:

{
    "engineConfig": "projects/ PROJECT_ID 
/locations/ LOCATION 
/instances/ INSTANCE_ID 
/engineConfigs/ ENGINE_CONFIG_ID 
",
    "primaryDataset": "projects/ PROJECT_ID 
/locations/ LOCATION 
/instances/ INSTANCE_ID 
/datasets/ DATASET_ID 
",
    "endTime": " TRAINING_END_DATE 
"
}

To send your request, choose one of these options:

cat > request.json << 'EOF'
{
    "engineConfig": "projects/ PROJECT_ID 
/locations/ LOCATION 
/instances/ INSTANCE_ID 
/engineConfigs/ ENGINE_CONFIG_ID 
",
    "primaryDataset": "projects/ PROJECT_ID 
/locations/ LOCATION 
/instances/ INSTANCE_ID 
/datasets/ DATASET_ID 
",
    "endTime": " TRAINING_END_DATE 
"
}
EOF

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://financialservices.googleapis.com/v1/projects/ PROJECT_ID 
/locations/ LOCATION 
/instances/ INSTANCE_ID 
/models?model_id= MODEL_ID 
"

@'
{
    "engineConfig": "projects/ PROJECT_ID 
/locations/ LOCATION 
/instances/ INSTANCE_ID 
/engineConfigs/ ENGINE_CONFIG_ID 
",
    "primaryDataset": "projects/ PROJECT_ID 
/locations/ LOCATION 
/instances/ INSTANCE_ID 
/datasets/ DATASET_ID 
",
    "endTime": " TRAINING_END_DATE 
"
}
'@  | Out-File -FilePath request.json -Encoding utf8

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://financialservices.googleapis.com/v1/projects/ PROJECT_ID 
/locations/ LOCATION 
/instances/ INSTANCE_ID 
/models?model_id= MODEL_ID 
" | Select-Object -Expand Content

You should receive a JSON response similar to the following:

{
  "name": "projects/ PROJECT_ID 
/locations/ LOCATION 
/operations/ OPERATION_ID 
",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.financialservices.v1.OperationMetadata",
    "createTime": "2023-03-14T15:52:55.358979323Z",
    "target": "projects/ PROJECT_ID 
/locations/ LOCATION 
/instances/ INSTANCE_ID 
/models/ MODEL_ID 
",
    "verb": "create",
    "requestedCancellation": false,
    "apiVersion": "v1"
  },
  "done": false
}

Check for the result

Use the projects.locations.operations.get method to check if the model has been created. If the response contains "done": false , repeat the command until the response contains "done": true . These operations can take a few minutes to several hours to complete.

Permissions required for this task

To perform this task, you must have been granted the following permissions:

Permissions

• financialservices.operations.get