Define runtime parameters¶

Define environment variables to supply different values to custom model code at runtime by including them as runtime parameters, making your custom model easier to reuse. Define runtime parameters in code or through the UI:

• Code: Provide a model-metadata.yaml file in the model artifact. Define this file before uploading a model to Workshop, or use the template available in Workshop through a custom model's Files > Create dropdown. The YAML structure is defined on this page.

• UI: Define runtime parameters in the Runtime parameters section of the custom model in Workshop. For more information, see the Create custom models documentation.

Runtime parameters are injected into containers in two ways:

1. As standard environment variables without prefixes or JSON parsing for simple types (so you can use os.getenv to access environment variables without the datarobot-drum library).
2. For backward compatibility also in the legacy prefixed (MLOPS_RUNTIME_PARAM_*) and JSONified format.

Parameters created via the Workshop UI persist and merge when you upload new code versions, ensuring a seamless development flow.

{"awsAccessKeyId": "<your-key-id>", "awsSecretAccessKey": "<your-access-key>"}

MAIN_AWS_CREDENTIAL_AWS_ACCESS_KEY_ID="<your-key-id>"
MAIN_AWS_CREDENTIAL_AWS_SECRET_ACCESS_KEY="<your-access-key>"

To change runtime parameter values for an existing deployment, deactivate the deployment, update the values in the deployment's Settings > Resources tab, and then reactivate the deployment. For details, see Configure deployment resource settings.

Runtime parameter definitions¶

Add runtime parameters to a custom model through the model metadata, making your custom model code easier to reuse. To define runtime parameters, you can add the following runtimeParameterDefinitions in model-metadata.yaml:

DataRobot reserved runtime parameters¶

The following runtime parameter is reserved by DataRobot for custom model configuration:

Define custom model metadata¶

Before you define runtimeParameterDefinitions in model-metadata.yaml, define the custom model metadata required for the target type. For binary and multiclass models, that includes an inferenceModel block (targetName and class labels; for multiclass, classLabels).

name: binary-example
targetType: binary
type: inference
inferenceModel:
  targetName: target
  positiveClassLabel: "1"
  negativeClassLabel: "0"

name: regression-example
targetType: regression
type: inference

name: textgeneration-example
targetType: textgeneration
type: inference

name: anomaly-example
targetType: anomaly
type: inference

name: unstructured-example
targetType: unstructured
type: inference

name: multiclass-example
targetType: multiclass
type: inference
inferenceModel:
  targetName: class
  classLabels:
    - class_a
    - class_b
    - class_c

Then, below the model information, you can provide the runtimeParameterDefinitions:

name: runtime-parameter-example
targetType: regression
type: inference

runtimeParameterDefinitions:
- fieldName: my_first_runtime_parameter
  type: string
  description: My first runtime parameter.

- fieldName: runtime_parameter_with_default_value
  type: string
  defaultValue: Default
  description: A string-type runtime parameter with a default value.

- fieldName: runtime_parameter_boolean
  type: boolean
  defaultValue: true
  description: A boolean-type runtime parameter with a default value of true.

- fieldName: runtime_parameter_numeric
  type: numeric
  defaultValue: 0
  minValue: -100
  maxValue: 100
  description: A boolean-type runtime parameter with a default value of 0, a minimum value of -100, and a maximum value of 100.

- fieldName: runtime_parameter_for_credentials
  type: credential
  credentialType: basic
  allowEmpty: false
  description: A runtime parameter containing a dictionary of credentials; credentials must be provided before registering the custom model.

- fieldName: runtime_parameter_for_connected_deployment
  type: deployment
  description: A runtime parameter defined to accept the deployment ID of another deployment to connect to the deployed custom model.

Provide credentials through runtime parameters¶

The credential runtime parameter type supports any credentialType value available in the DataRobot REST API. At runtime, credential payloads are also reflected as environment variables in the container; see the runtime parameter considerations for naming rules (single-field types such as api_token, bearer, and gcp use the bare parameter name; multi-field types such as basic and s3 use suffixed names per field).

You can provide credentials in two ways:

• Reference existing credentials: Use the credential ID as the defaultValue to reference credentials defined in the DataRobot Credentials management section.

• Provide credential values directly: Include the full credential structure when defining the runtime parameter (typically used during local development with DRUM).

Reference existing credentials¶

To reference an existing credential, set the defaultValue to the credential ID:

- fieldName: my_api_token
  type: credential
  credentialType: api_token
  allowEmpty: false
  defaultValue: <credential-id>
  description: A runtime parameter referencing an existing API token credential.

Provide credential values directly¶

The credential information required depends on the credentialType, as shown in the examples below:

basic:
  credentialType: basic
  description: string
  name: string
  password: string
  user: string
        

azure:
  credentialType: azure
  description: string
  name: string
  azureConnectionString: string
        

gcp:
  credentialType: gcp
  description: string
  name: string
  gcpKey: string
        

s3:
  credentialType: s3
  description: string
  name: string
  awsAccessKeyId: string
  awsSecretAccessKey: string
  awsSessionToken: string
        

api_token:
  credentialType: api_token
  apiToken: string
  name: string
        

Provide override values during local development¶

For local development with DRUM, you can specify a .yaml file containing the values of the runtime parameters. The values defined here override the defaultValue set in model-metadata.yaml:

my_first_runtime_parameter: Hello, world.
runtime_parameter_with_default_value: Override the default value.
runtime_parameter_for_credentials:
  credentialType: basic
  name: credentials
  password: password1
  user: user1

When using DRUM, the --runtime-params-file option specifies the file containing the runtime parameter values:

drum score --runtime-params-file .runtime-parameters.yaml --code-dir model_templates/python3_sklearn --target-type regression --input tests/testdata/juniors_3_year_stats_regression.csv

Import and use runtime parameters in custom code¶

To import and access runtime parameters, you can import the RuntimeParameters module in your code in custom.py:

from datarobot_drum import RuntimeParameters


def mask(value, visible=3):
    return value[:visible] + ("*" * len(value[visible:]))


def transform(data, model):
    print("Loading the following Runtime Parameters:")
    parameter1 = RuntimeParameters.get("my_first_runtime_parameter")
    parameter2 = RuntimeParameters.get("runtime_parameter_with_default_value")
    print(f"\tParameter 1: {parameter1}")
    print(f"\tParameter 2: {parameter2}")

    credentials = RuntimeParameters.get("runtime_parameter_for_credentials")
    if credentials is not None:
        credential_type = credentials.pop("credentialType")
        print(
            f"\tCredentials (type={credential_type}): "
            + str({k: mask(v) for k, v in credentials.items()})
        )
    else:
        print("No credential data set")
    return data