BedrockAgentCoreControl / Client / update_online_evaluation_config

update_online_evaluation_config

BedrockAgentCoreControl.Client.update_online_evaluation_config(**kwargs)

Updates an online evaluation configuration’s settings, including rules, data sources, evaluators, and execution status. Changes take effect immediately for ongoing evaluations.

See also: AWS API Documentation

Request Syntax

response = client.update_online_evaluation_config(
    clientToken='string',
    onlineEvaluationConfigId='string',
    description='string',
    rule={
        'samplingConfig': {
            'samplingPercentage': 123.0
        },
        'filters': [
            {
                'key': 'string',
                'operator': 'Equals'|'NotEquals'|'GreaterThan'|'LessThan'|'GreaterThanOrEqual'|'LessThanOrEqual'|'Contains'|'NotContains',
                'value': {
                    'stringValue': 'string',
                    'doubleValue': 123.0,
                    'booleanValue': True|False
                }
            },
        ],
        'sessionConfig': {
            'sessionTimeoutMinutes': 123
        }
    },
    dataSourceConfig={
        'cloudWatchLogs': {
            'logGroupNames': [
                'string',
            ],
            'logGroupNamePrefixes': [
                'string',
            ],
            'serviceNames': [
                'string',
            ]
        }
    },
    evaluators=[
        {
            'evaluatorId': 'string'
        },
    ],
    insights=[
        {
            'insightId': 'string'
        },
    ],
    clusteringConfig={
        'frequencies': [
            'DAILY'|'WEEKLY'|'MONTHLY',
        ]
    },
    outputConfig={
        'cloudWatchConfig': {
            'logGroupName': 'string',
            'metricsNamespace': 'string',
            'resultDestination': 'DEDICATED_LOG_GROUP'|'SOURCE_LOG_GROUP'
        }
    },
    evaluationExecutionRoleArn='string',
    executionStatus='ENABLED'|'DISABLED'
)
Parameters:

  • clientToken (string) –

    A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If you don’t specify this field, a value is randomly generated for you. If this token matches a previous request, the service ignores the request, but doesn’t return an error. For more information, see Ensuring idempotency.

    This field is autopopulated if not provided.

  • onlineEvaluationConfigId (string) –

    [REQUIRED]

    The unique identifier of the online evaluation configuration to update.

  • description (string) – The updated description of the online evaluation configuration.

  • rule (dict) –

    The updated evaluation rule containing sampling configuration, filters, and session settings.

    • samplingConfig (dict) – [REQUIRED]

      The sampling configuration that determines what percentage of agent traces to evaluate.

      • samplingPercentage (float) – [REQUIRED]

        The percentage of agent traces to sample for evaluation, ranging from 0.01% to 100%.

    • filters (list) –

      The list of filters that determine which agent traces should be included in the evaluation based on trace properties.

      • (dict) –

        The filter that applies conditions to agent traces during online evaluation to determine which traces should be evaluated.

        • key (string) – [REQUIRED]

          The key or field name to filter on within the agent trace data.

        • operator (string) – [REQUIRED]

          The comparison operator to use for filtering.

        • value (dict) – [REQUIRED]

          The value to compare against using the specified operator.

          Note

          This is a Tagged Union structure. Only one of the following top level keys can be set: stringValue, doubleValue, booleanValue.

          • stringValue (string) –

            The string value for text-based filtering.

          • doubleValue (float) –

            The numeric value for numerical filtering and comparisons.

          • booleanValue (boolean) –

            The boolean value for true/false filtering conditions.

    • sessionConfig (dict) –

      The session configuration that defines timeout settings for detecting when agent sessions are complete and ready for evaluation.

      • sessionTimeoutMinutes (integer) – [REQUIRED]

        The number of minutes of inactivity after which an agent session is considered complete and ready for evaluation. Default is 15 minutes.

  • dataSourceConfig (dict) –

    The updated data source configuration specifying CloudWatch log groups and service names to monitor.

    Note

    This is a Tagged Union structure. Only one of the following top level keys can be set: cloudWatchLogs.

    • cloudWatchLogs (dict) –

      The CloudWatch logs configuration for reading agent traces from log groups.

      • logGroupNames (list) –

        The list of CloudWatch log group names to monitor for agent traces.

        • (string) –

      • logGroupNamePrefixes (list) –

        The list of CloudWatch log group name prefixes to monitor for agent traces. Specify this instead of logGroupNames to match log groups by prefix. Specify either logGroupNames or logGroupNamePrefixes, not both. One of the two is required.

        • (string) –

          Prefix of a CloudWatch Logs log group name.

      • serviceNames (list) – [REQUIRED]

        The list of service names to filter traces within the specified log groups. Used to identify relevant agent sessions.

        • (string) –

  • evaluators (list) –

    The updated list of evaluators to apply during online evaluation.

    • (dict) –

      The reference to an evaluator used in online evaluation configurations, containing the evaluator identifier.

      Note

      This is a Tagged Union structure. Only one of the following top level keys can be set: evaluatorId.

      • evaluatorId (string) –

        The unique identifier of the evaluator. Can reference builtin evaluators (e.g., Builtin.Helpfulness) or custom evaluators.

  • insights (list) –

    The updated list of insight types to run against agent sessions.

    • (dict) –

      A reference to an insight analysis to run against sessions during evaluation. Insights provide deeper analysis beyond individual evaluator scores, including failure detection, user intent clustering, and execution summarization.

      • insightId (string) – [REQUIRED]

        The unique identifier of the insight to run.

  • clusteringConfig (dict) –

    The updated clustering configuration for periodic batch evaluation.

    • frequencies (list) – [REQUIRED]

      The list of frequencies at which clustering batch evaluations are triggered.

      • (string) –

  • outputConfig (dict) –

    The configuration that specifies where evaluation results should be written for monitoring and analysis.

    • cloudWatchConfig (dict) – [REQUIRED]

      The CloudWatch configuration for writing evaluation results to CloudWatch logs with embedded metric format.

      • logGroupName (string) –

        The name of the CloudWatch log group where evaluation results will be written. An existing log group is used as-is; otherwise the service creates it, which requires the evaluation execution role to grant logs:CreateLogGroup on the log group. Don’t specify this value when resultDestination is SOURCE_LOG_GROUP. The name can’t be under the service-reserved /aws/bedrock-agentcore/evaluations/ namespace, apart from this configuration’s own service-managed default group.

      • metricsNamespace (string) –

        The CloudWatch metrics namespace where evaluation result metrics are published. If you omit this value, the service publishes metrics to Bedrock-AgentCore/Evaluations. This value can’t begin with AWS/.

      • resultDestination (string) –

        The destination where evaluation results are written. Valid values:

        • DEDICATED_LOG_GROUP (default) – Writes results to a dedicated result log group.

        • SOURCE_LOG_GROUP – Writes results back to the log group that the agent traces were read from. If you use this value, don’t specify logGroupName.

  • evaluationExecutionRoleArn (string) – The updated Amazon Resource Name (ARN) of the IAM role used for evaluation execution.

  • executionStatus (string) – The updated execution status to enable or disable the online evaluation.

Return type:

dict

Returns:

Response Syntax

{
    'onlineEvaluationConfigArn': 'string',
    'onlineEvaluationConfigId': 'string',
    'updatedAt': datetime(2015, 1, 1),
    'status': 'ACTIVE'|'CREATING'|'CREATE_FAILED'|'UPDATING'|'UPDATE_FAILED'|'DELETING'|'ERROR',
    'executionStatus': 'ENABLED'|'DISABLED',
    'failureReason': 'string'
}

Response Structure

  • (dict) –

    • onlineEvaluationConfigArn (string) –

      The Amazon Resource Name (ARN) of the updated online evaluation configuration.

    • onlineEvaluationConfigId (string) –

      The unique identifier of the updated online evaluation configuration.

    • updatedAt (datetime) –

      The timestamp when the online evaluation configuration was last updated.

    • status (string) –

      The status of the online evaluation configuration.

    • executionStatus (string) –

      The execution status indicating whether the online evaluation is currently running.

    • failureReason (string) –

      The reason for failure if the online evaluation configuration update or execution failed.

Exceptions