BedrockAgentCoreControl / Client / get_online_evaluation_config

get_online_evaluation_config

BedrockAgentCoreControl.Client.get_online_evaluation_config(**kwargs)

Retrieves detailed information about an online evaluation configuration, including its rules, data sources, evaluators, and execution status.

See also: AWS API Documentation

Request Syntax

response = client.get_online_evaluation_config(
    onlineEvaluationConfigId='string'
)
Parameters:

onlineEvaluationConfigId (string) –

[REQUIRED]

The unique identifier of the online evaluation configuration to retrieve.

Return type:

dict

Returns:

Response Syntax

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

Response Structure

  • (dict) –

    • onlineEvaluationConfigArn (string) –

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

    • onlineEvaluationConfigId (string) –

      The unique identifier of the online evaluation configuration.

    • onlineEvaluationConfigName (string) –

      The name of the online evaluation configuration.

    • description (string) –

      The description of the online evaluation configuration.

    • rule (dict) –

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

      • samplingConfig (dict) –

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

        • samplingPercentage (float) –

          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) –

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

          • operator (string) –

            The comparison operator to use for filtering.

          • value (dict) –

            The value to compare against using the specified operator.

            Note

            This is a Tagged Union structure. Only one of the following top level keys will be set: stringValue, doubleValue, booleanValue. If a client receives an unknown member it will set SDK_UNKNOWN_MEMBER as the top level key, which maps to the name or tag of the unknown member. The structure of SDK_UNKNOWN_MEMBER is as follows:

            'SDK_UNKNOWN_MEMBER': {'name': 'UnknownMemberName'}

            • 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) –

          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 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 will be set: cloudWatchLogs. If a client receives an unknown member it will set SDK_UNKNOWN_MEMBER as the top level key, which maps to the name or tag of the unknown member. The structure of SDK_UNKNOWN_MEMBER is as follows:

      'SDK_UNKNOWN_MEMBER': {'name': 'UnknownMemberName'}

      • 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) –

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

          • (string) –

    • evaluators (list) –

      The list of evaluators applied 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 will be set: evaluatorId. If a client receives an unknown member it will set SDK_UNKNOWN_MEMBER as the top level key, which maps to the name or tag of the unknown member. The structure of SDK_UNKNOWN_MEMBER is as follows:

        'SDK_UNKNOWN_MEMBER': {'name': 'UnknownMemberName'}

        • evaluatorId (string) –

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

    • insights (list) –

      The list of insight types configured for this evaluation.

      • (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) –

          The unique identifier of the insight to run.

    • clusteringConfig (dict) –

      The clustering configuration for periodic batch evaluation.

      • frequencies (list) –

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

        • (string) –

    • outputConfig (dict) –

      The output configuration specifying where evaluation results are written.

      • cloudWatchConfig (dict) –

        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 Amazon Resource Name (ARN) of the IAM role used for evaluation execution.

    • status (string) –

      The status of the online evaluation configuration.

    • executionStatus (string) –

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

    • createdAt (datetime) –

      The timestamp when the online evaluation configuration was created.

    • updatedAt (datetime) –

      The timestamp when the online evaluation configuration was last updated.

    • failureReason (string) –

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

Exceptions