创建在线评估

# Create online evaluation configuration
agentcore add online-eval \
  --name "your_config_name" \
  --runtime "your_runtime_name" \
  --evaluator "Builtin.GoalSuccessRate" "Builtin.Helpfulness" \
  --sampling-rate 1.0 \
  --enable-on-create

此命令将在线评估配置添加到您的本地agentcore.json。运行agentcore deploy以在您的 AWS 帐户中创建它。

输入在线评估配置的名称。

选择要包括的评估者。您可以从内置评估器和您创建的任何自定义评估器中进行选择。

设置采样率 — 将要评估的代理请求的百分比。

选择部署后是否自动启用评估。

查看配置并按 Enter 进行确认。

from bedrock_agentcore_starter_toolkit import Evaluation

# Initialize the evaluation client
eval_client = Evaluation()

# Replace these with your actual values
config_name = "YOUR_CONFIG_NAME"
agent_id = "YOUR_AGENT_ID"  # e.g., agent_myagent-ABC123xyz

# Create online evaluation configuration
config = eval_client.create_online_config(
    config_name=config_name,                  # Must use underscores, not hyphens
    agent_id=agent_id,                        # Agent ID (e.g., agent_myagent-ABC123xyz)
    sampling_rate=1.0,                        # Percentage to evaluate (0-100). 1.0 = evaluate 1% of interactions
    evaluator_list=["Builtin.GoalSuccessRate", "Builtin.Helpfulness"],  # List of evaluator IDs
    config_description="Online Evaluation Config",  # Optional description
    auto_create_execution_role=True,          # Automatically creates IAM role (default: True)
    enable_on_create=True                     # Enable immediately after creation (default: True)
)

print("✅ Online evaluation configuration created!")
print(f"Config ID: {config['onlineEvaluationConfigId']}")
print(f"Status: {config['status']}")

# Save the config ID for later operations
config_id = config['onlineEvaluationConfigId']
print(f"\nSaved config_id: {config_id}")

import boto3

# Your input log group that contains agent traces
LOG_GROUP_NAME = "/aws/agentcore/test-agent-traces"

# The service.name attribute from Otel
SERVICE_NAME = "strands_healthcare_single_agent.DEFAULT"

# The role created earlier with the required permissions for eval
role_arn = f"arn:aws:iam::{ACCOUNT_ID}:role/AgentCoreEvaluationRole"

client = boto3.client('bedrock-agentcore-control')

create_config_response = client.create_online_evaluation_config(
    onlineEvaluationConfigName="strands_healthcare_agent_1",
    description="Continuous evaluation of a healthcare agent",
    rule={
        "samplingConfig": {"samplingPercentage": 80.0}
    },
    dataSourceConfig={
        "cloudWatchLogs": {
            "logGroupNames": [LOG_GROUP_NAME],
            "serviceNames": [SERVICE_NAME]
        }
    },
    evaluators=[{"evaluatorId":"Builtin.Helpfulness"}],
    evaluationExecutionRoleArn=role_arn,
    enableOnCreate=True
)

aws bedrock-agentcore-control create-online-evaluation-config \
    --online-evaluation-config-name "strands_healthcare_agent_1" \
    --description "Continuous evaluation of a healthcare agent" \
    --rule '{"samplingConfig": {"samplingPercentage": 80.0}}' \
    --data-source-config '{"cloudWatchLogs": {"logGroupNames": ["/aws/agentcore/test-agent-traces"], "serviceNames": ["strands_healthcare_single_agent.DEFAULT"]}}' \
    --evaluators '[{"evaluatorId": "Builtin.Helpfulness"}]' \
    --evaluation-execution-role-arn "arn:aws:iam::{YOUR_ACCOUNT_ID}:role/AgentCoreEvaluationRole" \
    --enable-on-create