배치 평가 시작

CLI는를 사용할 때 프로젝트 구성에서 serviceNames 및를 logGroupNames 자동으로 확인합니다--runtime.

agentcore run batch-evaluation \
  --runtime MyAgent \
  --evaluator Builtin.GoalSuccessRate Builtin.Helpfulness Builtin.Faithfulness

선택적 플래그가 있는 경우:

# Custom name and lookback window
agentcore run batch-evaluation \
  --runtime MyAgent \
  --evaluator Builtin.GoalSuccessRate \
  --name my_baseline_eval \
  --lookback-days 1

# Specific sessions
agentcore run batch-evaluation \
  --runtime MyAgent \
  --evaluator Builtin.GoalSuccessRate \
  --session-ids session-abc123 session-def456

# With ground truth
agentcore run batch-evaluation \
  --runtime MyAgent \
  --evaluator Builtin.GoalSuccessRate Builtin.Correctness \
  --ground-truth ground-truth.json

기본적으로 명령은 작업을 시작하고 즉시 반환합니다. 작업이 터미널 상태(COMPLETED, FAILED또는 STOPPED)에 도달할 때까지 --wait를 블록으로 전달하면 CLI가 평가자당 평균 점수를 표시하고 결과를에 저장합니다.cli/jobs/batch-eval-results/.

agentcore run batch-evaluation는 다음 플래그도 지원합니다.

import boto3
import uuid
import time
import json

client = boto3.client("bedrock-agentcore", region_name="us-west-2")

# All sessions in the log group
response = client.start_batch_evaluation(
    batchEvaluationName=f"baseline_eval_{uuid.uuid4().hex[:8]}",
    evaluators=[
        {"evaluatorId": "Builtin.GoalSuccessRate"},
        {"evaluatorId": "Builtin.Helpfulness"},
        {"evaluatorId": "Builtin.Faithfulness"},
    ],
    dataSourceConfig={
        "cloudWatchLogs": {
            "serviceNames": ["MyAgent.DEFAULT"],
            "logGroupNames": ["/aws/bedrock-agentcore/runtimes/MyAgent-abc123-DEFAULT"],
        }
    },
    clientToken=str(uuid.uuid4()),
)

batch_eval_id = response["batchEvaluationId"]
print(f"Started: {batch_eval_id}")

# Poll until complete
while True:
    result = client.get_batch_evaluation(batchEvaluationId=batch_eval_id)
    status = result["status"]
    print(f"Status: {status}")

    if status in ("COMPLETED", "COMPLETED_WITH_ERRORS", "FAILED", "STOPPED"):
        break
    time.sleep(30)

print(json.dumps(result, indent=4, default=str))

세션 ID 필터링 사용:

response = client.start_batch_evaluation(
    batchEvaluationName=f"targeted-eval-{uuid.uuid4().hex[:8]}",
    evaluators=[
        {"evaluatorId": "Builtin.GoalSuccessRate"},
    ],
    dataSourceConfig={
        "cloudWatchLogs": {
            "serviceNames": ["MyAgent.DEFAULT"],
            "logGroupNames": ["/aws/bedrock-agentcore/runtimes/MyAgent-abc123-DEFAULT"],
            "filterConfig": {
                "sessionIds": ["session-001", "session-002", "session-003"]
            },
        }
    },
    clientToken=str(uuid.uuid4()),
)

시간 범위 필터링 사용:

from datetime import datetime, timedelta, timezone

now = datetime.now(timezone.utc)
response = client.start_batch_evaluation(
    batchEvaluationName=f"weekly-eval-{uuid.uuid4().hex[:8]}",
    evaluators=[
        {"evaluatorId": "Builtin.GoalSuccessRate"},
    ],
    dataSourceConfig={
        "cloudWatchLogs": {
            "serviceNames": ["MyAgent.DEFAULT"],
            "logGroupNames": ["/aws/bedrock-agentcore/runtimes/MyAgent-abc123-DEFAULT"],
            "filterConfig": {
                "timeRange": {
                    "startTime": (now - timedelta(days=7)).isoformat(),
                    "endTime": now.isoformat(),
                }
            },
        }
    },
    clientToken=str(uuid.uuid4()),
)