人間ベースのモデル評価ジョブを作成

aws bedrock create-evaluation-job --cli-input-json file://my_eval_job.json

{
    "jobName": "model-eval-llama-vs-my-other-model",
    "roleArn": "arn:aws:iam::111122223333:role/service-role/Amazon-Bedrock-IAM-Role-20250218T223671",
    "evaluationConfig": {
        "human": {
            "customMetrics": [
                {
                    "description": "Measures the organization and structure of a generated text.",
                    "name": "Coherence",
                    "ratingMethod": "ThumbsUpDown"
                },
                {
                    "description": "Indicates the accuracy of a generated text.",
                    "name": "Accuracy",
                    "ratingMethod": "ComparisonChoice"
                }
            ],
            "datasetMetricConfigs": [
                {
                    "dataset": {
                        "datasetLocation": {
                            "s3Uri": "s3://amzn-s3-demo-bucket/input/model-eval/fitness-dataset-model-eval-byoir-2-models.jsonl"
                        },
                        "name": "dataset1"
                    },
                    "metricNames": [
                        "Coherence",
                        "Accuracy"
                    ],
                    "taskType": "Generation"
                }
            ],
            "humanWorkflowConfig": {
                "flowDefinitionArn": "arn:aws:sagemaker:us-east-1:111122223333:flow-definition/bedrock-fitness-human-byoir",
                "instructions": "<h3>The following are the metrics and their descriptions for this evaluation</h3>\n<p><strong>Coherence</strong>: Measures the organization and structure of a generated text. - <em>Thumbs up/down</em>\n<strong>Accuracy</strong>: Indicates the accuracy of a generated text. - <em>Choice buttons</em></p>\n<h3>Instructions for how to use the evaluation tool</h3>\n<p>The evaluation creator should use this space to write detailed descriptions for every rating method so your evaluators know how to properly rate the responses with the buttons on their screen.</p>\n<h4>For example:</h4>\n<p>If using <strong>Likert scale - individual</strong>, define the 1 and 5 of the 5 point Likert scale for each metric so your evaluators know if 1 or 5 means favorable/acceptable/preferable.\nIf using <strong>Likert scale - comparison</strong>, describe what the evaluator is looking for to determine their preference between two responses.\nIf using <strong>Choice buttons</strong>, describe what is preferred according to your metric and its description.\nIf using <strong>Ordinal ranking</strong>, define what should receive a #1 ranking according to your metric and its description.\nIf using <strong>Thumbs up/down</strong>, define what makes an acceptable response according to your metric and its description.</p>\n<h3>Describing your ground truth responses if applicable to your dataset</h3>\n<p>Describe the purpose of your ground truth responses that will be shown on screen next to each model response. Note that the ground truth responses you provide are not rated/scored by the evaluators - they are meant to be a reference standard for comparison against the model responses.</p>"
            }
        }
    },
    "inferenceConfig": {
        "models": [
            {
                "precomputedInferenceSource": {
                    "inferenceSourceIdentifier": "llama-3-1-80b"
                }
            },
            {
                "precomputedInferenceSource": {
                    "inferenceSourceIdentifier": "my_other_model"
                }
            }
        ]
    },
    "outputDataConfig": {
        "s3Uri": "s3://amzn-s3-demo-bucket/output/"
    }
}