Evaluation Test Cases

API Reference

Agents

Evaluation Test Cases

Create Evaluation Test Case.

client.agents.evaluationTestCases.create(EvaluationTestCaseCreateParams { dataset_uuid, description, metrics, 3 more } body?, RequestOptionsoptions?): EvaluationTestCaseCreateResponse { test_case_uuid }

post/v2/gen-ai/evaluation_test_cases

List Evaluation Test Cases

client.agents.evaluationTestCases.list(RequestOptionsoptions?): EvaluationTestCaseListResponse { evaluation_test_cases }

get/v2/gen-ai/evaluation_test_cases

List Evaluation Runs by Test Case

client.agents.evaluationTestCases.listEvaluationRuns(stringevaluationTestCaseUuid, EvaluationTestCaseListEvaluationRunsParams { evaluation_test_case_version } query?, RequestOptionsoptions?): EvaluationTestCaseListEvaluationRunsResponse { evaluation_runs }

get/v2/gen-ai/evaluation_test_cases/{evaluation_test_case_uuid}/evaluation_runs

Retrieve Information About an Existing Evaluation Test Case

client.agents.evaluationTestCases.retrieve(stringtestCaseUuid, EvaluationTestCaseRetrieveParams { evaluation_test_case_version } query?, RequestOptionsoptions?): EvaluationTestCaseRetrieveResponse { evaluation_test_case }

get/v2/gen-ai/evaluation_test_cases/{test_case_uuid}

Update an Evaluation Test Case.

client.agents.evaluationTestCases.update(stringtestCaseUuid, EvaluationTestCaseUpdateParams { dataset_uuid, description, metrics, 3 more } body?, RequestOptionsoptions?): EvaluationTestCaseUpdateResponse { test_case_uuid, version }

put/v2/gen-ai/evaluation_test_cases/{test_case_uuid}

ModelsExpand Collapse

APIEvaluationTestCase { archived_at, created_at, created_by_user_email, 15 more }

archived_at?: string

created_at?: string

created_by_user_email?: string

created_by_user_id?: string

dataset?: Dataset { created_at, dataset_name, dataset_uuid, 3 more }

created_at?: string

Time created at.

formatdate-time

dataset_name?: string

Name of the dataset.

dataset_uuid?: string

UUID of the dataset.

file_size?: string

The size of the dataset uploaded file in bytes.

formatuint64

has_ground_truth?: boolean

Does the dataset have a ground truth column?

row_count?: number

Number of rows in the dataset.

formatint64

dataset_name?: string

dataset_uuid?: string

description?: string

latest_version_number_of_runs?: number

metrics?: Array<APIEvaluationMetric { description, inverted, metric_name, 5 more } >

description?: string

inverted?: boolean

If true, the metric is inverted, meaning that a lower value is better.

metric_name?: string

metric_type?: "METRIC_TYPE_UNSPECIFIED" | "METRIC_TYPE_GENERAL_QUALITY" | "METRIC_TYPE_RAG_AND_TOOL"

Accepts one of the following:

"METRIC_TYPE_UNSPECIFIED"

"METRIC_TYPE_GENERAL_QUALITY"

"METRIC_TYPE_RAG_AND_TOOL"

metric_uuid?: string

metric_value_type?: "METRIC_VALUE_TYPE_UNSPECIFIED" | "METRIC_VALUE_TYPE_NUMBER" | "METRIC_VALUE_TYPE_STRING" | "METRIC_VALUE_TYPE_PERCENTAGE"

Accepts one of the following:

"METRIC_VALUE_TYPE_UNSPECIFIED"

"METRIC_VALUE_TYPE_NUMBER"

"METRIC_VALUE_TYPE_STRING"

"METRIC_VALUE_TYPE_PERCENTAGE"

range_max?: number

The maximum value for the metric.

formatfloat

range_min?: number

The minimum value for the metric.

formatfloat

name?: string

star_metric?: APIStarMetric { metric_uuid, name, success_threshold, success_threshold_pct }

metric_uuid?: string

name?: string

success_threshold?: number

The success threshold for the star metric. This is a value that the metric must reach to be considered successful.

formatfloat

success_threshold_pct?: number

The success threshold for the star metric. This is a percentage value between 0 and 100.

formatint32

test_case_uuid?: string

total_runs?: number

updated_at?: string

updated_by_user_email?: string

updated_by_user_id?: string

version?: number

APIStarMetric { metric_uuid, name, success_threshold, success_threshold_pct }

metric_uuid?: string

name?: string

success_threshold?: number

The success threshold for the star metric. This is a value that the metric must reach to be considered successful.

formatfloat

success_threshold_pct?: number

The success threshold for the star metric. This is a percentage value between 0 and 100.

formatint32