List Evaluation Runs by Test Case

client.Agents.EvaluationTestCases.ListEvaluationRuns(ctx, evaluationTestCaseUuid, query) (*AgentEvaluationTestCaseListEvaluationRunsResponse, error)

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

To list all evaluation runs by test case, send a GET request to /v2/gen-ai/evaluation_test_cases/{evaluation_test_case_uuid}/evaluation_runs.

ParametersExpand Collapse

evaluationTestCaseUuid string

query AgentEvaluationTestCaseListEvaluationRunsParams

EvaluationTestCaseVersion param.Field[int64]optional

Version of the test case.

ReturnsExpand Collapse

type AgentEvaluationTestCaseListEvaluationRunsResponse struct{…}

EvaluationRuns []APIEvaluationRunoptional

List of evaluation runs.

AgentDeleted booloptional

Whether agent is deleted

AgentDeploymentName stringoptional

The agent deployment name

AgentName stringoptional

Agent name

AgentUuid stringoptional

Agent UUID.

AgentVersionHash stringoptional

Version hash

AgentWorkspaceUuid stringoptional

Agent workspace uuid

CreatedByUserEmail stringoptional

CreatedByUserID stringoptional

formatuint64

ErrorDescription stringoptional

The error description

EvaluationRunUuid stringoptional

Evaluation run UUID.

EvaluationTestCaseWorkspaceUuid stringoptional

Evaluation test case workspace uuid

FinishedAt Timeoptional

Run end time.

formatdate-time

PassStatus booloptional

The pass status of the evaluation run based on the star metric.

QueuedAt Timeoptional

Run queued time.

formatdate-time

RunLevelMetricResults []APIEvaluationMetricResultoptional

ErrorDescription stringoptional

Error description if the metric could not be calculated.

MetricName stringoptional

Metric name

MetricValueType APIEvaluationMetricResultMetricValueTypeoptional

Accepts one of the following:

const APIEvaluationMetricResultMetricValueTypeMetricValueTypeUnspecified APIEvaluationMetricResultMetricValueType = "METRIC_VALUE_TYPE_UNSPECIFIED"

const APIEvaluationMetricResultMetricValueTypeMetricValueTypeNumber APIEvaluationMetricResultMetricValueType = "METRIC_VALUE_TYPE_NUMBER"

const APIEvaluationMetricResultMetricValueTypeMetricValueTypeString APIEvaluationMetricResultMetricValueType = "METRIC_VALUE_TYPE_STRING"

const APIEvaluationMetricResultMetricValueTypeMetricValueTypePercentage APIEvaluationMetricResultMetricValueType = "METRIC_VALUE_TYPE_PERCENTAGE"

NumberValue float64optional

The value of the metric as a number.

formatdouble

Reasoning stringoptional

Reasoning of the metric result.

StringValue stringoptional

The value of the metric as a string.

RunName stringoptional

Run name.

StarMetricResult APIEvaluationMetricResultoptional

ErrorDescription stringoptional

Error description if the metric could not be calculated.

MetricName stringoptional

Metric name

MetricValueType APIEvaluationMetricResultMetricValueTypeoptional

Accepts one of the following:

const APIEvaluationMetricResultMetricValueTypeMetricValueTypeUnspecified APIEvaluationMetricResultMetricValueType = "METRIC_VALUE_TYPE_UNSPECIFIED"

const APIEvaluationMetricResultMetricValueTypeMetricValueTypeNumber APIEvaluationMetricResultMetricValueType = "METRIC_VALUE_TYPE_NUMBER"

const APIEvaluationMetricResultMetricValueTypeMetricValueTypeString APIEvaluationMetricResultMetricValueType = "METRIC_VALUE_TYPE_STRING"

const APIEvaluationMetricResultMetricValueTypeMetricValueTypePercentage APIEvaluationMetricResultMetricValueType = "METRIC_VALUE_TYPE_PERCENTAGE"

NumberValue float64optional

The value of the metric as a number.

formatdouble

Reasoning stringoptional

Reasoning of the metric result.

StringValue stringoptional

The value of the metric as a string.

StartedAt Timeoptional

Run start time.

formatdate-time

Status APIEvaluationRunStatusoptional

Evaluation Run Statuses

Accepts one of the following:

const APIEvaluationRunStatusEvaluationRunStatusUnspecified APIEvaluationRunStatus = "EVALUATION_RUN_STATUS_UNSPECIFIED"

const APIEvaluationRunStatusEvaluationRunQueued APIEvaluationRunStatus = "EVALUATION_RUN_QUEUED"

const APIEvaluationRunStatusEvaluationRunRunningDataset APIEvaluationRunStatus = "EVALUATION_RUN_RUNNING_DATASET"

const APIEvaluationRunStatusEvaluationRunEvaluatingResults APIEvaluationRunStatus = "EVALUATION_RUN_EVALUATING_RESULTS"

const APIEvaluationRunStatusEvaluationRunCancelling APIEvaluationRunStatus = "EVALUATION_RUN_CANCELLING"

const APIEvaluationRunStatusEvaluationRunCancelled APIEvaluationRunStatus = "EVALUATION_RUN_CANCELLED"

const APIEvaluationRunStatusEvaluationRunSuccessful APIEvaluationRunStatus = "EVALUATION_RUN_SUCCESSFUL"

const APIEvaluationRunStatusEvaluationRunPartiallySuccessful APIEvaluationRunStatus = "EVALUATION_RUN_PARTIALLY_SUCCESSFUL"

const APIEvaluationRunStatusEvaluationRunFailed APIEvaluationRunStatus = "EVALUATION_RUN_FAILED"

TestCaseDescription stringoptional

Test case description.

TestCaseName stringoptional

Test case name.

TestCaseUuid stringoptional

Test-case UUID.

TestCaseVersion int64optional

Test-case-version.

formatint64

List Evaluation Runs by Test Case

package main

import (
  "context"
  "fmt"

  "github.com/stainless-sdks/-go"
  "github.com/stainless-sdks/-go/option"
)

func main() {
  client := gradient.NewClient(
    option.WithAccessToken("My Access Token"),
  )
  response, err := client.Agents.EvaluationTestCases.ListEvaluationRuns(
    context.TODO(),
    `"123e4567-e89b-12d3-a456-426614174000"`,
    gradient.AgentEvaluationTestCaseListEvaluationRunsParams{

    },
  )
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", response.EvaluationRuns)
}

{
  "evaluation_runs": [
    {
      "agent_deleted": true,
      "agent_deployment_name": "example name",
      "agent_name": "example name",
      "agent_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "agent_version_hash": "example string",
      "agent_workspace_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "created_by_user_email": "example@example.com",
      "created_by_user_id": "12345",
      "error_description": "example string",
      "evaluation_run_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "evaluation_test_case_workspace_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "finished_at": "2023-01-01T00:00:00Z",
      "pass_status": true,
      "queued_at": "2023-01-01T00:00:00Z",
      "run_level_metric_results": [
        {
          "error_description": "example string",
          "metric_name": "example name",
          "metric_value_type": "METRIC_VALUE_TYPE_UNSPECIFIED",
          "number_value": 123,
          "reasoning": "example string",
          "string_value": "example string"
        }
      ],
      "run_name": "example name",
      "star_metric_result": {
        "error_description": "example string",
        "metric_name": "example name",
        "metric_value_type": "METRIC_VALUE_TYPE_UNSPECIFIED",
        "number_value": 123,
        "reasoning": "example string",
        "string_value": "example string"
      },
      "started_at": "2023-01-01T00:00:00Z",
      "status": "EVALUATION_RUN_STATUS_UNSPECIFIED",
      "test_case_description": "example string",
      "test_case_name": "example name",
      "test_case_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "test_case_version": 123
    }
  ]
}

Returns Examples

{
  "evaluation_runs": [
    {
      "agent_deleted": true,
      "agent_deployment_name": "example name",
      "agent_name": "example name",
      "agent_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "agent_version_hash": "example string",
      "agent_workspace_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "created_by_user_email": "example@example.com",
      "created_by_user_id": "12345",
      "error_description": "example string",
      "evaluation_run_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "evaluation_test_case_workspace_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "finished_at": "2023-01-01T00:00:00Z",
      "pass_status": true,
      "queued_at": "2023-01-01T00:00:00Z",
      "run_level_metric_results": [
        {
          "error_description": "example string",
          "metric_name": "example name",
          "metric_value_type": "METRIC_VALUE_TYPE_UNSPECIFIED",
          "number_value": 123,
          "reasoning": "example string",
          "string_value": "example string"
        }
      ],
      "run_name": "example name",
      "star_metric_result": {
        "error_description": "example string",
        "metric_name": "example name",
        "metric_value_type": "METRIC_VALUE_TYPE_UNSPECIFIED",
        "number_value": 123,
        "reasoning": "example string",
        "string_value": "example string"
      },
      "started_at": "2023-01-01T00:00:00Z",
      "status": "EVALUATION_RUN_STATUS_UNSPECIFIED",
      "test_case_description": "example string",
      "test_case_name": "example name",
      "test_case_uuid": "123e4567-e89b-12d3-a456-426614174000",
      "test_case_version": 123
    }
  ]
}