Evaluation Runs

API Reference

Agents

Evaluation Runs

Run an Evaluation Test Case

post/v2/gen-ai/evaluation_runs

Retrieve Results of an Evaluation Run

get/v2/gen-ai/evaluation_runs/{evaluation_run_uuid}/results

Retrieve Information About an Existing Evaluation Run

get/v2/gen-ai/evaluation_runs/{evaluation_run_uuid}

Retrieve Results of an Evaluation Run Prompt

get/v2/gen-ai/evaluation_runs/{evaluation_run_uuid}/results/{prompt_id}

ModelsExpand Collapse

APIEvaluationMetric = object { description, inverted, metric_name, 5 more }

description: optional string

inverted: optional boolean

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

metric_name: optional string

metric_type: optional "METRIC_TYPE_UNSPECIFIED" or "METRIC_TYPE_GENERAL_QUALITY" or "METRIC_TYPE_RAG_AND_TOOL"

Accepts one of the following:

"METRIC_TYPE_UNSPECIFIED"

"METRIC_TYPE_GENERAL_QUALITY"

"METRIC_TYPE_RAG_AND_TOOL"

metric_uuid: optional string

metric_value_type: optional "METRIC_VALUE_TYPE_UNSPECIFIED" or "METRIC_VALUE_TYPE_NUMBER" or "METRIC_VALUE_TYPE_STRING" or "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: optional number

The maximum value for the metric.

formatfloat

range_min: optional number

The minimum value for the metric.

formatfloat

APIEvaluationMetricResult = object { error_description, metric_name, metric_value_type, 3 more }

error_description: optional string

Error description if the metric could not be calculated.

metric_name: optional string

Metric name

metric_value_type: optional "METRIC_VALUE_TYPE_UNSPECIFIED" or "METRIC_VALUE_TYPE_NUMBER" or "METRIC_VALUE_TYPE_STRING" or "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"

number_value: optional number

The value of the metric as a number.

formatdouble

reasoning: optional string

Reasoning of the metric result.

string_value: optional string

The value of the metric as a string.

APIEvaluationPrompt = object { ground_truth, input, input_tokens, 5 more }

ground_truth: optional string

The ground truth for the prompt.

input: optional string

input_tokens: optional string

The number of input tokens used in the prompt.

formatuint64

output: optional string

output_tokens: optional string

The number of output tokens used in the prompt.

formatuint64

prompt_chunks: optional array of object { chunk_usage_pct, chunk_used, index_uuid, 2 more }

The list of prompt chunks.

chunk_usage_pct: optional number

The usage percentage of the chunk.

formatdouble

chunk_used: optional boolean

Indicates if the chunk was used in the prompt.

index_uuid: optional string

The index uuid (Knowledge Base) of the chunk.

source_name: optional string

The source name for the chunk, e.g., the file name or document title.

text: optional string

Text content of the chunk.

prompt_id: optional number

Prompt ID

formatint64

prompt_level_metric_results: optional array of APIEvaluationMetricResult

The metric results for the prompt.

APIEvaluationRun = object { agent_deleted, agent_name, agent_uuid, 19 more }

agent_deleted: optional boolean

Whether agent is deleted

agent_name: optional string

Agent name

agent_uuid: optional string

Agent UUID.

agent_version_hash: optional string

Version hash

agent_workspace_uuid: optional string

Agent workspace uuid

created_by_user_email: optional string

created_by_user_id: optional string

error_description: optional string

The error description

evaluation_run_uuid: optional string

Evaluation run UUID.

evaluation_test_case_workspace_uuid: optional string

Evaluation test case workspace uuid

finished_at: optional string

Run end time.

formatdate-time

pass_status: optional boolean

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

queued_at: optional string

Run queued time.

formatdate-time

run_level_metric_results: optional array of APIEvaluationMetricResult

run_name: optional string

Run name.

star_metric_result: optional APIEvaluationMetricResult

started_at: optional string

Run start time.

formatdate-time

status: optional "EVALUATION_RUN_STATUS_UNSPECIFIED" or "EVALUATION_RUN_QUEUED" or "EVALUATION_RUN_RUNNING_DATASET" or 6 more

Evaluation Run Statuses

Accepts one of the following:

"EVALUATION_RUN_STATUS_UNSPECIFIED"

"EVALUATION_RUN_QUEUED"

"EVALUATION_RUN_RUNNING_DATASET"

"EVALUATION_RUN_EVALUATING_RESULTS"

"EVALUATION_RUN_CANCELLING"

"EVALUATION_RUN_CANCELLED"

"EVALUATION_RUN_SUCCESSFUL"

"EVALUATION_RUN_PARTIALLY_SUCCESSFUL"

"EVALUATION_RUN_FAILED"

test_case_description: optional string

Test case description.

test_case_name: optional string

Test case name.

test_case_uuid: optional string

Test-case UUID.

test_case_version: optional number

Test-case-version.

formatint64