AIEvalRunResponse
Fields
32 fields
accuracy- number or null
agreement_rate- number or null
candidate- EvalCandidateResolved or null
completed_at- string (date-time) or null
correct_items- integer
dataset_id· required- string (uuid)
duration_ms- integer or null
error_code- string or null
error_items- integer or null
error_text- string or null
evaluated_at· required- string (date-time)
f1_score- number or null
fallback_used- boolean
heartbeat_at- string (date-time) or null
id· required- string (uuid)
items_capped- boolean or null
measured- boolean
metric_kind- string or null
metric_label- string
metrics- array of EvalMetric or null
model_name· required- string
model_version_id- string (uuid) or null
precision- number or null
project_id- string (uuid) or null
recall- number or null
requested_by- string (uuid) or null
scored_items- integer or null
started_at- string (date-time) or null
status- string or null
task_type· required- string
total_items- integer
unscored_items- integer or null
Raw schema (JSON)
{
"properties": {
"accuracy": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Accuracy"
},
"agreement_rate": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Agreement Rate"
},
"candidate": {
"anyOf": [
{
"$ref": "#/components/schemas/EvalCandidateResolved"
},
{
"type": "null"
}
]
},
"completed_at": {
"anyOf": [
{
"format": "date-time",
"type": "string"
},
{
"type": "null"
}
],
"title": "Completed At"
},
"correct_items": {
"default": 0,
"title": "Correct Items",
"type": "integer"
},
"dataset_id": {
"format": "uuid",
"title": "Dataset Id",
"type": "string"
},
"duration_ms": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Duration Ms"
},
"error_code": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Error Code"
},
"error_items": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": 0,
"title": "Error Items"
},
"error_text": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Error Text"
},
"evaluated_at": {
"format": "date-time",
"title": "Evaluated At",
"type": "string"
},
"f1_score": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "F1 Score"
},
"fallback_used": {
"default": false,
"title": "Fallback Used",
"type": "boolean"
},
"heartbeat_at": {
"anyOf": [
{
"format": "date-time",
"type": "string"
},
{
"type": "null"
}
],
"title": "Heartbeat At"
},
"id": {
"format": "uuid",
"title": "Id",
"type": "string"
},
"items_capped": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"default": false,
"title": "Items Capped"
},
"measured": {
"default": true,
"title": "Measured",
"type": "boolean"
},
"metric_kind": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": "label_agreement",
"title": "Metric Kind"
},
"metric_label": {
"default": "",
"title": "Metric Label",
"type": "string"
},
"metrics": {
"anyOf": [
{
"items": {
"$ref": "#/components/schemas/EvalMetric"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Metrics"
},
"model_name": {
"title": "Model Name",
"type": "string"
},
"model_version_id": {
"anyOf": [
{
"format": "uuid",
"type": "string"
},
{
"type": "null"
}
],
"title": "Model Version Id"
},
"precision": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Precision"
},
"project_id": {
"anyOf": [
{
"format": "uuid",
"type": "string"
},
{
"type": "null"
}
],
"title": "Project Id"
},
"recall": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Recall"
},
"requested_by": {
"anyOf": [
{
"format": "uuid",
"type": "string"
},
{
"type": "null"
}
],
"title": "Requested By"
},
"scored_items": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": 0,
"title": "Scored Items"
},
"started_at": {
"anyOf": [
{
"format": "date-time",
"type": "string"
},
{
"type": "null"
}
],
"title": "Started At"
},
"status": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": "completed",
"title": "Status"
},
"task_type": {
"title": "Task Type",
"type": "string"
},
"total_items": {
"default": 0,
"title": "Total Items",
"type": "integer"
},
"unscored_items": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"default": 0,
"title": "Unscored Items"
}
},
"required": [
"id",
"dataset_id",
"model_name",
"task_type",
"evaluated_at"
],
"title": "AIEvalRunResponse",
"type": "object"
}Used by endpoints
Section titled “Used by endpoints”4 endpoints send or return this schema, on its own or inside another schema.
GET/api/v1/ai-eval/runs/{eval_run_id}— Get Eval RunPOST/api/v1/ai-eval/runs/evaluate/{dataset_id}— Run EvaluationGET/api/v1/ai-eval/dashboard— Get Quality DashboardGET/api/v1/ai-eval/runs— List Eval Runs
Used by schemas
Section titled “Used by schemas”More details
Section titled “More details”- Specification: OpenAPI JSON