Evaluate Thread

POSThttps://api.confident-ai.com/v2/evaluate/threads/{threadId}

Queues an evaluation of a thread against the multi-turn metrics in metricCollection. The evaluation runs in the background, and its results are stored on the thread, so fetch the thread to read them once it has finished.

POST/v2/evaluate/threads/{threadId}

curl -X POST "https://api.confident-ai.com/v2/evaluate/threads/{threadId}" \
  -H "CONFIDENT_API_KEY: <PROJECT-API-KEY>" \
  -H "Content-Type: application/json" \
  -d '{
  "metricCollection": "Collection Name",
  "chatbotRole": "A helpful geography assistant.",
  "overwriteMetrics": false
}'

200

{
  "success": true,
  "data": {
    "id": "thread-42"
  },
  "deprecated": false
}

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Path parameters

threadIdstringRequired
The id of the thread, as you supplied it when creating its traces.

Request body

metricCollectionstringRequired
The name of the multi-turn metric collection you wish to use for evaluation.
chatbotRolestring
This is the role of the chatbot in the thread, which the multi-turn metrics that judge role adherence evaluate the thread against.
overwriteMetricsboolean
Set this to true to re-run every metric in the collection and replace the results already stored, and omit this field to keep those results and only run the metrics that have none yet.

Response

Evaluate Thread succeeded.

successboolean
Indicates if the request was successful.
dataobject
The thread whose evaluation was queued.
Show 1 propertyHide 1 property
- idstring
  This is the id of the thread the evaluation was queued for.
deprecatedboolean
Indicates if this endpoint is deprecated.

Built byConfident AI