Generate Classifier Labels

(v2)

POST

Generates labels for a classifier from your project's real traffic: it samples recent traces, spans or threads and runs them through the classifier's normal auto-classification pipeline. Repeated proposals are merged and written back as RECOMMENDED labels for a human to review.

The run is asynchronous, so poll the labels endpoint for results. Existing labels are retained, and the sampled entities receive ordinary classification results. Auto Classify must be enabled. Reading traffic and running the model consumes usage.

POST/v2/classifiers/{classifierId}/generate

curl -X POST "https://api.confident-ai.com/v2/classifiers/{classifierId}/generate" \
  -H "CONFIDENT_API_KEY: <PROJECT-API-KEY>"

200

{
  "success": true,
  "data": {
    "classifierId": "<CLASSIFIER-ID>",
    "started": true,
    "message": "Label generation started. Generated labels appear with status RECOMMENDED as the sampled data is classified."
  },
  "link": "https://app.confident-ai.com/project/<PROJECT-ID>/workflows",
  "deprecated": false
}

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Path parameters

classifierIdstringRequired
The id of the classifier.

Response

Generate Classifier Labels succeeded.

successboolean
Indicates if the request was successful.
dataobject
The outcome of dispatching a label generation run. The run itself is asynchronous and returns no handle, so poll the labels endpoint for its results.
Show 3 propertiesHide 3 properties
- classifierIdstring
  The classifier labels were generated for.
- startedboolean
  Whether a generation run was dispatched. False means there was too little traffic to sample, or sampling was briefly unavailable — it is an outcome, not an error.
- messagestring
  A human-readable explanation of the outcome.
linkstring
This is the URL of the resource on the Confident AI platform.
deprecatedboolean
Indicates if this endpoint is deprecated.

Built byConfident AI