Update Collection

PUThttps://api.confident-ai.com/v1/metric-collections/{metricCollectionId}

Updates a metric collection. Only the fields you send are changed, and metricSettings replaces the whole list rather than merging into it.

PUT/v1/metric-collections/{metricCollectionId}

curl -X PUT "https://api.confident-ai.com/v1/metric-collections/{metricCollectionId}" \
  -H "CONFIDENT_API_KEY: <PROJECT-API-KEY>" \
  -H "Content-Type: application/json" \
  -d '{
  "name": "New Collection Name"
}'

200

{
  "success": true,
  "data": {
    "id": "COLLECTION-ID",
    "metricCollection": {
      "id": "COLLECTION-ID",
      "name": "Collection Name",
      "multiTurn": false,
      "sampleRate": 1,
      "inputTransformerId": null,
      "outputTransformerId": null,
      "metricsSettings": [
        {
          "metric": {
            "name": "Answer Relevancy"
          },
          "activated": true,
          "threshold": 0.8,
          "includeReason": true,
          "strictMode": false,
          "sampleRate": 1,
          "evaluationModelProvider": null,
          "evaluationModelName": null
        }
      ]
    }
  },
  "deprecated": false
}

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Path parameters

metricCollectionIdstringRequired
The id of the metric collection you want to update.

Request body

namestring
The name of the metric collection, which must be unique within your project.
metricSettingslist of objects
Replaces every metric setting on the collection. Fetch the collection first and resend each metric it should keep.
Show 8 propertiesHide 8 properties
- metricobjectRequired
  This is a metric object, which contains the metric name.
  Show 1 propertyHide 1 property
  - namestringRequired
    This is the name of the metric.
- activatedboolean
  This determines if the metric is activated. Only activated metrics are used for evaluations. Non-activated metrics are skipped.
- thresholdnumber
  This determines the threshold for the metric which determines if the metric passes or fails depending on if the metric score is equal or greater than the threshold.
- includeReasonboolean
  This determines if the reason for the metric score should be generated during evaluations.
- strictModeboolean
  This determines if the metric is in strict mode. Metrics in strict mode output a binary score of 0 or 1, indicating pass or fail, as opposed to a continuous score from 0 to 1.
- sampleRatenumber
  This determines the probability of the metric being ran for evaluation.
- evaluationModelProviderenum
  Evaluates this metric with your own model instead of the project default.
  Show 18 enum valuesHide 18 enum values
  - OPEN_AI
  - CUSTOM
  - CONFIDENT_AI
  - BEDROCK
  - ANTHROPIC
  - GEMINI
  - X_AI
  - DEEPSEEK
  - MOONSHOT_AI
  - VERTEX_AI
  - AZURE
  - MISTRAL
  - PERPLEXITY
  - OPEN_ROUTER
  - PORTKEY
  - LITE_LLM
  - TRUE_FOUNDRY
  - HUGGING_FACE
- evaluationModelNamestring
  The model to use, required whenever evaluationModelProvider is set to anything other than CONFIDENT_AI.
sampleRatenumber
The share of eligible entities the whole collection is run against, between 0 and 1. Applied on top of each metric's own sampleRate.
inputTransformerIdstring
A transformer that reshapes the payload before evaluation. Ids come from the transformers endpoint. Send null to unset it.
outputTransformerIdstring
A transformer that reshapes the result after evaluation. Send null to unset it.

Response

The updated metric collection.

successboolean
Indicates if the request was successful.
dataobject
The metric collection. Create and update also return its id alongside it.
Show 1 propertyHide 1 property
- metricCollectionobject
  A metric collection and the metrics configured inside it.
  Show 7 propertiesHide 7 properties
  - idstring
    This is the id of the metric collection.
  - namestring
    This is the name of the metric collection, which should be supplied to the evals API to run evaluations remotely.
  - multiTurnboolean
    This is true if the metric collection is a multi-turn collection, which only contains multi-turn metrics for multi-turn evaluations.
  - sampleRatenumber
    The share of eligible entities the collection is run against.
  - inputTransformerIdstring
    The transformer that reshapes the payload before evaluation, if one is set.
  - outputTransformerIdstring
    The transformer that reshapes the result after evaluation, if one is set.
  - metricsSettingslist of objects
    The settings for each metric in the collection, which can also be configured on Confident AI's metric collection page.
    Show 8 propertiesHide 8 properties
    metricobject
    This is a metric object, which contains the metric name.
    Show 1 propertyHide 1 property
    namestring
    This is the name of the metric.
    activatedboolean
    This is true if the metric is activated. Only activated metrics are used for evaluations. Non-activated metrics are skipped.
    thresholdnumber
    This is the threshold for the metric, which determines if the metric passes or fails depending on if the metric score is above or below the threshold.
    includeReasonboolean
    This is true if the reason for the metric score is generated during evaluations.
    strictModeboolean
    This is true if the metric is in strict mode. Metrics in strict mode output a binary score of 0 or 1, indicating pass or fail, as opposed to a continuous score from 0 to 1.
    sampleRatenumber
    This is the probability of the metric being ran for evaluation.
    evaluationModelProviderenum
    The provider of the model this metric is evaluated with, if it overrides the project default.
    Show 18 enum valuesHide 18 enum values
    OPEN_AI
    CUSTOM
    CONFIDENT_AI
    BEDROCK
    ANTHROPIC
    GEMINI
    X_AI
    DEEPSEEK
    MOONSHOT_AI
    VERTEX_AI
    AZURE
    MISTRAL
    PERPLEXITY
    OPEN_ROUTER
    PORTKEY
    LITE_LLM
    TRUE_FOUNDRY
    HUGGING_FACE
    evaluationModelNamestring
    The model this metric is evaluated with, if it overrides the project default.
deprecatedboolean
Indicates if this endpoint is deprecated.

Built byConfident AI