Method: projects.locations.featurestores.entityTypes.writeFeatureValues

Writes feature values of one or more entities of an EntityType.

The feature values are merged into existing entities if any. The feature values to be written must have timestamp within the online storage retention.

HTTP request

POST https://{service-endpoint}/v1/{entityType}:writeFeatureValues

Where {service-endpoint} is one of the supported service endpoints.

Path parameters



Required. The resource name of the EntityType for the entities being written. value format: projects/{project}/locations/{location}/featurestores/ {featurestore}/entityTypes/{entityType}. For example, for a machine learning model predicting user clicks on a website, an EntityType id could be user.

Request body

The request body contains data with the following structure:

JSON representation
  "payloads": [
      object (WriteFeatureValuesPayload)

object (WriteFeatureValuesPayload)

Required. The entities to be written. Up to 100,000 feature values can be written across all payloads.

Response body

If successful, the response body is empty.

Authorization scopes

Requires the following OAuth scope:


For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the entityType resource:

  • aiplatform.entityTypes.writeFeatureValues

For more information, see the IAM documentation.


Contains feature values to be written for a specific entity.

JSON representation
  "entityId": string,
  "featureValues": {
    string: {
      object (FeatureValue)


Required. The id of the entity.


map (key: string, value: object (FeatureValue))

Required. feature values to be written, mapping from feature id to value. Up to 100,000 featureValues entries may be written across all payloads. The feature generation time, aligned by days, must be no older than five years (1825 days) and no later than one year (366 days) in the future.