Method: projects.locations.models.exportEvaluatedExamples

Exports examples on which the model was evaluated (i.e. which were in the TEST set of the dataset the model was created from), together with their ground truth annotations and the annotations created (predicted) by the model. The examples, ground truth and predictions are exported in the state they were at the moment the model was evaluated.

This export is available only for 30 days since the model evaluation is created.

Currently only available for Tables.

Returns an empty response in the response field when it completes.

HTTP request


Path parameters



Required. The resource name of the model whose evaluated examples are to be exported.

Authorization requires the following Google IAM permission on the specified resource name:

  • automl.modelEvaluations.get

Request body

The request body contains data with the following structure:

JSON representation
  "outputConfig": {
    object (ExportEvaluatedExamplesOutputConfig)

object (ExportEvaluatedExamplesOutputConfig)

Required. The desired output location and configuration.

Response body

If successful, the response body contains an instance of Operation.

Authorization Scopes

Requires the following OAuth scope:


For more information, see the Authentication Overview.


Output configuration for models.exportEvaluatedExamples Action. Note that this call is available only for 30 days since the moment the model was evaluated. The output depends on the domain, as follows (note that only examples from the TEST set are exported):

  • For Tables:

bigqueryDestination pointing to a BigQuery project must be set. In the given project a new dataset will be created with name

export_evaluated_examples_<model-display-name>_<timestamp-of-export-call> where will be made BigQuery-dataset-name compatible (e.g. most special characters will become underscores), and timestamp will be in YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset an evaluatedExamples table will be created. It will have all the same columns as the

primary_table of the dataset from which the model was created, as they were at the moment of model's evaluation (this includes the target column with its ground truth), followed by a column called "predicted_". That last column will contain the model's prediction result for each respective row, given as ARRAY of AnnotationPayloads, represented as STRUCT-s, containing TablesAnnotation.

JSON representation
  "bigqueryDestination": {
    object (BigQueryDestination)

object (BigQueryDestination)

The BigQuery location where the output is to be written to.