Method: projects.datasets.evaluations.exampleComparisons.search

Searches example comparisons from an evaluation. The return format is a list of example comparisons that show ground truth and prediction(s) for a single input. Search by providing an evaluation ID.

HTTP request

POST https://datalabeling.googleapis.com/v1beta1/{parent=projects/*/datasets/*/evaluations/*}/exampleComparisons:search

The URL uses gRPC Transcoding syntax.

Path parameters

Parameters
parent

string

Required. Name of the Evaluation resource to search for example comparisons from. Format:

"projects/{project_id}/datasets/{dataset_id}/evaluations/{evaluation_id}"

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

  • datalabeling.examplecomparisons.list

Request body

The request body contains data with the following structure:

JSON representation 
{
  "pageSize": number,
  "pageToken": string
}
Fields
pageSize

number

Optional. Requested page size. Server may return fewer results than requested. Default value is 100.

pageToken

string

Optional. A token identifying a page of results for the server to return. Typically obtained by the [nextPageToken][exampleComparisons.search.next_page_token] of the response to a previous search rquest.

If you don't specify this field, the API call requests the first page of the search.

Response body

If successful, the response body contains data with the following structure:

Results of searching example comparisons.

JSON representation 
{
  "exampleComparisons": [
    {
      object (ExampleComparison)
    }
  ],
  "nextPageToken": string
}
Fields
exampleComparisons[]

object (ExampleComparison)

A list of example comparisons matching the search criteria.

nextPageToken

string

A token to retrieve next page of results.

Authorization Scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

ExampleComparison

Example comparisons comparing ground truth output and predictions for a specific input.

JSON representation 
{
  "groundTruthExample": {
    object (Example)
  },
  "modelCreatedExamples": [
    {
      object (Example)
    }
  ]
}
Fields
groundTruthExample

object (Example)

The ground truth output for the input.

modelCreatedExamples[]

object (Example)

Predictions by the model for the input.