// Copyright 2024 Google LLC
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
//     http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//

syntax = "proto3";

package google.cloud.datalabeling.v1beta1;

import "google/api/resource.proto";
import "google/cloud/datalabeling/v1beta1/dataset.proto";
import "google/cloud/datalabeling/v1beta1/evaluation.proto";
import "google/cloud/datalabeling/v1beta1/human_annotation_config.proto";
import "google/protobuf/timestamp.proto";
import "google/rpc/status.proto";

option csharp_namespace = "Google.Cloud.DataLabeling.V1Beta1";
option go_package = "cloud.google.com/go/datalabeling/apiv1beta1/datalabelingpb;datalabelingpb";
option java_multiple_files = true;
option java_package = "com.google.cloud.datalabeling.v1beta1";
option php_namespace = "Google\\Cloud\\DataLabeling\\V1beta1";
option ruby_package = "Google::Cloud::DataLabeling::V1beta1";

// Defines an evaluation job that runs periodically to generate
// [Evaluations][google.cloud.datalabeling.v1beta1.Evaluation]. [Creating an evaluation
// job](/ml-engine/docs/continuous-evaluation/create-job) is the starting point
// for using continuous evaluation.
message EvaluationJob {
  option (google.api.resource) = {
    type: "datalabeling.googleapis.com/EvaluationJob"
    pattern: "projects/{project}/evaluationJobs/{evaluation_job}"
  };

  // State of the job.
  enum State {
    STATE_UNSPECIFIED = 0;

    // The job is scheduled to run at the [configured interval][google.cloud.datalabeling.v1beta1.EvaluationJob.schedule]. You
    // can [pause][google.cloud.datalabeling.v1beta1.DataLabelingService.PauseEvaluationJob] or
    // [delete][google.cloud.datalabeling.v1beta1.DataLabelingService.DeleteEvaluationJob] the job.
    //
    // When the job is in this state, it samples prediction input and output
    // from your model version into your BigQuery table as predictions occur.
    SCHEDULED = 1;

    // The job is currently running. When the job runs, Data Labeling Service
    // does several things:
    //
    // 1. If you have configured your job to use Data Labeling Service for
    //    ground truth labeling, the service creates a
    //    [Dataset][google.cloud.datalabeling.v1beta1.Dataset] and a labeling task for all data sampled
    //    since the last time the job ran. Human labelers provide ground truth
    //    labels for your data. Human labeling may take hours, or even days,
    //    depending on how much data has been sampled. The job remains in the
    //    `RUNNING` state during this time, and it can even be running multiple
    //    times in parallel if it gets triggered again (for example 24 hours
    //    later) before the earlier run has completed. When human labelers have
    //    finished labeling the data, the next step occurs.
    //    <br><br>
    //    If you have configured your job to provide your own ground truth
    //    labels, Data Labeling Service still creates a [Dataset][google.cloud.datalabeling.v1beta1.Dataset] for newly
    //    sampled data, but it expects that you have already added ground truth
    //    labels to the BigQuery table by this time. The next step occurs
    //    immediately.
    //
    // 2. Data Labeling Service creates an [Evaluation][google.cloud.datalabeling.v1beta1.Evaluation] by comparing your
    //    model version's predictions with the ground truth labels.
    //
    // If the job remains in this state for a long time, it continues to sample
    // prediction data into your BigQuery table and will run again at the next
    // interval, even if it causes the job to run multiple times in parallel.
    RUNNING = 2;

    // The job is not sampling prediction input and output into your BigQuery
    // table and it will not run according to its schedule. You can
    // [resume][google.cloud.datalabeling.v1beta1.DataLabelingService.ResumeEvaluationJob] the job.
    PAUSED = 3;

    // The job has this state right before it is deleted.
    STOPPED = 4;
  }

  // Output only. After you create a job, Data Labeling Service assigns a name
  // to the job with the following format:
  //
  // "projects/<var>{project_id}</var>/evaluationJobs/<var>{evaluation_job_id}</var>"
  string name = 1;

  // Required. Description of the job. The description can be up to 25,000
  // characters long.
  string description = 2;

  // Output only. Describes the current state of the job.
  State state = 3;

  // Required. Describes the interval at which the job runs. This interval must
  // be at least 1 day, and it is rounded to the nearest day. For example, if
  // you specify a 50-hour interval, the job runs every 2 days.
  //
  // You can provide the schedule in
  // [crontab format](/scheduler/docs/configuring/cron-job-schedules) or in an
  // [English-like
  // format](/appengine/docs/standard/python/config/cronref#schedule_format).
  //
  // Regardless of what you specify, the job will run at 10:00 AM UTC. Only the
  // interval from this schedule is used, not the specific time of day.
  string schedule = 4;

  // Required. The [AI Platform Prediction model
  // version](/ml-engine/docs/prediction-overview) to be evaluated. Prediction
  // input and output is sampled from this model version. When creating an
  // evaluation job, specify the model version in the following format:
  //
  // "projects/<var>{project_id}</var>/models/<var>{model_name}</var>/versions/<var>{version_name}</var>"
  //
  // There can only be one evaluation job per model version.
  string model_version = 5;

  // Required. Configuration details for the evaluation job.
  EvaluationJobConfig evaluation_job_config = 6;

  // Required. Name of the [AnnotationSpecSet][google.cloud.datalabeling.v1beta1.AnnotationSpecSet] describing all the
  // labels that your machine learning model outputs. You must create this
  // resource before you create an evaluation job and provide its name in the
  // following format:
  //
  // "projects/<var>{project_id}</var>/annotationSpecSets/<var>{annotation_spec_set_id}</var>"
  string annotation_spec_set = 7;

  // Required. Whether you want Data Labeling Service to provide ground truth
  // labels for prediction input. If you want the service to assign human
  // labelers to annotate your data, set this to `true`. If you want to provide
  // your own ground truth labels in the evaluation job's BigQuery table, set
  // this to `false`.
  bool label_missing_ground_truth = 8;

  // Output only. Every time the evaluation job runs and an error occurs, the
  // failed attempt is appended to this array.
  repeated Attempt attempts = 9;

  // Output only. Timestamp of when this evaluation job was created.
  google.protobuf.Timestamp create_time = 10;
}

// Configures specific details of how a continuous evaluation job works. Provide
// this configuration when you create an EvaluationJob.
message EvaluationJobConfig {
  // Required. Details for how you want human reviewers to provide ground truth
  // labels.
  oneof human_annotation_request_config {
    // Specify this field if your model version performs image classification or
    // general classification.
    //
    // `annotationSpecSet` in this configuration must match
    // [EvaluationJob.annotationSpecSet][google.cloud.datalabeling.v1beta1.EvaluationJob.annotation_spec_set].
    // `allowMultiLabel` in this configuration must match
    // `classificationMetadata.isMultiLabel` in [input_config][google.cloud.datalabeling.v1beta1.EvaluationJobConfig.input_config].
    ImageClassificationConfig image_classification_config = 4;

    // Specify this field if your model version performs image object detection
    // (bounding box detection).
    //
    // `annotationSpecSet` in this configuration must match
    // [EvaluationJob.annotationSpecSet][google.cloud.datalabeling.v1beta1.EvaluationJob.annotation_spec_set].
    BoundingPolyConfig bounding_poly_config = 5;

    // Specify this field if your model version performs text classification.
    //
    // `annotationSpecSet` in this configuration must match
    // [EvaluationJob.annotationSpecSet][google.cloud.datalabeling.v1beta1.EvaluationJob.annotation_spec_set].
    // `allowMultiLabel` in this configuration must match
    // `classificationMetadata.isMultiLabel` in [input_config][google.cloud.datalabeling.v1beta1.EvaluationJobConfig.input_config].
    TextClassificationConfig text_classification_config = 8;
  }

  // Rquired. Details for the sampled prediction input. Within this
  // configuration, there are requirements for several fields:
  //
  // * `dataType` must be one of `IMAGE`, `TEXT`, or `GENERAL_DATA`.
  // * `annotationType` must be one of `IMAGE_CLASSIFICATION_ANNOTATION`,
  //   `TEXT_CLASSIFICATION_ANNOTATION`, `GENERAL_CLASSIFICATION_ANNOTATION`,
  //   or `IMAGE_BOUNDING_BOX_ANNOTATION` (image object detection).
  // * If your machine learning model performs classification, you must specify
  //   `classificationMetadata.isMultiLabel`.
  // * You must specify `bigquerySource` (not `gcsSource`).
  InputConfig input_config = 1;

  // Required. Details for calculating evaluation metrics and creating
  // [Evaulations][google.cloud.datalabeling.v1beta1.Evaluation]. If your model version performs image object
  // detection, you must specify the `boundingBoxEvaluationOptions` field within
  // this configuration. Otherwise, provide an empty object for this
  // configuration.
  EvaluationConfig evaluation_config = 2;

  // Optional. Details for human annotation of your data. If you set
  // [labelMissingGroundTruth][google.cloud.datalabeling.v1beta1.EvaluationJob.label_missing_ground_truth] to
  // `true` for this evaluation job, then you must specify this field. If you
  // plan to provide your own ground truth labels, then omit this field.
  //
  // Note that you must create an [Instruction][google.cloud.datalabeling.v1beta1.Instruction] resource before you can
  // specify this field. Provide the name of the instruction resource in the
  // `instruction` field within this configuration.
  HumanAnnotationConfig human_annotation_config = 3;

  // Required. Prediction keys that tell Data Labeling Service where to find the
  // data for evaluation in your BigQuery table. When the service samples
  // prediction input and output from your model version and saves it to
  // BigQuery, the data gets stored as JSON strings in the BigQuery table. These
  // keys tell Data Labeling Service how to parse the JSON.
  //
  // You can provide the following entries in this field:
  //
  // * `data_json_key`: the data key for prediction input. You must provide
  //   either this key or `reference_json_key`.
  // * `reference_json_key`: the data reference key for prediction input. You
  //   must provide either this key or `data_json_key`.
  // * `label_json_key`: the label key for prediction output. Required.
  // * `label_score_json_key`: the score key for prediction output. Required.
  // * `bounding_box_json_key`: the bounding box key for prediction output.
  //   Required if your model version perform image object detection.
  //
  // Learn [how to configure prediction
  // keys](/ml-engine/docs/continuous-evaluation/create-job#prediction-keys).
  map<string, string> bigquery_import_keys = 9;

  // Required. The maximum number of predictions to sample and save to BigQuery
  // during each [evaluation interval][google.cloud.datalabeling.v1beta1.EvaluationJob.schedule]. This limit
  // overrides `example_sample_percentage`: even if the service has not sampled
  // enough predictions to fulfill `example_sample_perecentage` during an
  // interval, it stops sampling predictions when it meets this limit.
  int32 example_count = 10;

  // Required. Fraction of predictions to sample and save to BigQuery during
  // each [evaluation interval][google.cloud.datalabeling.v1beta1.EvaluationJob.schedule]. For example, 0.1 means
  // 10% of predictions served by your model version get saved to BigQuery.
  double example_sample_percentage = 11;

  // Optional. Configuration details for evaluation job alerts. Specify this
  // field if you want to receive email alerts if the evaluation job finds that
  // your predictions have low mean average precision during a run.
  EvaluationJobAlertConfig evaluation_job_alert_config = 13;
}

// Provides details for how an evaluation job sends email alerts based on the
// results of a run.
message EvaluationJobAlertConfig {
  // Required. An email address to send alerts to.
  string email = 1;

  // Required. A number between 0 and 1 that describes a minimum mean average
  // precision threshold. When the evaluation job runs, if it calculates that
  // your model version's predictions from the recent interval have
  // [meanAveragePrecision][google.cloud.datalabeling.v1beta1.PrCurve.mean_average_precision] below this
  // threshold, then it sends an alert to your specified email.
  double min_acceptable_mean_average_precision = 2;
}

// Records a failed evaluation job run.
message Attempt {
  google.protobuf.Timestamp attempt_time = 1;

  // Details of errors that occurred.
  repeated google.rpc.Status partial_failures = 2;
}