// 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.aiplatform.v1;

import "google/api/field_behavior.proto";
import "google/api/resource.proto";
import "google/cloud/aiplatform/v1/completion_stats.proto";
import "google/cloud/aiplatform/v1/encryption_spec.proto";
import "google/cloud/aiplatform/v1/explanation.proto";
import "google/cloud/aiplatform/v1/io.proto";
import "google/cloud/aiplatform/v1/job_state.proto";
import "google/cloud/aiplatform/v1/machine_resources.proto";
import "google/cloud/aiplatform/v1/manual_batch_tuning_parameters.proto";
import "google/cloud/aiplatform/v1/unmanaged_container_model.proto";
import "google/protobuf/struct.proto";
import "google/protobuf/timestamp.proto";
import "google/rpc/status.proto";

option csharp_namespace = "Google.Cloud.AIPlatform.V1";
option go_package = "cloud.google.com/go/aiplatform/apiv1/aiplatformpb;aiplatformpb";
option java_multiple_files = true;
option java_outer_classname = "BatchPredictionJobProto";
option java_package = "com.google.cloud.aiplatform.v1";
option php_namespace = "Google\\Cloud\\AIPlatform\\V1";
option ruby_package = "Google::Cloud::AIPlatform::V1";

// A job that uses a
// [Model][google.cloud.aiplatform.v1.BatchPredictionJob.model] to produce
// predictions on multiple [input
// instances][google.cloud.aiplatform.v1.BatchPredictionJob.input_config]. If
// predictions for significant portion of the instances fail, the job may finish
// without attempting predictions for all remaining instances.
message BatchPredictionJob {
  option (google.api.resource) = {
    type: "aiplatform.googleapis.com/BatchPredictionJob"
    pattern: "projects/{project}/locations/{location}/batchPredictionJobs/{batch_prediction_job}"
  };

  // Configures the input to
  // [BatchPredictionJob][google.cloud.aiplatform.v1.BatchPredictionJob]. See
  // [Model.supported_input_storage_formats][google.cloud.aiplatform.v1.Model.supported_input_storage_formats]
  // for Model's supported input formats, and how instances should be expressed
  // via any of them.
  message InputConfig {
    // Required. The source of the input.
    oneof source {
      // The Cloud Storage location for the input instances.
      GcsSource gcs_source = 2;

      // The BigQuery location of the input table.
      // The schema of the table should be in the format described by the given
      // context OpenAPI Schema, if one is provided. The table may contain
      // additional columns that are not described by the schema, and they will
      // be ignored.
      BigQuerySource bigquery_source = 3;
    }

    // Required. The format in which instances are given, must be one of the
    // [Model's][google.cloud.aiplatform.v1.BatchPredictionJob.model]
    // [supported_input_storage_formats][google.cloud.aiplatform.v1.Model.supported_input_storage_formats].
    string instances_format = 1 [(google.api.field_behavior) = REQUIRED];
  }

  // Configuration defining how to transform batch prediction input instances to
  // the instances that the Model accepts.
  message InstanceConfig {
    // The format of the instance that the Model accepts. Vertex AI will
    // convert compatible
    // [batch prediction input instance
    // formats][google.cloud.aiplatform.v1.BatchPredictionJob.InputConfig.instances_format]
    // to the specified format.
    //
    // Supported values are:
    //
    // * `object`: Each input is converted to JSON object format.
    //     * For `bigquery`, each row is converted to an object.
    //     * For `jsonl`, each line of the JSONL input must be an object.
    //     * Does not apply to `csv`, `file-list`, `tf-record`, or
    //       `tf-record-gzip`.
    //
    // * `array`: Each input is converted to JSON array format.
    //     * For `bigquery`, each row is converted to an array. The order
    //       of columns is determined by the BigQuery column order, unless
    //       [included_fields][google.cloud.aiplatform.v1.BatchPredictionJob.InstanceConfig.included_fields]
    //       is populated.
    //       [included_fields][google.cloud.aiplatform.v1.BatchPredictionJob.InstanceConfig.included_fields]
    //       must be populated for specifying field orders.
    //     * For `jsonl`, if each line of the JSONL input is an object,
    //       [included_fields][google.cloud.aiplatform.v1.BatchPredictionJob.InstanceConfig.included_fields]
    //       must be populated for specifying field orders.
    //     * Does not apply to `csv`, `file-list`, `tf-record`, or
    //       `tf-record-gzip`.
    //
    // If not specified, Vertex AI converts the batch prediction input as
    // follows:
    //
    //  * For `bigquery` and `csv`, the behavior is the same as `array`. The
    //    order of columns is the same as defined in the file or table, unless
    //    [included_fields][google.cloud.aiplatform.v1.BatchPredictionJob.InstanceConfig.included_fields]
    //    is populated.
    //  * For `jsonl`, the prediction instance format is determined by
    //    each line of the input.
    //  * For `tf-record`/`tf-record-gzip`, each record will be converted to
    //    an object in the format of `{"b64": <value>}`, where `<value>` is
    //    the Base64-encoded string of the content of the record.
    //  * For `file-list`, each file in the list will be converted to an
    //    object in the format of `{"b64": <value>}`, where `<value>` is
    //    the Base64-encoded string of the content of the file.
    string instance_type = 1;

    // The name of the field that is considered as a key.
    //
    // The values identified by the key field is not included in the transformed
    // instances that is sent to the Model. This is similar to
    // specifying this name of the field in
    // [excluded_fields][google.cloud.aiplatform.v1.BatchPredictionJob.InstanceConfig.excluded_fields].
    // In addition, the batch prediction output will not include the instances.
    // Instead the output will only include the value of the key field, in a
    // field named `key` in the output:
    //
    //  * For `jsonl` output format, the output will have a `key` field
    //    instead of the `instance` field.
    //  * For `csv`/`bigquery` output format, the output will have have a `key`
    //    column instead of the instance feature columns.
    //
    // The input must be JSONL with objects at each line, CSV, BigQuery
    // or TfRecord.
    string key_field = 2;

    // Fields that will be included in the prediction instance that is
    // sent to the Model.
    //
    // If
    // [instance_type][google.cloud.aiplatform.v1.BatchPredictionJob.InstanceConfig.instance_type]
    // is `array`, the order of field names in included_fields also determines
    // the order of the values in the array.
    //
    // When included_fields is populated,
    // [excluded_fields][google.cloud.aiplatform.v1.BatchPredictionJob.InstanceConfig.excluded_fields]
    // must be empty.
    //
    // The input must be JSONL with objects at each line, BigQuery
    // or TfRecord.
    repeated string included_fields = 3;

    // Fields that will be excluded in the prediction instance that is
    // sent to the Model.
    //
    // Excluded will be attached to the batch prediction output if
    // [key_field][google.cloud.aiplatform.v1.BatchPredictionJob.InstanceConfig.key_field]
    // is not specified.
    //
    // When excluded_fields is populated,
    // [included_fields][google.cloud.aiplatform.v1.BatchPredictionJob.InstanceConfig.included_fields]
    // must be empty.
    //
    // The input must be JSONL with objects at each line, BigQuery
    // or TfRecord.
    repeated string excluded_fields = 4;
  }

  // Configures the output of
  // [BatchPredictionJob][google.cloud.aiplatform.v1.BatchPredictionJob]. See
  // [Model.supported_output_storage_formats][google.cloud.aiplatform.v1.Model.supported_output_storage_formats]
  // for supported output formats, and how predictions are expressed via any of
  // them.
  message OutputConfig {
    // Required. The destination of the output.
    oneof destination {
      // The Cloud Storage location of the directory where the output is
      // to be written to. In the given directory a new directory is created.
      // Its name is `prediction-<model-display-name>-<job-create-time>`,
      // where timestamp is in YYYY-MM-DDThh:mm:ss.sssZ ISO-8601 format.
      // Inside of it files `predictions_0001.<extension>`,
      // `predictions_0002.<extension>`, ..., `predictions_N.<extension>`
      // are created where `<extension>` depends on chosen
      // [predictions_format][google.cloud.aiplatform.v1.BatchPredictionJob.OutputConfig.predictions_format],
      // and N may equal 0001 and depends on the total number of successfully
      // predicted instances. If the Model has both
      // [instance][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]
      // and
      // [prediction][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]
      // schemata defined then each such file contains predictions as per the
      // [predictions_format][google.cloud.aiplatform.v1.BatchPredictionJob.OutputConfig.predictions_format].
      // If prediction for any instance failed (partially or completely), then
      // an additional `errors_0001.<extension>`, `errors_0002.<extension>`,...,
      // `errors_N.<extension>` files are created (N depends on total number
      // of failed predictions). These files contain the failed instances,
      // as per their schema, followed by an additional `error` field which as
      // value has [google.rpc.Status][google.rpc.Status]
      // containing only `code` and `message` fields.
      GcsDestination gcs_destination = 2;

      // The BigQuery project or dataset location where the output is to be
      // written to. If project is provided, a new dataset is created with name
      // `prediction_<model-display-name>_<job-create-time>`
      // where <model-display-name> is made
      // BigQuery-dataset-name compatible (for example, most special characters
      // become underscores), and timestamp is in
      // YYYY_MM_DDThh_mm_ss_sssZ "based on ISO-8601" format. In the dataset
      // two tables will be created, `predictions`, and `errors`.
      // If the Model has both
      // [instance][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]
      // and
      // [prediction][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri]
      // schemata defined then the tables have columns as follows: The
      // `predictions` table contains instances for which the prediction
      // succeeded, it has columns as per a concatenation of the Model's
      // instance and prediction schemata. The `errors` table contains rows for
      // which the prediction has failed, it has instance columns, as per the
      // instance schema, followed by a single "errors" column, which as values
      // has [google.rpc.Status][google.rpc.Status]
      // represented as a STRUCT, and containing only `code` and `message`.
      BigQueryDestination bigquery_destination = 3;
    }

    // Required. The format in which Vertex AI gives the predictions, must be
    // one of the [Model's][google.cloud.aiplatform.v1.BatchPredictionJob.model]
    // [supported_output_storage_formats][google.cloud.aiplatform.v1.Model.supported_output_storage_formats].
    string predictions_format = 1 [(google.api.field_behavior) = REQUIRED];
  }

  // Further describes this job's output.
  // Supplements
  // [output_config][google.cloud.aiplatform.v1.BatchPredictionJob.output_config].
  message OutputInfo {
    // The output location into which prediction output is written.
    oneof output_location {
      // Output only. The full path of the Cloud Storage directory created, into
      // which the prediction output is written.
      string gcs_output_directory = 1
          [(google.api.field_behavior) = OUTPUT_ONLY];

      // Output only. The path of the BigQuery dataset created, in
      // `bq://projectId.bqDatasetId`
      // format, into which the prediction output is written.
      string bigquery_output_dataset = 2
          [(google.api.field_behavior) = OUTPUT_ONLY];
    }

    // Output only. The name of the BigQuery table created, in
    // `predictions_<timestamp>`
    // format, into which the prediction output is written.
    // Can be used by UI to generate the BigQuery output path, for example.
    string bigquery_output_table = 4
        [(google.api.field_behavior) = OUTPUT_ONLY];
  }

  // Output only. Resource name of the BatchPredictionJob.
  string name = 1 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Required. The user-defined name of this BatchPredictionJob.
  string display_name = 2 [(google.api.field_behavior) = REQUIRED];

  // The name of the Model resource that produces the predictions via this job,
  // must share the same ancestor Location.
  // Starting this job has no impact on any existing deployments of the Model
  // and their resources.
  // Exactly one of model and unmanaged_container_model must be set.
  //
  // The model resource name may contain version id or version alias to specify
  // the version.
  //  Example: `projects/{project}/locations/{location}/models/{model}@2`
  //              or
  //            `projects/{project}/locations/{location}/models/{model}@golden`
  // if no version is specified, the default version will be deployed.
  //
  // The model resource could also be a publisher model.
  //  Example: `publishers/{publisher}/models/{model}`
  //              or
  //           `projects/{project}/locations/{location}/publishers/{publisher}/models/{model}`
  string model = 3 [(google.api.resource_reference) = {
    type: "aiplatform.googleapis.com/Model"
  }];

  // Output only. The version ID of the Model that produces the predictions via
  // this job.
  string model_version_id = 30 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Contains model information necessary to perform batch prediction without
  // requiring uploading to model registry.
  // Exactly one of model and unmanaged_container_model must be set.
  UnmanagedContainerModel unmanaged_container_model = 28;

  // Required. Input configuration of the instances on which predictions are
  // performed. The schema of any single instance may be specified via the
  // [Model's][google.cloud.aiplatform.v1.BatchPredictionJob.model]
  // [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata]
  // [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri].
  InputConfig input_config = 4 [(google.api.field_behavior) = REQUIRED];

  // Configuration for how to convert batch prediction input instances to the
  // prediction instances that are sent to the Model.
  InstanceConfig instance_config = 27;

  // The parameters that govern the predictions. The schema of the parameters
  // may be specified via the
  // [Model's][google.cloud.aiplatform.v1.BatchPredictionJob.model]
  // [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata]
  // [parameters_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.parameters_schema_uri].
  google.protobuf.Value model_parameters = 5;

  // Required. The Configuration specifying where output predictions should
  // be written.
  // The schema of any single prediction may be specified as a concatenation
  // of [Model's][google.cloud.aiplatform.v1.BatchPredictionJob.model]
  // [PredictSchemata's][google.cloud.aiplatform.v1.Model.predict_schemata]
  // [instance_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.instance_schema_uri]
  // and
  // [prediction_schema_uri][google.cloud.aiplatform.v1.PredictSchemata.prediction_schema_uri].
  OutputConfig output_config = 6 [(google.api.field_behavior) = REQUIRED];

  // The config of resources used by the Model during the batch prediction. If
  // the Model
  // [supports][google.cloud.aiplatform.v1.Model.supported_deployment_resources_types]
  // DEDICATED_RESOURCES this config may be provided (and the job will use these
  // resources), if the Model doesn't support AUTOMATIC_RESOURCES, this config
  // must be provided.
  BatchDedicatedResources dedicated_resources = 7;

  // The service account that the DeployedModel's container runs as. If not
  // specified, a system generated one will be used, which
  // has minimal permissions and the custom container, if used, may not have
  // enough permission to access other Google Cloud resources.
  //
  // Users deploying the Model must have the `iam.serviceAccounts.actAs`
  // permission on this service account.
  string service_account = 29;

  // Immutable. Parameters configuring the batch behavior. Currently only
  // applicable when
  // [dedicated_resources][google.cloud.aiplatform.v1.BatchPredictionJob.dedicated_resources]
  // are used (in other cases Vertex AI does the tuning itself).
  ManualBatchTuningParameters manual_batch_tuning_parameters = 8
      [(google.api.field_behavior) = IMMUTABLE];

  // Generate explanation with the batch prediction results.
  //
  // When set to `true`, the batch prediction output changes based on the
  // `predictions_format` field of the
  // [BatchPredictionJob.output_config][google.cloud.aiplatform.v1.BatchPredictionJob.output_config]
  // object:
  //
  //  * `bigquery`: output includes a column named `explanation`. The value
  //    is a struct that conforms to the
  //    [Explanation][google.cloud.aiplatform.v1.Explanation] object.
  //  * `jsonl`: The JSON objects on each line include an additional entry
  //    keyed `explanation`. The value of the entry is a JSON object that
  //    conforms to the [Explanation][google.cloud.aiplatform.v1.Explanation]
  //    object.
  //  * `csv`: Generating explanations for CSV format is not supported.
  //
  // If this field is set to true, either the
  // [Model.explanation_spec][google.cloud.aiplatform.v1.Model.explanation_spec]
  // or
  // [explanation_spec][google.cloud.aiplatform.v1.BatchPredictionJob.explanation_spec]
  // must be populated.
  bool generate_explanation = 23;

  // Explanation configuration for this BatchPredictionJob. Can be
  // specified only if
  // [generate_explanation][google.cloud.aiplatform.v1.BatchPredictionJob.generate_explanation]
  // is set to `true`.
  //
  // This value overrides the value of
  // [Model.explanation_spec][google.cloud.aiplatform.v1.Model.explanation_spec].
  // All fields of
  // [explanation_spec][google.cloud.aiplatform.v1.BatchPredictionJob.explanation_spec]
  // are optional in the request. If a field of the
  // [explanation_spec][google.cloud.aiplatform.v1.BatchPredictionJob.explanation_spec]
  // object is not populated, the corresponding field of the
  // [Model.explanation_spec][google.cloud.aiplatform.v1.Model.explanation_spec]
  // object is inherited.
  ExplanationSpec explanation_spec = 25;

  // Output only. Information further describing the output of this job.
  OutputInfo output_info = 9 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. The detailed state of the job.
  JobState state = 10 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Only populated when the job's state is JOB_STATE_FAILED or
  // JOB_STATE_CANCELLED.
  google.rpc.Status error = 11 [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Partial failures encountered.
  // For example, single files that can't be read.
  // This field never exceeds 20 entries.
  // Status details fields contain standard Google Cloud error details.
  repeated google.rpc.Status partial_failures = 12
      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Information about resources that had been consumed by this
  // job. Provided in real time at best effort basis, as well as a final value
  // once the job completes.
  //
  // Note: This field currently may be not populated for batch predictions that
  // use AutoML Models.
  ResourcesConsumed resources_consumed = 13
      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Statistics on completed and failed prediction instances.
  CompletionStats completion_stats = 14
      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Time when the BatchPredictionJob was created.
  google.protobuf.Timestamp create_time = 15
      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Time when the BatchPredictionJob for the first time entered
  // the `JOB_STATE_RUNNING` state.
  google.protobuf.Timestamp start_time = 16
      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Time when the BatchPredictionJob entered any of the following
  // states: `JOB_STATE_SUCCEEDED`, `JOB_STATE_FAILED`, `JOB_STATE_CANCELLED`.
  google.protobuf.Timestamp end_time = 17
      [(google.api.field_behavior) = OUTPUT_ONLY];

  // Output only. Time when the BatchPredictionJob was most recently updated.
  google.protobuf.Timestamp update_time = 18
      [(google.api.field_behavior) = OUTPUT_ONLY];

  // The labels with user-defined metadata to organize BatchPredictionJobs.
  //
  // Label keys and values can be no longer than 64 characters
  // (Unicode codepoints), can only contain lowercase letters, numeric
  // characters, underscores and dashes. International characters are allowed.
  //
  // See https://goo.gl/xmQnxf for more information and examples of labels.
  map<string, string> labels = 19;

  // Customer-managed encryption key options for a BatchPredictionJob. If this
  // is set, then all resources created by the BatchPredictionJob will be
  // encrypted with the provided encryption key.
  EncryptionSpec encryption_spec = 24;

  // For custom-trained Models and AutoML Tabular Models, the container of the
  // DeployedModel instances will send `stderr` and `stdout` streams to
  // Cloud Logging by default. Please note that the logs incur cost,
  // which are subject to [Cloud Logging
  // pricing](https://cloud.google.com/logging/pricing).
  //
  // User can disable container logging by setting this flag to true.
  bool disable_container_logging = 34;
}