feat: add instance_config to batch_prediction_job in aiplatform v1bet…

…a1 batch_prediction_job.proto

PiperOrigin-RevId: 487284583

google/cloud/aiplatform/v1beta1/batch_prediction_job.proto

@@ -73,6 +73,91 @@ message BatchPredictionJob {
     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.v1beta1.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.v1beta1.BatchPredictionJob.InstanceConfig.included_fields] is populated.
+    //       [included_fields][google.cloud.aiplatform.v1beta1.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.v1beta1.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.v1beta1.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.v1beta1.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.v1beta1.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.v1beta1.BatchPredictionJob.InstanceConfig.excluded_fields] must be empty.
+    //
+    // The input must be JSONL with objects at each line, CSV, 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.v1beta1.BatchPredictionJob.InstanceConfig.key_field]
+    // is not specified.
+    //
+    // When excluded_fields is populated, [included_fields][google.cloud.aiplatform.v1beta1.BatchPredictionJob.InstanceConfig.included_fields] must be empty.
+    //
+    // The input must be JSONL with objects at each line, CSV, BigQuery
+    // or TfRecord.
+    repeated string excluded_fields = 4;
+  }
+
   // Configures the output of [BatchPredictionJob][google.cloud.aiplatform.v1beta1.BatchPredictionJob].
   // See [Model.supported_output_storage_formats][google.cloud.aiplatform.v1beta1.Model.supported_output_storage_formats] for supported output
   // formats, and how predictions are expressed via any of them.
@@ -183,6 +268,10 @@ message BatchPredictionJob {
   // [instance_schema_uri][google.cloud.aiplatform.v1beta1.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.v1beta1.BatchPredictionJob.model]
   // [PredictSchemata's][google.cloud.aiplatform.v1beta1.Model.predict_schemata]