// Copyright 2019 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/annotations.proto";
import "google/api/resource.proto";
import "google/cloud/datalabeling/v1beta1/annotation.proto";
import "google/cloud/datalabeling/v1beta1/annotation_spec_set.proto";
import "google/cloud/datalabeling/v1beta1/data_payloads.proto";
import "google/cloud/datalabeling/v1beta1/human_annotation_config.proto";
import "google/protobuf/timestamp.proto";
option go_package = "google.golang.org/genproto/googleapis/cloud/datalabeling/v1beta1;datalabeling";
option java_multiple_files = true;
option java_package = "com.google.cloud.datalabeling.v1beta1";
enum DataType {
DATA_TYPE_UNSPECIFIED = 0;
// Allowed for continuous evaluation.
IMAGE = 1;
VIDEO = 2;
// Allowed for continuous evaluation.
TEXT = 4;
// Allowed for continuous evaluation.
GENERAL_DATA = 6;
}
// Dataset is the resource to hold your data. You can request multiple labeling
// tasks for a dataset while each one will generate an AnnotatedDataset.
message Dataset {
option (google.api.resource) = {
type: "datalabeling.googleapis.com/Dataset"
pattern: "projects/{project}/datasets/{dataset}"
};
// Output only. Dataset resource name, format is:
// projects/{project_id}/datasets/{dataset_id}
string name = 1;
// Required. The display name of the dataset. Maximum of 64 characters.
string display_name = 2;
// Optional. User-provided description of the annotation specification set.
// The description can be up to 10000 characters long.
string description = 3;
// Output only. Time the dataset is created.
google.protobuf.Timestamp create_time = 4;
// Output only. This is populated with the original input configs
// where ImportData is called. It is available only after the clients
// import data to this dataset.
repeated InputConfig input_configs = 5;
// Output only. The names of any related resources that are blocking changes
// to the dataset.
repeated string blocking_resources = 6;
// Output only. The number of data items in the dataset.
int64 data_item_count = 7;
}
// The configuration of input data, including data type, location, etc.
message InputConfig {
// Optional. The metadata associated with each data type.
oneof data_type_metadata {
// Required for text import, as language code must be specified.
TextMetadata text_metadata = 6;
}
// Required. Where the data is from.
oneof source {
// Source located in Cloud Storage.
GcsSource gcs_source = 2;
// Source located in BigQuery. You must specify this field if you are using
// this InputConfig in an [EvaluationJob][google.cloud.datalabeling.v1beta1.EvaluationJob].
BigQuerySource bigquery_source = 5;
}
// Required. Data type must be specifed when user tries to import data.
DataType data_type = 1;
// Optional. The type of annotation to be performed on this data. You must
// specify this field if you are using this InputConfig in an
// [EvaluationJob][google.cloud.datalabeling.v1beta1.EvaluationJob].
AnnotationType annotation_type = 3;
// Optional. Metadata about annotations for the input. You must specify this
// field if you are using this InputConfig in an [EvaluationJob][google.cloud.datalabeling.v1beta1.EvaluationJob] for a
// model version that performs classification.
ClassificationMetadata classification_metadata = 4;
}
// Metadata for the text.
message TextMetadata {
// The language of this text, as a
// [BCP-47](https://www.rfc-editor.org/rfc/bcp/bcp47.txt).
// Default value is en-US.
string language_code = 1;
}
// Metadata for classification annotations.
message ClassificationMetadata {
// Whether the classification task is multi-label or not.
bool is_multi_label = 1;
}
// Source of the Cloud Storage file to be imported.
message GcsSource {
// Required. The input URI of source file. This must be a Cloud Storage path
// (`gs://...`).
string input_uri = 1;
// Required. The format of the source file. Only "text/csv" is supported.
string mime_type = 2;
}
// The BigQuery location for input data. If used in an [EvaluationJob][google.cloud.datalabeling.v1beta1.EvaluationJob], this
// is where the service saves the prediction input and output sampled from the
// model version.
message BigQuerySource {
// Required. BigQuery URI to a table, up to 2,000 characters long. If you
// specify the URI of a table that does not exist, Data Labeling Service
// creates a table at the URI with the correct schema when you create your
// [EvaluationJob][google.cloud.datalabeling.v1beta1.EvaluationJob]. If you specify the URI of a table that already exists,
// it must have the
// [correct
// schema](/ml-engine/docs/continuous-evaluation/create-job#table-schema).
//
// Provide the table URI in the following format:
//
// "bq://{your_project_id}/{your_dataset_name}/{your_table_name}"
//
// [Learn
// more](/ml-engine/docs/continuous-evaluation/create-job#table-schema).
string input_uri = 1;
}
// The configuration of output data.
message OutputConfig {
// Required. Location to output data to.
oneof destination {
// Output to a file in Cloud Storage. Should be used for labeling output
// other than image segmentation.
GcsDestination gcs_destination = 1;
// Output to a folder in Cloud Storage. Should be used for image
// segmentation labeling output.
GcsFolderDestination gcs_folder_destination = 2;
}
}
// Export destination of the data.Only gcs path is allowed in
// output_uri.
message GcsDestination {
// Required. The output uri of destination file.
string output_uri = 1;
// Required. The format of the gcs destination. Only "text/csv" and
// "application/json"
// are supported.
string mime_type = 2;
}
// Export folder destination of the data.
message GcsFolderDestination {
// Required. Cloud Storage directory to export data to.
string output_folder_uri = 1;
}
// DataItem is a piece of data, without annotation. For example, an image.
message DataItem {
option (google.api.resource) = {
type: "datalabeling.googleapis.com/DataItem"
pattern: "projects/{project}/datasets/{dataset}/dataItems/{data_item}"
};
// Output only.
oneof payload {
// The image payload, a container of the image bytes/uri.
ImagePayload image_payload = 2;
// The text payload, a container of text content.
TextPayload text_payload = 3;
// The video payload, a container of the video uri.
VideoPayload video_payload = 4;
}
// Output only. Name of the data item, in format of:
// projects/{project_id}/datasets/{dataset_id}/dataItems/{data_item_id}
string name = 1;
}
// AnnotatedDataset is a set holding annotations for data in a Dataset. Each
// labeling task will generate an AnnotatedDataset under the Dataset that the
// task is requested for.
message AnnotatedDataset {
option (google.api.resource) = {
type: "datalabeling.googleapis.com/AnnotatedDataset"
pattern: "projects/{project}/datasets/{dataset}/annotatedDatasets/{annotated_dataset}"
};
// Output only. AnnotatedDataset resource name in format of:
// projects/{project_id}/datasets/{dataset_id}/annotatedDatasets/
// {annotated_dataset_id}
string name = 1;
// Output only. The display name of the AnnotatedDataset. It is specified in
// HumanAnnotationConfig when user starts a labeling task. Maximum of 64
// characters.
string display_name = 2;
// Output only. The description of the AnnotatedDataset. It is specified in
// HumanAnnotationConfig when user starts a labeling task. Maximum of 10000
// characters.
string description = 9;
// Output only. Source of the annotation.
AnnotationSource annotation_source = 3;
// Output only. Type of the annotation. It is specified when starting labeling
// task.
AnnotationType annotation_type = 8;
// Output only. Number of examples in the annotated dataset.
int64 example_count = 4;
// Output only. Number of examples that have annotation in the annotated
// dataset.
int64 completed_example_count = 5;
// Output only. Per label statistics.
LabelStats label_stats = 6;
// Output only. Time the AnnotatedDataset was created.
google.protobuf.Timestamp create_time = 7;
// Output only. Additional information about AnnotatedDataset.
AnnotatedDatasetMetadata metadata = 10;
// Output only. The names of any related resources that are blocking changes
// to the annotated dataset.
repeated string blocking_resources = 11;
}
// Statistics about annotation specs.
message LabelStats {
// Map of each annotation spec's example count. Key is the annotation spec
// name and value is the number of examples for that annotation spec.
// If the annotated dataset does not have annotation spec, the map will return
// a pair where the key is empty string and value is the total number of
// annotations.
map example_count = 1;
}
// Metadata on AnnotatedDataset.
message AnnotatedDatasetMetadata {
// Specific request configuration used when requesting the labeling task.
oneof annotation_request_config {
// Configuration for image classification task.
ImageClassificationConfig image_classification_config = 2;
// Configuration for image bounding box and bounding poly task.
BoundingPolyConfig bounding_poly_config = 3;
// Configuration for image polyline task.
PolylineConfig polyline_config = 4;
// Configuration for image segmentation task.
SegmentationConfig segmentation_config = 5;
// Configuration for video classification task.
VideoClassificationConfig video_classification_config = 6;
// Configuration for video object detection task.
ObjectDetectionConfig object_detection_config = 7;
// Configuration for video object tracking task.
ObjectTrackingConfig object_tracking_config = 8;
// Configuration for video event labeling task.
EventConfig event_config = 9;
// Configuration for text classification task.
TextClassificationConfig text_classification_config = 10;
// Configuration for text entity extraction task.
TextEntityExtractionConfig text_entity_extraction_config = 11;
}
// HumanAnnotationConfig used when requesting the human labeling task for this
// AnnotatedDataset.
HumanAnnotationConfig human_annotation_config = 1;
}
// An Example is a piece of data and its annotation. For example, an image with
// label "house".
message Example {
option (google.api.resource) = {
type: "datalabeling.googleapis.com/Example"
pattern: "projects/{project}/datasets/{dataset}/annotatedDatasets/{annotated_dataset}/examples/{example}"
};
// Output only. The data part of Example.
oneof payload {
// The image payload, a container of the image bytes/uri.
ImagePayload image_payload = 2;
// The text payload, a container of the text content.
TextPayload text_payload = 6;
// The video payload, a container of the video uri.
VideoPayload video_payload = 7;
}
// Output only. Name of the example, in format of:
// projects/{project_id}/datasets/{dataset_id}/annotatedDatasets/
// {annotated_dataset_id}/examples/{example_id}
string name = 1;
// Output only. Annotations for the piece of data in Example.
// One piece of data can have multiple annotations.
repeated Annotation annotations = 5;
}