// Copyright 2025 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.automl.v1;

import "google/api/annotations.proto";
import "google/api/client.proto";
import "google/api/field_behavior.proto";
import "google/api/resource.proto";
import "google/cloud/automl/v1/annotation_payload.proto";
import "google/cloud/automl/v1/data_items.proto";
import "google/cloud/automl/v1/io.proto";
import "google/longrunning/operations.proto";

option csharp_namespace = "Google.Cloud.AutoML.V1";
option go_package = "cloud.google.com/go/automl/apiv1/automlpb;automlpb";
option java_multiple_files = true;
option java_outer_classname = "PredictionServiceProto";
option java_package = "com.google.cloud.automl.v1";
option php_namespace = "Google\\Cloud\\AutoMl\\V1";
option ruby_package = "Google::Cloud::AutoML::V1";

// AutoML Prediction API.
//
// On any input that is documented to expect a string parameter in
// snake_case or dash-case, either of those cases is accepted.
service PredictionService {
  option (google.api.default_host) = "automl.googleapis.com";
  option (google.api.oauth_scopes) = "https://www.googleapis.com/auth/cloud-platform";

  // Perform an online prediction. The prediction result is directly
  // returned in the response.
  // Available for following ML scenarios, and their expected request payloads:
  //
  // AutoML Vision Classification
  //
  // * An image in .JPEG, .GIF or .PNG format, image_bytes up to 30MB.
  //
  // AutoML Vision Object Detection
  //
  // * An image in .JPEG, .GIF or .PNG format, image_bytes up to 30MB.
  //
  // AutoML Natural Language Classification
  //
  // * A TextSnippet up to 60,000 characters, UTF-8 encoded or a document in
  // .PDF, .TIF or .TIFF format with size upto 2MB.
  //
  // AutoML Natural Language Entity Extraction
  //
  // * A TextSnippet up to 10,000 characters, UTF-8 NFC encoded or a document
  //  in .PDF, .TIF or .TIFF format with size upto 20MB.
  //
  // AutoML Natural Language Sentiment Analysis
  //
  // * A TextSnippet up to 60,000 characters, UTF-8 encoded or a document in
  // .PDF, .TIF or .TIFF format with size upto 2MB.
  //
  // AutoML Translation
  //
  // * A TextSnippet up to 25,000 characters, UTF-8 encoded.
  //
  // AutoML Tables
  //
  // * A row with column values matching
  //   the columns of the model, up to 5MB. Not available for FORECASTING
  //   `prediction_type`.
  rpc Predict(PredictRequest) returns (PredictResponse) {
    option (google.api.http) = {
      post: "/v1/{name=projects/*/locations/*/models/*}:predict"
      body: "*"
    };
    option (google.api.method_signature) = "name,payload,params";
  }

  // Perform a batch prediction. Unlike the online [Predict][google.cloud.automl.v1.PredictionService.Predict], batch
  // prediction result won't be immediately available in the response. Instead,
  // a long running operation object is returned. User can poll the operation
  // result via [GetOperation][google.longrunning.Operations.GetOperation]
  // method. Once the operation is done, [BatchPredictResult][google.cloud.automl.v1.BatchPredictResult] is returned in
  // the [response][google.longrunning.Operation.response] field.
  // Available for following ML scenarios:
  //
  // * AutoML Vision Classification
  // * AutoML Vision Object Detection
  // * AutoML Video Intelligence Classification
  // * AutoML Video Intelligence Object Tracking * AutoML Natural Language Classification
  // * AutoML Natural Language Entity Extraction
  // * AutoML Natural Language Sentiment Analysis
  // * AutoML Tables
  rpc BatchPredict(BatchPredictRequest) returns (google.longrunning.Operation) {
    option (google.api.http) = {
      post: "/v1/{name=projects/*/locations/*/models/*}:batchPredict"
      body: "*"
    };
    option (google.api.method_signature) = "name,input_config,output_config,params";
    option (google.longrunning.operation_info) = {
      response_type: "BatchPredictResult"
      metadata_type: "OperationMetadata"
    };
  }
}

// Request message for [PredictionService.Predict][google.cloud.automl.v1.PredictionService.Predict].
message PredictRequest {
  // Required. Name of the model requested to serve the prediction.
  string name = 1 [
    (google.api.field_behavior) = REQUIRED,
    (google.api.resource_reference) = {
      type: "automl.googleapis.com/Model"
    }
  ];

  // Required. Payload to perform a prediction on. The payload must match the
  // problem type that the model was trained to solve.
  ExamplePayload payload = 2 [(google.api.field_behavior) = REQUIRED];

  // Additional domain-specific parameters, any string must be up to 25000
  // characters long.
  //
  // AutoML Vision Classification
  //
  // `score_threshold`
  // : (float) A value from 0.0 to 1.0. When the model
  //   makes predictions for an image, it will only produce results that have
  //   at least this confidence score. The default is 0.5.
  //
  // AutoML Vision Object Detection
  //
  // `score_threshold`
  // : (float) When Model detects objects on the image,
  //   it will only produce bounding boxes which have at least this
  //   confidence score. Value in 0 to 1 range, default is 0.5.
  //
  // `max_bounding_box_count`
  // : (int64) The maximum number of bounding
  //   boxes returned. The default is 100. The
  //   number of returned bounding boxes might be limited by the server.
  //
  // AutoML Tables
  //
  // `feature_importance`
  // : (boolean) Whether
  // [feature_importance][google.cloud.automl.v1.TablesModelColumnInfo.feature_importance]
  //   is populated in the returned list of
  //   [TablesAnnotation][google.cloud.automl.v1.TablesAnnotation]
  //   objects. The default is false.
  map<string, string> params = 3;
}

// Response message for [PredictionService.Predict][google.cloud.automl.v1.PredictionService.Predict].
message PredictResponse {
  // Prediction result.
  // AutoML Translation and AutoML Natural Language Sentiment Analysis
  // return precisely one payload.
  repeated AnnotationPayload payload = 1;

  // The preprocessed example that AutoML actually makes prediction on.
  // Empty if AutoML does not preprocess the input example.
  //
  // For AutoML Natural Language (Classification, Entity Extraction, and
  // Sentiment Analysis), if the input is a document, the recognized text is
  // returned in the
  // [document_text][google.cloud.automl.v1.Document.document_text]
  // property.
  ExamplePayload preprocessed_input = 3;

  // Additional domain-specific prediction response metadata.
  //
  // AutoML Vision Object Detection
  //
  // `max_bounding_box_count`
  // : (int64) The maximum number of bounding boxes to return per image.
  //
  // AutoML Natural Language Sentiment Analysis
  //
  // `sentiment_score`
  // : (float, deprecated) A value between -1 and 1,
  //   -1 maps to least positive sentiment, while 1 maps to the most positive
  //   one and the higher the score, the more positive the sentiment in the
  //   document is. Yet these values are relative to the training data, so
  //   e.g. if all data was positive then -1 is also positive (though
  //   the least).
  //   `sentiment_score` is not the same as "score" and "magnitude"
  //   from Sentiment Analysis in the Natural Language API.
  map<string, string> metadata = 2;
}

// Request message for [PredictionService.BatchPredict][google.cloud.automl.v1.PredictionService.BatchPredict].
message BatchPredictRequest {
  // Required. Name of the model requested to serve the batch prediction.
  string name = 1 [
    (google.api.field_behavior) = REQUIRED,
    (google.api.resource_reference) = {
      type: "automl.googleapis.com/Model"
    }
  ];

  // Required. The input configuration for batch prediction.
  BatchPredictInputConfig input_config = 3 [(google.api.field_behavior) = REQUIRED];

  // Required. The Configuration specifying where output predictions should
  // be written.
  BatchPredictOutputConfig output_config = 4 [(google.api.field_behavior) = REQUIRED];

  // Additional domain-specific parameters for the predictions, any string must
  // be up to 25000 characters long.
  //
  // AutoML Natural Language Classification
  //
  // `score_threshold`
  // : (float) A value from 0.0 to 1.0. When the model
  //   makes predictions for a text snippet, it will only produce results
  //   that have at least this confidence score. The default is 0.5.
  //
  //
  // AutoML Vision Classification
  //
  // `score_threshold`
  // : (float) A value from 0.0 to 1.0. When the model
  //   makes predictions for an image, it will only produce results that
  //   have at least this confidence score. The default is 0.5.
  //
  // AutoML Vision Object Detection
  //
  // `score_threshold`
  // : (float) When Model detects objects on the image,
  //   it will only produce bounding boxes which have at least this
  //   confidence score. Value in 0 to 1 range, default is 0.5.
  //
  // `max_bounding_box_count`
  // : (int64) The maximum number of bounding
  //   boxes returned per image. The default is 100, the
  //   number of bounding boxes returned might be limited by the server.
  // AutoML Video Intelligence Classification
  //
  // `score_threshold`
  // : (float) A value from 0.0 to 1.0. When the model
  //   makes predictions for a video, it will only produce results that
  //   have at least this confidence score. The default is 0.5.
  //
  // `segment_classification`
  // : (boolean) Set to true to request
  //   segment-level classification. AutoML Video Intelligence returns
  //   labels and their confidence scores for the entire segment of the
  //   video that user specified in the request configuration.
  //   The default is true.
  //
  // `shot_classification`
  // : (boolean) Set to true to request shot-level
  //   classification. AutoML Video Intelligence determines the boundaries
  //   for each camera shot in the entire segment of the video that user
  //   specified in the request configuration. AutoML Video Intelligence
  //   then returns labels and their confidence scores for each detected
  //   shot, along with the start and end time of the shot.
  //   The default is false.
  //
  //   WARNING: Model evaluation is not done for this classification type,
  //   the quality of it depends on training data, but there are no metrics
  //   provided to describe that quality.
  //
  // `1s_interval_classification`
  // : (boolean) Set to true to request
  //   classification for a video at one-second intervals. AutoML Video
  //   Intelligence returns labels and their confidence scores for each
  //   second of the entire segment of the video that user specified in the
  //   request configuration. The default is false.
  //
  //   WARNING: Model evaluation is not done for this classification
  //   type, the quality of it depends on training data, but there are no
  //   metrics provided to describe that quality.
  //
  // AutoML Video Intelligence Object Tracking
  //
  // `score_threshold`
  // : (float) When Model detects objects on video frames,
  //   it will only produce bounding boxes which have at least this
  //   confidence score. Value in 0 to 1 range, default is 0.5.
  //
  // `max_bounding_box_count`
  // : (int64) The maximum number of bounding
  //   boxes returned per image. The default is 100, the
  //   number of bounding boxes returned might be limited by the server.
  //
  // `min_bounding_box_size`
  // : (float) Only bounding boxes with shortest edge
  //   at least that long as a relative value of video frame size are
  //   returned. Value in 0 to 1 range. Default is 0.
  //
  map<string, string> params = 5;
}

// Result of the Batch Predict. This message is returned in
// [response][google.longrunning.Operation.response] of the operation returned
// by the [PredictionService.BatchPredict][google.cloud.automl.v1.PredictionService.BatchPredict].
message BatchPredictResult {
  // Additional domain-specific prediction response metadata.
  //
  // AutoML Vision Object Detection
  //
  // `max_bounding_box_count`
  // : (int64) The maximum number of bounding boxes returned per image.
  //
  // AutoML Video Intelligence Object Tracking
  //
  // `max_bounding_box_count`
  // : (int64) The maximum number of bounding boxes returned per frame.
  map<string, string> metadata = 1;
}