New creates a new Service.

NewService creates a new Service.

Apply machine learning models to reveal the structure and meaning of text.

See, edit, configure, and delete your Google Cloud data and see the email address for your Google Account.

AnalyzeEntitiesRequest: The entity analysis request message.

AnalyzeEntitiesResponse: The entity analysis response message.

AnalyzeSentimentRequest: The sentiment analysis request message.

AnalyzeSentimentResponse: The sentiment analysis response message.

AnnotateTextRequest: The request message for the text annotation API, which can perform multiple analysis types in one call.

AnnotateTextRequestFeatures: All available features.

AnnotateTextResponse: The text annotations response message.

ClassificationCategory: Represents a category returned from the text classifier.

ClassifyTextRequest: The document classification request message.

ClassifyTextResponse: The document classification response message.

Color: Represents a color in the RGBA color space.

CpuMetric: Metric for billing reports.

Document: Represents the input to API methods.

Entity: Represents a phrase in the text that is a known entity, such as a person, an organization, or location.

EntityMention: Represents a mention for an entity in the text.

InfraUsage: Infra Usage of billing metrics.

ModerateTextRequest: The document moderation request message.

ModerateTextResponse: The document moderation response message.

Sentence: Represents a sentence in the input document.

Sentiment: Represents the feeling associated with the entire text or entities in the text.

Status: The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs.

TextSpan: Represents a text span in the input document.

XPSArrayStats: The data statistics of a series of ARRAY values.

XPSBoundingBoxMetricsEntry: Bounding box matching model metrics for a single intersection-over-union threshold and multiple label match confidence thresholds.

XPSBoundingBoxMetricsEntryConfidenceMetricsEntry: Metrics for a single confidence threshold.

XPSCategoryStats: The data statistics of a series of CATEGORY values.

XPSCategoryStatsSingleCategoryStats: The statistics of a single CATEGORY value.

XPSClassificationEvaluationMetrics: Model evaluation metrics for classification problems.

XPSColorMap: Map from color to display name.

XPSColorMapIntColor: RGB color and each channel is represented by an integer.

XPSColumnSpecCorrelatedColumn: Identifies a table's column, and its correlation with the column this ColumnSpec describes.

XPSCommonStats: Common statistics for a column with a specified data type.

XPSConfidenceMetricsEntry: ConfidenceMetricsEntry includes generic precision, recall, f1 score etc.

XPSConfusionMatrix: Confusion matrix of the model running the classification.

XPSConfusionMatrixRow: A row in the confusion matrix.

XPSCoreMlFormat: A model format used for iOS mobile devices.

XPSCorrelationStats: A correlation statistics between two series of DataType values.

XPSDataErrors: Different types of errors and the stats associatesd with each error.

XPSDataStats: The data statistics of a series of values that share the same DataType.

XPSDataType: Indicated the type of data that can be stored in a structured data entity (e.g.

XPSDockerFormat: A model format used for Docker containers.

XPSEdgeTpuTfLiteFormat: A model format used for Edge TPU (https://cloud.google.com/edge-tpu/) devices.

XPSEvaluationMetrics: Contains xPS-specific model evaluation metrics either for a single annotation spec (label), or for the model overall.

XPSEvaluationMetricsSet: Specifies location of model evaluation metrics.

XPSExampleSet: Set of examples or input sources.

XPSFileSpec: Spec of input and output files, on external file systems (for example, Colossus Namespace System or Google Cloud Storage).

XPSFloat64Stats: The data statistics of a series of FLOAT64 values.

XPSFloat64StatsHistogramBucket: A bucket of a histogram.

XPSImageExportModelSpec: Information of downloadable models that are pre-generated as part of training flow and will be persisted in AutoMl backend.

XPSImageModelArtifactSpec: Stores the locations and related metadata of the model artifacts.

XPSImageModelServingSpec: Serving specification for image models.

XPSImageObjectDetectionEvaluationMetrics: Model evaluation metrics for image object detection problems.

XPSImageSegmentationEvaluationMetrics: Model evaluation metrics for image segmentation problems.

XPSImageSegmentationEvaluationMetricsConfidenceMetricsEntry: Metrics for a single confidence threshold.

XPSIntegratedGradientsAttribution: An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure.

XPSModelArtifactItem: A single model artifact item.

XPSRegressionEvaluationMetrics: Model evaluation metrics for regression problems.

XPSRegressionMetricsEntry: A pair of actual & observed values for the model being evaluated.

XPSResponseExplanationMetadataInputMetadata: Metadata of the input of a feature.

XPSResponseExplanationMetadataOutputMetadata: Metadata of the prediction output to be explained.

XPSResponseExplanationSpec: Specification of Model explanation.

XPSStringStats: The data statistics of a series of STRING values.

XPSStringStatsUnigramStats: The statistics of a unigram.

XPSStructStats: The data statistics of a series of STRUCT values.

XPSStructType: `StructType` defines the DataType-s of a STRUCT type.

XPSTablesClassificationMetrics: Metrics for Tables classification problems.

XPSTablesClassificationMetricsCurveMetrics: Metrics curve data point for a single value.

XPSTablesConfidenceMetricsEntry: Metrics for a single confidence threshold.

XPSTablesDatasetMetadata: Metadata for a dataset used for AutoML Tables.

XPSTablesModelColumnInfo: An information specific to given column and Tables Model, in context of the Model and the predictions created by it.

XPSTablesModelStructure: A description of Tables model structure.

XPSTablesModelStructureModelParameters: Model hyper-parameters for a model.

XPSTablesRegressionMetrics: Metrics for Tables regression problems.

XPSTextComponentModel: Component model.

XPSTextSentimentEvaluationMetrics: Model evaluation metrics for text sentiment problems.

XPSTextToSpeechTrainResponse: TextToSpeech train response.

XPSTfJsFormat: A TensorFlow.js (https://www.tensorflow.org/js) model that can be used in the browser and in Node.js using JavaScript.

XPSTfLiteFormat: LINT.IfChange A model format used for mobile and IoT devices.

XPSTfSavedModelFormat: A tensorflow model format in SavedModel format.

XPSTimestampStats: The data statistics of a series of TIMESTAMP values.

XPSTimestampStatsGranularStats: Stats split by a defined in context granularity.

XPSTrackMetricsEntry: Track matching model metrics for a single track match threshold and multiple label match confidence thresholds.

XPSTrackMetricsEntryConfidenceMetricsEntry: Metrics for a single confidence threshold.

XPSTranslationEvaluationMetrics: Evaluation metrics for the dataset.

XPSTranslationPreprocessResponse: Translation preprocess response.

XPSTranslationTrainResponse: Train response for translation.

XPSTuningTrial: Metrics for a tuning job generated, will get forwarded to Stackdriver as model tuning logs.

XPSVideoActionMetricsEntry: The Evaluation metrics entry given a specific precision_window_length.

XPSVideoActionMetricsEntryConfidenceMetricsEntry: Metrics for a single confidence threshold.

XPSVideoActionRecognitionEvaluationMetrics: Model evaluation metrics for video action recognition.

XPSVideoExportModelSpec: Information of downloadable models that are pre-generated as part of training flow and will be persisted in AutoMl backend.

XPSVideoObjectTrackingEvaluationMetrics: Model evaluation metrics for ObjectTracking problems.

XPSVisionErrorAnalysisConfig: The vision model error analysis configuration.

XPSVisualization: Visualization configurations for image explanation.

XPSXraiAttribution: An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure.