Provides natural language understanding technologies, such as sentiment analysis, entity recognition, entity sentiment analysis, and other text annotations, to developers.

The entity analysis request message.

The entity analysis response message.

The sentiment analysis request message.

The sentiment analysis response message.

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

All available features. Setting each one to true will enable that specific analysis for the input.

The text annotations response message.

Represents a category returned from the text classifier.

The document classification request message.

The document classification response message.

Represents a color in the RGBA color space. This representation is designed for simplicity of conversion to and from color representations in various languages over compactness. For example, the fields of this representation can be trivially provided to the constructor of java.awt.Color in Java; it can also be trivially provided to UIColor's +colorWithRed:green:blue:alpha method in iOS; and, with just a little work, it can be easily formatted into a CSS rgba() string in JavaScript. This reference page doesn't have information about the absolute color space that should be used to interpret the RGB value—for example, sRGB, Adobe RGB, DCI-P3, and BT.2020. By default, applications should assume the sRGB color space. When color equality needs to be decided, implementations, unless documented otherwise, treat two colors as equal if all their red, green, blue, and alpha values each differ by at most 1e-5. Example (Java): import com.google.type.Color; // ... public static java.awt.Color fromProto(Color protocolor) { float alpha = protocolor.hasAlpha() ? protocolor.getAlpha().getValue() : 1.0; return new java.awt.Color( protocolor.getRed(), protocolor.getGreen(), protocolor.getBlue(), alpha); } public static Color toProto(java.awt.Color color) { float red = (float) color.getRed(); float green = (float) color.getGreen(); float blue = (float) color.getBlue(); float denominator = 255.0; Color.Builder resultBuilder = Color .newBuilder() .setRed(red / denominator) .setGreen(green / denominator) .setBlue(blue / denominator); int alpha = color.getAlpha(); if (alpha != 255) { result.setAlpha( FloatValue .newBuilder() .setValue(((float) alpha) / denominator) .build()); } return resultBuilder.build(); } // ... Example (iOS / Obj-C): // ... static UIColor* fromProto(Color* protocolor) { float red = [protocolor red]; float green = [protocolor green]; float blue = [protocolor blue]; FloatValue* alpha_wrapper = [protocolor alpha]; float alpha = 1.0; if (alpha_wrapper != nil) { alpha = [alpha_wrapper value]; } return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; } static Color* toProto(UIColor* color) { CGFloat red, green, blue, alpha; if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { return nil; } Color* result = [[Color alloc] init]; [result setRed:red]; [result setGreen:green]; [result setBlue:blue]; if (alpha <= 0.9999) { [result setAlpha:floatWrapperWithValue(alpha)]; } [result autorelease]; return result; } // ... Example (JavaScript): // ... var protoToCssColor = function(rgb_color) { var redFrac = rgb_color.red || 0.0; var greenFrac = rgb_color.green || 0.0; var blueFrac = rgb_color.blue || 0.0; var red = Math.floor(redFrac * 255); var green = Math.floor(greenFrac * 255); var blue = Math.floor(blueFrac * 255); if (!('alpha' in rgb_color)) { return rgbToCssColor(red, green, blue); } var alphaFrac = rgb_color.alpha.value || 0.0; var rgbParams = [red, green, blue].join(','); return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); }; var rgbToCssColor = function(red, green, blue) { var rgbNumber = new Number((red << 16) | (green << 8) | blue); var hexString = rgbNumber.toString(16); var missingZeros = 6 - hexString.length; var resultBuilder = ['#']; for (var i = 0; i < missingZeros; i++) { resultBuilder.push('0'); } resultBuilder.push(hexString); return resultBuilder.join(''); }; // ...

Metric for billing reports.

Defines the root interface for all clients that generate credentials for calling Google APIs. All clients should implement this interface.

Represents the input to API methods.

Represents a phrase in the text that is a known entity, such as a person, an organization, or location. The API associates information, such as probability and mentions, with entities.

Represents a mention for an entity in the text. Currently, proper noun mentions are supported.

Infra Usage of billing metrics. Next ID: 6

The document moderation request message.

The document moderation response message.

Represents a sentence in the input document.

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

The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by gRPC. Each Status message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the API Design Guide.

Represents a text span in the input document.

The data statistics of a series of ARRAY values.

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

Metrics for a single confidence threshold.

The data statistics of a series of CATEGORY values.

The statistics of a single CATEGORY value.

Model evaluation metrics for classification problems. It can be used for image and video classification. Next tag: 9.

Map from color to display name. Will only be used by Image Segmentation for uCAIP.

RGB color and each channel is represented by an integer.

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

===========================================================================

The fields below are used exclusively for Forecasting.

Common statistics for a column with a specified data type.

ConfidenceMetricsEntry includes generic precision, recall, f1 score etc. Next tag: 16.

Confusion matrix of the model running the classification.

A row in the confusion matrix.

A model format used for iOS mobile devices.

A correlation statistics between two series of DataType values. The series may have differing DataType-s, but within a single series the DataType must be the same.

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

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

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

A model format used for Docker containers. Use the params field to customize the container. The container is verified to work correctly on ubuntu 16.04 operating system.

A model format used for Edge TPU devices.

Contains xPS-specific model evaluation metrics either for a single annotation spec (label), or for the model overall. Next tag: 18.

Specifies location of model evaluation metrics.

Set of examples or input sources.

Spec of input and output files, on external file systems (CNS, GCS, etc).

The data statistics of a series of FLOAT64 values.

A bucket of a histogram.

Information of downloadable models that are pre-generated as part of training flow and will be persisted in AutoMl backend. Upon receiving ExportModel request from user, AutoMl backend can serve the pre-generated models to user if exists (by copying the files from internal path to user provided location), otherwise, AutoMl backend will call xPS ExportModel API to generate the model on the fly with the requesting format.

Stores the locations and related metadata of the model artifacts. Populated for uCAIP requests only.

Serving specification for image models.

Model evaluation metrics for image object detection problems. Evaluates prediction quality of labeled bounding boxes.

Model evaluation metrics for image segmentation problems. Next tag: 4.

Metrics for a single confidence threshold.

An attribution method that computes the Aumann-Shapley value taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1703.01365

A single model artifact item.

Next ID: 8

Model evaluation metrics for regression problems. It can be used for Tables.

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

Metadata of the input of a feature.

Metadata of the prediction output to be explained.

Specification of Model explanation. Feature-based XAI in AutoML Vision ICN is deprecated, see b/288407203 for context.

The data statistics of a series of STRING values.

The statistics of a unigram.

The data statistics of a series of STRUCT values.

StructType defines the DataType-s of a STRUCT type.

Metrics for Tables classification problems.

Metrics curve data point for a single value.

Metrics for a single confidence threshold.

Metadata for a dataset used for AutoML Tables. Next ID: 6

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

A description of Tables model structure.

Model hyper-parameters for a model.

Metrics for Tables regression problems.

Component model. Next ID: 10

Model evaluation metrics for text sentiment problems.

TextToSpeech train response

A TensorFlow.js model that can be used in the browser and in Node.js using JavaScript.

LINT.IfChange A model format used for mobile and IoT devices. See https://www.tensorflow.org/lite.

A tensorflow model format in SavedModel format.

The data statistics of a series of TIMESTAMP values.

Stats split by a defined in context granularity.

Track matching model metrics for a single track match threshold and multiple label match confidence thresholds. Next tag: 6.

Metrics for a single confidence threshold. Next tag: 6.

Next ID: 18

Evaluation metrics for the dataset.

Translation preprocess response.

Train response for translation.

Metrics for a tuning job generated, will get forwarded to Stackdriver as model tuning logs. Setting this as a standalone message out of CreateModelMetadata to avoid confusion as we expose this message only to users.

The Evaluation metrics entry given a specific precision_window_length.

Metrics for a single confidence threshold.

Model evaluation metrics for video action recognition.

Information of downloadable models that are pre-generated as part of training flow and will be persisted in AutoMl backend. Upon receiving ExportModel request from user, AutoMl backend can serve the pre-generated models to user if exists (by copying the files from internal path to user provided location), otherwise, AutoMl backend will call xPS ExportModel API to generate the model on the fly with the requesting format.

Model evaluation metrics for ObjectTracking problems. Next tag: 10.

The vision model error analysis configuration. Next tag: 3

Visualization configurations for image explanation.

An explanation method that redistributes Integrated Gradients attributions to segmented regions, taking advantage of the model's fully differentiable structure. Refer to this paper for more details: https://arxiv.org/abs/1906.02825 Only supports image Models (modality is IMAGE).