Deprecated: Do not use.

Deprecated: Do not use.

Deprecated: Do not use.

The manager has successfully loaded this servable and made it available for serving (i.e.

This servable has reached the end of its journey in the manager.

The manager has decided to load this servable.

The manager is tracking this servable, but has not initiated any action pertaining to it.

Default value.

The manager has decided to make this servable unavailable, and unload it.

A single class.

Contains one result per input example, in the same order as the input in ClassificationRequest.

List of classes for a single item (tensorflow.Example).

Specifies one or more fully independent input Examples.

Specifies one or more independent input Examples, with a common context Example.

Config proto for FileSystemStoragePathSource.

A servable name and base path to look for versions of the servable.

A policy that dictates which version(s) of a servable should be served.

Serve all versions found on disk.

Serve the latest versions (i.e.

Serve a specific version (or set of versions).

GetModelStatusRequest contains a ModelSpec indicating the model for which to get status.

Response for ModelStatusRequest on successful run.

Inference result, matches the type of request or is an error.

Inference request such as classification, regression, etc...

Configuration for logging query/responses.

Metadata logged along with the request logs.

Common configuration for loading a model being served.

Static list of models to be loaded for serving.

ModelServer config.

Metadata for an inference request such as the model name and version.

Version number, state, and status for a single version of a model.

Configuration for monitoring.

Inference request containing one or more requests.

Inference request containing one or more responses.

Configuration for a servable platform e.g.

Logged model inference request.

PredictRequest specifies which TensorFlow model to run, as well as how inputs are mapped to tensors and how outputs are filtered before returning to user.

Response for PredictRequest on successful run.

Configuration for Prometheus monitoring.

Regression result for a single item (tensorflow.Example).

Contains one result per input example, in the same order as the input in RegressionRequest.

Message returned for "signature_def" field.

Configuration for a secure gRPC channel.

Config proto for StaticStoragePathSource.

Status that corresponds to Status in third_party/tensorflow/core/lib/core/status.h.

UnimplementedModelServiceServer can be embedded to have forward compatible implementations.

UnimplementedPredictionServiceServer can be embedded to have forward compatible implementations.

UnimplementedSessionServiceServer can be embedded to have forward compatible implementations.

ModelServiceClient is the client API for ModelService service.

ModelServiceServer is the server API for ModelService service.

PredictionServiceClient is the client API for PredictionService service.

PredictionServiceServer is the server API for PredictionService service.

SessionServiceClient is the client API for SessionService service.

SessionServiceServer is the server API for SessionService service.

The type of model.

States that map to ManagerState enum in tensorflow_serving/core/servable_state.h.