tfx.components.infra_validator.model_server_clients.tensorflow_serving_client.TensorFlowServingClient

A model server client for TensorFlow Serving.

tfx.components.infra_validator.model_server_clients.tensorflow_serving_client.TensorFlowServingClient(
    endpoint: Text,
    model_name: Text
)

It uses gRPC client to talk to TensorFlow Serving server.

Methods

SendRequests(
    requests: List[tfx.components.infra_validator.types.Request]
) -> None

Send requests to the model server.

Args
`requests`	A list of request protos.

Raises
`ValidationFailed`	If error occurred while sending requests.

WaitUntilModelLoaded(
    deadline: float,
    polling_interval_sec: int
) -> None

Wait until model is loaded and available.

Args
`deadline`	A deadline time in UTC timestamp (in seconds).
`polling_interval_sec`	GetServingStatus() polling interval.

Raises
`DeadlineExceeded`	When deadline exceeded before model is ready.
`ValidationFailed`	If validation failed explicitly.