Class InferGrpcStreamContext¶
Defined in File request_grpc.h
Class Documentation¶
-
class
InferGrpcStreamContext¶ InferGrpcStreamContext is the streaming instantiation of InferGrpcContext.
All synchronous and asynchronous requests sent from this context will be sent in the same stream.
Public Static Functions
-
static Error
Create(std::unique_ptr<InferContext> *ctx, const std::string &server_url, const std::string &model_name, int64_t model_version = -1, bool verbose = false)¶ Create streaming context that performs inference for a non-sequence model using the GRPC protocol.
- Return
Error object indicating success or failure.
- Parameters
ctx: Returns a new InferGrpcContext object.server_url: The inference server name and port.model_name: The name of the model to get status for.model_version: The version of the model to use for inference, or -1 to indicate that the latest (i.e. highest version number) version should be used.verbose: If true generate verbose output when contacting the inference server.
-
static Error
Create(std::unique_ptr<InferContext> *ctx, CorrelationID correlation_id, const std::string &server_url, const std::string &model_name, int64_t model_version = -1, bool verbose = false)¶ Create streaming context that performs inference for a sequence model using a given correlation ID and the GRPC protocol.
- Return
Error object indicating success or failure.
- Parameters
ctx: Returns a new InferGrpcContext object.correlation_id: The correlation ID to use for all inferences performed with this context. A value of 0 (zero) indicates that no correlation ID should be used.server_url: The inference server name and port.model_name: The name of the model to get status for.model_version: The version of the model to use for inference, or -1 to indicate that the latest (i.e. highest version number) version should be used.verbose: If true generate verbose output when contacting the inference server.
-
static Error