OpenLLM/openllm-client/protos/service.proto

// Vendorred from: https://github.com/bentoml/BentoML/blob/main/src/bentoml/grpc/v1/service.proto
syntax = "proto3";

package bentoml.grpc.v1;

import "google/protobuf/struct.proto";
import "google/protobuf/wrappers.proto";

// cc_enable_arenas pre-allocate memory for given message to improve speed. (C++ only)
option cc_enable_arenas = true;
option go_package = "github.com/bentoml/bentoml/grpc/v1;service";
option java_multiple_files = true;
option java_outer_classname = "ServiceProto";
option java_package = "com.bentoml.grpc.v1";
option objc_class_prefix = "SVC";
option py_generic_services = true;

// a gRPC BentoServer.
service BentoService {
  // Call handles methodcaller of given API entrypoint.
  rpc Call(Request) returns (Response) {}
  // ServiceMetadata returns metadata of bentoml.Service.
  rpc ServiceMetadata(ServiceMetadataRequest) returns (ServiceMetadataResponse) {}
}

// ServiceMetadataRequest message doesn't take any arguments.
message ServiceMetadataRequest {}

// ServiceMetadataResponse returns metadata of bentoml.Service.
// Currently it includes name, version, apis, and docs.
message ServiceMetadataResponse {
  // DescriptorMetadata is a metadata of any given IODescriptor.
  message DescriptorMetadata {
    // descriptor_id describes the given ID of the descriptor, which matches with our OpenAPI definition.
    optional string descriptor_id = 1;

    // attributes is the kwargs of the given descriptor.
    google.protobuf.Struct attributes = 2;
  }
  // InferenceAPI is bentoml._internal.service.inferece_api.InferenceAPI
  // that is exposed to gRPC client.
  // There is no way for reflection to get information of given @svc.api.
  message InferenceAPI {
    // name is the name of the API.
    string name = 1;
    // input is the input descriptor of the API.
    optional DescriptorMetadata input = 2;
    // output is the output descriptor of the API.
    optional DescriptorMetadata output = 3;
    // docs is the optional documentation of the API.
    optional string docs = 4;
  }
  // name is the service name.
  string name = 1;
  // apis holds a list of InferenceAPI of the service.
  repeated InferenceAPI apis = 2;
  // docs is the documentation of the service.
  string docs = 3;
}

// Request message for incoming Call.
message Request {
  // api_name defines the API entrypoint to call.
  // api_name is the name of the function defined in bentoml.Service.
  // Example:
  //
  //     @svc.api(input=NumpyNdarray(), output=File())
  //     def predict(input: NDArray[float]) -> bytes:
  //         ...
  //
  //     api_name is "predict" in this case.
  string api_name = 1;

  oneof content {
    // NDArray represents a n-dimensional array of arbitrary type.
    NDArray ndarray = 3;

    // DataFrame represents any tabular data type. We are using
    // DataFrame as a trivial representation for tabular type.
    DataFrame dataframe = 5;

    // Series portrays a series of values. This can be used for
    // representing Series types in tabular data.
    Series series = 6;

    // File represents for any arbitrary file type. This can be
    // plaintext, image, video, audio, etc.
    File file = 7;

    // Text represents a string inputs.
    google.protobuf.StringValue text = 8;

    // JSON is represented by using google.protobuf.Value.
    // see https://github.com/protocolbuffers/protobuf/blob/main/src/google/protobuf/struct.proto
    google.protobuf.Value json = 9;

    // Multipart represents a multipart message.
    // It comprises of a mapping from given type name to a subset of aforementioned types.
    Multipart multipart = 10;

    // serialized_bytes is for data serialized in BentoML's internal serialization format.
    bytes serialized_bytes = 2;
  }

  // Tensor is similiar to ndarray but with a name
  // We are reserving it for now for future use.
  // repeated Tensor tensors = 4;
  reserved 4, 11 to 13;
}

// Request message for incoming Call.
message Response {
  oneof content {
    // NDArray represents a n-dimensional array of arbitrary type.
    NDArray ndarray = 1;

    // DataFrame represents any tabular data type. We are using
    // DataFrame as a trivial representation for tabular type.
    DataFrame dataframe = 3;

    // Series portrays a series of values. This can be used for
    // representing Series types in tabular data.
    Series series = 5;

    // File represents for any arbitrary file type. This can be
    // plaintext, image, video, audio, etc.
    File file = 6;

    // Text represents a string inputs.
    google.protobuf.StringValue text = 7;

    // JSON is represented by using google.protobuf.Value.
    // see https://github.com/protocolbuffers/protobuf/blob/main/src/google/protobuf/struct.proto
    google.protobuf.Value json = 8;

    // Multipart represents a multipart message.
    // It comprises of a mapping from given type name to a subset of aforementioned types.
    Multipart multipart = 9;

    // serialized_bytes is for data serialized in BentoML's internal serialization format.
    bytes serialized_bytes = 2;
  }
  // Tensor is similiar to ndarray but with a name
  // We are reserving it for now for future use.
  // repeated Tensor tensors = 4;
  reserved 4, 10 to 13;
}

// Part represents possible value types for multipart message.
// These are the same as the types in Request message.
message Part {
  oneof representation {
    // NDArray represents a n-dimensional array of arbitrary type.
    NDArray ndarray = 1;

    // DataFrame represents any tabular data type. We are using
    // DataFrame as a trivial representation for tabular type.
    DataFrame dataframe = 3;

    // Series portrays a series of values. This can be used for
    // representing Series types in tabular data.
    Series series = 5;

    // File represents for any arbitrary file type. This can be
    // plaintext, image, video, audio, etc.
    File file = 6;

    // Text represents a string inputs.
    google.protobuf.StringValue text = 7;

    // JSON is represented by using google.protobuf.Value.
    // see https://github.com/protocolbuffers/protobuf/blob/main/src/google/protobuf/struct.proto
    google.protobuf.Value json = 8;

    // serialized_bytes is for data serialized in BentoML's internal serialization format.
    bytes serialized_bytes = 4;
  }

  // Tensor is similiar to ndarray but with a name
  // We are reserving it for now for future use.
  // Tensor tensors = 4;
  reserved 2, 9 to 13;
}

// Multipart represents a multipart message.
// It comprises of a mapping from given type name to a subset of aforementioned types.
message Multipart {
  map<string, Part> fields = 1;
}

// File represents for any arbitrary file type. This can be
// plaintext, image, video, audio, etc.
message File {
  // optional file type, let it be csv, text, parquet, etc.
  // v1alpha1 uses 1 as FileType enum.
  optional string kind = 3;
  // contents of file as bytes.
  bytes content = 2;
}

// DataFrame represents any tabular data type. We are using
// DataFrame as a trivial representation for tabular type.
// This message carries given implementation of tabular data based on given orientation.
// TODO: support index, records, etc.
message DataFrame {
  // columns name
  repeated string column_names = 1;

  // columns orient.
  // { column ↠ { index ↠ value } }
  repeated Series columns = 2;
}

// Series portrays a series of values. This can be used for
// representing Series types in tabular data.
message Series {
  // A bool parameter value
  repeated bool bool_values = 1 [packed = true];

  // A float parameter value
  repeated float float_values = 2 [packed = true];

  // A int32 parameter value
  repeated int32 int32_values = 3 [packed = true];

  // A int64 parameter value
  repeated int64 int64_values = 6 [packed = true];

  // A string parameter value
  repeated string string_values = 5;

  // represents a double parameter value.
  repeated double double_values = 4 [packed = true];
}

// NDArray represents a n-dimensional array of arbitrary type.
message NDArray {
  // Represents data type of a given array.
  enum DType {
    // Represents a None type.
    DTYPE_UNSPECIFIED = 0;

    // Represents an float type.
    DTYPE_FLOAT = 1;

    // Represents an double type.
    DTYPE_DOUBLE = 2;

    // Represents a bool type.
    DTYPE_BOOL = 3;

    // Represents an int32 type.
    DTYPE_INT32 = 4;

    // Represents an int64 type.
    DTYPE_INT64 = 5;

    // Represents a uint32 type.
    DTYPE_UINT32 = 6;

    // Represents a uint64 type.
    DTYPE_UINT64 = 7;

    // Represents a string type.
    DTYPE_STRING = 8;
  }

  // DTYPE is the data type of given array
  DType dtype = 1;

  // shape is the shape of given array.
  repeated int32 shape = 2;

  // represents a string parameter value.
  repeated string string_values = 5;

  // represents a float parameter value.
  repeated float float_values = 3 [packed = true];

  // represents a double parameter value.
  repeated double double_values = 4 [packed = true];

  // represents a bool parameter value.
  repeated bool bool_values = 6 [packed = true];

  // represents a int32 parameter value.
  repeated int32 int32_values = 7 [packed = true];

  // represents a int64 parameter value.
  repeated int64 int64_values = 8 [packed = true];

  // represents a uint32 parameter value.
  repeated uint32 uint32_values = 9 [packed = true];

  // represents a uint64 parameter value.
  repeated uint64 uint64_values = 10 [packed = true];
}