v1

package
v1.27.3 Latest Latest
Warning

This package is not in the latest version of its module.

Go to latest
Published: May 13, 2025 License: Apache-2.0 Imports: 16 Imported by: 0

Documentation

Overview

Package v1 is a reverse proxy.

It translates gRPC into RESTful JSON APIs.

Index

Constants

This section is empty.

Variables

View Source
var ChatService_ServiceDesc = grpc.ServiceDesc{
	ServiceName: "llmariner.chat.server.v1.ChatService",
	HandlerType: (*ChatServiceServer)(nil),
	Methods:     []grpc.MethodDesc{},
	Streams:     []grpc.StreamDesc{},
	Metadata:    "api/v1/inference_server.proto",
}

ChatService_ServiceDesc is the grpc.ServiceDesc for ChatService service. It's only intended for direct use with grpc.RegisterService, and not to be introspected or modified (even as a copy)

View Source
var File_api_v1_inference_server_embeddings_proto protoreflect.FileDescriptor
View Source
var File_api_v1_inference_server_internal_proto protoreflect.FileDescriptor
View Source
var File_api_v1_inference_server_management_proto protoreflect.FileDescriptor
View Source
var File_api_v1_inference_server_proto protoreflect.FileDescriptor
View Source
var File_api_v1_inference_server_worker_proto protoreflect.FileDescriptor
View Source
var InferenceInternalService_ServiceDesc = grpc.ServiceDesc{
	ServiceName: "llmariner.inference.server.v1.InferenceInternalService",
	HandlerType: (*InferenceInternalServiceServer)(nil),
	Methods:     []grpc.MethodDesc{},
	Streams: []grpc.StreamDesc{
		{
			StreamName:    "ProcessTasksInternal",
			Handler:       _InferenceInternalService_ProcessTasksInternal_Handler,
			ServerStreams: true,
			ClientStreams: true,
		},
	},
	Metadata: "api/v1/inference_server_internal.proto",
}

InferenceInternalService_ServiceDesc is the grpc.ServiceDesc for InferenceInternalService service. It's only intended for direct use with grpc.RegisterService, and not to be introspected or modified (even as a copy)

View Source
var InferenceService_ServiceDesc = grpc.ServiceDesc{
	ServiceName: "llmariner.inference.server.v1.InferenceService",
	HandlerType: (*InferenceServiceServer)(nil),
	Methods: []grpc.MethodDesc{
		{
			MethodName: "GetInferenceStatus",
			Handler:    _InferenceService_GetInferenceStatus_Handler,
		},
		{
			MethodName: "ActivateModel",
			Handler:    _InferenceService_ActivateModel_Handler,
		},
		{
			MethodName: "DeactivateModel",
			Handler:    _InferenceService_DeactivateModel_Handler,
		},
	},
	Streams:  []grpc.StreamDesc{},
	Metadata: "api/v1/inference_server_management.proto",
}

InferenceService_ServiceDesc is the grpc.ServiceDesc for InferenceService service. It's only intended for direct use with grpc.RegisterService, and not to be introspected or modified (even as a copy)

View Source
var InferenceWorkerService_ServiceDesc = grpc.ServiceDesc{
	ServiceName: "llmariner.inference.server.v1.InferenceWorkerService",
	HandlerType: (*InferenceWorkerServiceServer)(nil),
	Methods:     []grpc.MethodDesc{},
	Streams: []grpc.StreamDesc{
		{
			StreamName:    "ProcessTasks",
			Handler:       _InferenceWorkerService_ProcessTasks_Handler,
			ServerStreams: true,
			ClientStreams: true,
		},
	},
	Metadata: "api/v1/inference_server_worker.proto",
}

InferenceWorkerService_ServiceDesc is the grpc.ServiceDesc for InferenceWorkerService service. It's only intended for direct use with grpc.RegisterService, and not to be introspected or modified (even as a copy)

Functions

func RegisterChatServiceServer

func RegisterChatServiceServer(s grpc.ServiceRegistrar, srv ChatServiceServer)

func RegisterInferenceInternalServiceServer added in v1.4.0

func RegisterInferenceInternalServiceServer(s grpc.ServiceRegistrar, srv InferenceInternalServiceServer)

func RegisterInferenceServiceHandler added in v1.15.0

func RegisterInferenceServiceHandler(ctx context.Context, mux *runtime.ServeMux, conn *grpc.ClientConn) error

RegisterInferenceServiceHandler registers the http handlers for service InferenceService to "mux". The handlers forward requests to the grpc endpoint over "conn".

func RegisterInferenceServiceHandlerClient added in v1.15.0

func RegisterInferenceServiceHandlerClient(ctx context.Context, mux *runtime.ServeMux, client InferenceServiceClient) error

RegisterInferenceServiceHandlerClient registers the http handlers for service InferenceService to "mux". The handlers forward requests to the grpc endpoint over the given implementation of "InferenceServiceClient". Note: the gRPC framework executes interceptors within the gRPC handler. If the passed in "InferenceServiceClient" doesn't go through the normal gRPC flow (creating a gRPC client etc.) then it will be up to the passed in "InferenceServiceClient" to call the correct interceptors.

func RegisterInferenceServiceHandlerFromEndpoint added in v1.15.0

func RegisterInferenceServiceHandlerFromEndpoint(ctx context.Context, mux *runtime.ServeMux, endpoint string, opts []grpc.DialOption) (err error)

RegisterInferenceServiceHandlerFromEndpoint is same as RegisterInferenceServiceHandler but automatically dials to "endpoint" and closes the connection when "ctx" gets done.

func RegisterInferenceServiceHandlerServer added in v1.15.0

func RegisterInferenceServiceHandlerServer(ctx context.Context, mux *runtime.ServeMux, server InferenceServiceServer) error

RegisterInferenceServiceHandlerServer registers the http handlers for service InferenceService to "mux". UnaryRPC :call InferenceServiceServer directly. StreamingRPC :currently unsupported pending https://github.com/grpc/grpc-go/issues/906. Note that using this registration option will cause many gRPC library features to stop working. Consider using RegisterInferenceServiceHandlerFromEndpoint instead.

func RegisterInferenceServiceServer added in v1.15.0

func RegisterInferenceServiceServer(s grpc.ServiceRegistrar, srv InferenceServiceServer)

func RegisterInferenceWorkerServiceServer

func RegisterInferenceWorkerServiceServer(s grpc.ServiceRegistrar, srv InferenceWorkerServiceServer)

Types

type ActivateModelRequest added in v1.21.0

type ActivateModelRequest struct {
	Id string `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	// contains filtered or unexported fields
}

func (*ActivateModelRequest) Descriptor deprecated added in v1.21.0

func (*ActivateModelRequest) Descriptor() ([]byte, []int)

Deprecated: Use ActivateModelRequest.ProtoReflect.Descriptor instead.

func (*ActivateModelRequest) GetId added in v1.21.0

func (x *ActivateModelRequest) GetId() string

func (*ActivateModelRequest) ProtoMessage added in v1.21.0

func (*ActivateModelRequest) ProtoMessage()

func (*ActivateModelRequest) ProtoReflect added in v1.21.0

func (x *ActivateModelRequest) ProtoReflect() protoreflect.Message

func (*ActivateModelRequest) Reset added in v1.21.0

func (x *ActivateModelRequest) Reset()

func (*ActivateModelRequest) String added in v1.21.0

func (x *ActivateModelRequest) String() string

type ActivateModelResponse added in v1.21.0

type ActivateModelResponse struct {
	// contains filtered or unexported fields
}

func (*ActivateModelResponse) Descriptor deprecated added in v1.21.0

func (*ActivateModelResponse) Descriptor() ([]byte, []int)

Deprecated: Use ActivateModelResponse.ProtoReflect.Descriptor instead.

func (*ActivateModelResponse) ProtoMessage added in v1.21.0

func (*ActivateModelResponse) ProtoMessage()

func (*ActivateModelResponse) ProtoReflect added in v1.21.0

func (x *ActivateModelResponse) ProtoReflect() protoreflect.Message

func (*ActivateModelResponse) Reset added in v1.21.0

func (x *ActivateModelResponse) Reset()

func (*ActivateModelResponse) String added in v1.21.0

func (x *ActivateModelResponse) String() string

type ChatCompletion

type ChatCompletion struct {
	Id                string                   `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	Choices           []*ChatCompletion_Choice `protobuf:"bytes,2,rep,name=choices,proto3" json:"choices,omitempty"`
	Created           int32                    `protobuf:"varint,3,opt,name=created,proto3" json:"created,omitempty"`
	Model             string                   `protobuf:"bytes,4,opt,name=model,proto3" json:"model,omitempty"`
	SystemFingerprint string                   `protobuf:"bytes,5,opt,name=system_fingerprint,json=systemFingerprint,proto3" json:"system_fingerprint,omitempty"`
	Object            string                   `protobuf:"bytes,6,opt,name=object,proto3" json:"object,omitempty"`
	Usage             *Usage                   `protobuf:"bytes,7,opt,name=usage,proto3" json:"usage,omitempty"`
	// contains filtered or unexported fields
}

func (*ChatCompletion) Descriptor deprecated

func (*ChatCompletion) Descriptor() ([]byte, []int)

Deprecated: Use ChatCompletion.ProtoReflect.Descriptor instead.

func (*ChatCompletion) GetChoices

func (x *ChatCompletion) GetChoices() []*ChatCompletion_Choice

func (*ChatCompletion) GetCreated

func (x *ChatCompletion) GetCreated() int32

func (*ChatCompletion) GetId

func (x *ChatCompletion) GetId() string

func (*ChatCompletion) GetModel

func (x *ChatCompletion) GetModel() string

func (*ChatCompletion) GetObject

func (x *ChatCompletion) GetObject() string

func (*ChatCompletion) GetSystemFingerprint

func (x *ChatCompletion) GetSystemFingerprint() string

func (*ChatCompletion) GetUsage

func (x *ChatCompletion) GetUsage() *Usage

func (*ChatCompletion) ProtoMessage

func (*ChatCompletion) ProtoMessage()

func (*ChatCompletion) ProtoReflect

func (x *ChatCompletion) ProtoReflect() protoreflect.Message

func (*ChatCompletion) Reset

func (x *ChatCompletion) Reset()

func (*ChatCompletion) String

func (x *ChatCompletion) String() string

type ChatCompletionChunk

type ChatCompletionChunk struct {
	Id                string                        `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	Choices           []*ChatCompletionChunk_Choice `protobuf:"bytes,2,rep,name=choices,proto3" json:"choices,omitempty"`
	Created           int32                         `protobuf:"varint,3,opt,name=created,proto3" json:"created,omitempty"`
	Model             string                        `protobuf:"bytes,4,opt,name=model,proto3" json:"model,omitempty"`
	SystemFingerprint string                        `protobuf:"bytes,5,opt,name=system_fingerprint,json=systemFingerprint,proto3" json:"system_fingerprint,omitempty"`
	Object            string                        `protobuf:"bytes,6,opt,name=object,proto3" json:"object,omitempty"`
	Usage             *Usage                        `protobuf:"bytes,7,opt,name=usage,proto3" json:"usage,omitempty"`
	// contains filtered or unexported fields
}

func (*ChatCompletionChunk) Descriptor deprecated

func (*ChatCompletionChunk) Descriptor() ([]byte, []int)

Deprecated: Use ChatCompletionChunk.ProtoReflect.Descriptor instead.

func (*ChatCompletionChunk) GetChoices

func (*ChatCompletionChunk) GetCreated

func (x *ChatCompletionChunk) GetCreated() int32

func (*ChatCompletionChunk) GetId

func (x *ChatCompletionChunk) GetId() string

func (*ChatCompletionChunk) GetModel

func (x *ChatCompletionChunk) GetModel() string

func (*ChatCompletionChunk) GetObject

func (x *ChatCompletionChunk) GetObject() string

func (*ChatCompletionChunk) GetSystemFingerprint

func (x *ChatCompletionChunk) GetSystemFingerprint() string

func (*ChatCompletionChunk) GetUsage

func (x *ChatCompletionChunk) GetUsage() *Usage

func (*ChatCompletionChunk) ProtoMessage

func (*ChatCompletionChunk) ProtoMessage()

func (*ChatCompletionChunk) ProtoReflect

func (x *ChatCompletionChunk) ProtoReflect() protoreflect.Message

func (*ChatCompletionChunk) Reset

func (x *ChatCompletionChunk) Reset()

func (*ChatCompletionChunk) String

func (x *ChatCompletionChunk) String() string

type ChatCompletionChunk_Choice

type ChatCompletionChunk_Choice struct {
	Delta        *ChatCompletionChunk_Choice_Delta `protobuf:"bytes,1,opt,name=delta,proto3" json:"delta,omitempty"`
	FinishReason string                            `protobuf:"bytes,2,opt,name=finish_reason,json=finishReason,proto3" json:"finish_reason,omitempty"`
	Index        int32                             `protobuf:"varint,3,opt,name=index,proto3" json:"index,omitempty"`
	Logprobs     *Logprobs                         `protobuf:"bytes,4,opt,name=logprobs,proto3" json:"logprobs,omitempty"`
	// contains filtered or unexported fields
}

func (*ChatCompletionChunk_Choice) Descriptor deprecated

func (*ChatCompletionChunk_Choice) Descriptor() ([]byte, []int)

Deprecated: Use ChatCompletionChunk_Choice.ProtoReflect.Descriptor instead.

func (*ChatCompletionChunk_Choice) GetDelta

func (*ChatCompletionChunk_Choice) GetFinishReason

func (x *ChatCompletionChunk_Choice) GetFinishReason() string

func (*ChatCompletionChunk_Choice) GetIndex

func (x *ChatCompletionChunk_Choice) GetIndex() int32

func (*ChatCompletionChunk_Choice) GetLogprobs

func (x *ChatCompletionChunk_Choice) GetLogprobs() *Logprobs

func (*ChatCompletionChunk_Choice) ProtoMessage

func (*ChatCompletionChunk_Choice) ProtoMessage()

func (*ChatCompletionChunk_Choice) ProtoReflect

func (*ChatCompletionChunk_Choice) Reset

func (x *ChatCompletionChunk_Choice) Reset()

func (*ChatCompletionChunk_Choice) String

func (x *ChatCompletionChunk_Choice) String() string

type ChatCompletionChunk_Choice_Delta

type ChatCompletionChunk_Choice_Delta struct {
	Content   string                                       `protobuf:"bytes,1,opt,name=content,proto3" json:"content,omitempty"`
	ToolCalls []*ChatCompletionChunk_Choice_Delta_ToolCall `protobuf:"bytes,2,rep,name=tool_calls,json=toolCalls,proto3" json:"tool_calls,omitempty"`
	Role      string                                       `protobuf:"bytes,3,opt,name=role,proto3" json:"role,omitempty"`
	// contains filtered or unexported fields
}

func (*ChatCompletionChunk_Choice_Delta) Descriptor deprecated

func (*ChatCompletionChunk_Choice_Delta) Descriptor() ([]byte, []int)

Deprecated: Use ChatCompletionChunk_Choice_Delta.ProtoReflect.Descriptor instead.

func (*ChatCompletionChunk_Choice_Delta) GetContent

func (x *ChatCompletionChunk_Choice_Delta) GetContent() string

func (*ChatCompletionChunk_Choice_Delta) GetRole

func (*ChatCompletionChunk_Choice_Delta) GetToolCalls

func (*ChatCompletionChunk_Choice_Delta) ProtoMessage

func (*ChatCompletionChunk_Choice_Delta) ProtoMessage()

func (*ChatCompletionChunk_Choice_Delta) ProtoReflect

func (*ChatCompletionChunk_Choice_Delta) Reset

func (*ChatCompletionChunk_Choice_Delta) String

type ChatCompletionChunk_Choice_Delta_ToolCall

type ChatCompletionChunk_Choice_Delta_ToolCall struct {
	Id       string                                              `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	Type     string                                              `protobuf:"bytes,2,opt,name=type,proto3" json:"type,omitempty"`
	Function *ChatCompletionChunk_Choice_Delta_ToolCall_Function `protobuf:"bytes,3,opt,name=function,proto3" json:"function,omitempty"`
	// contains filtered or unexported fields
}

func (*ChatCompletionChunk_Choice_Delta_ToolCall) Descriptor deprecated

func (*ChatCompletionChunk_Choice_Delta_ToolCall) Descriptor() ([]byte, []int)

Deprecated: Use ChatCompletionChunk_Choice_Delta_ToolCall.ProtoReflect.Descriptor instead.

func (*ChatCompletionChunk_Choice_Delta_ToolCall) GetFunction

func (*ChatCompletionChunk_Choice_Delta_ToolCall) GetId

func (*ChatCompletionChunk_Choice_Delta_ToolCall) GetType

func (*ChatCompletionChunk_Choice_Delta_ToolCall) ProtoMessage

func (*ChatCompletionChunk_Choice_Delta_ToolCall) ProtoReflect

func (*ChatCompletionChunk_Choice_Delta_ToolCall) Reset

func (*ChatCompletionChunk_Choice_Delta_ToolCall) String

type ChatCompletionChunk_Choice_Delta_ToolCall_Function

type ChatCompletionChunk_Choice_Delta_ToolCall_Function struct {
	Name      string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	Arguments string `protobuf:"bytes,2,opt,name=arguments,proto3" json:"arguments,omitempty"`
	// contains filtered or unexported fields
}

func (*ChatCompletionChunk_Choice_Delta_ToolCall_Function) Descriptor deprecated

Deprecated: Use ChatCompletionChunk_Choice_Delta_ToolCall_Function.ProtoReflect.Descriptor instead.

func (*ChatCompletionChunk_Choice_Delta_ToolCall_Function) GetArguments

func (*ChatCompletionChunk_Choice_Delta_ToolCall_Function) GetName

func (*ChatCompletionChunk_Choice_Delta_ToolCall_Function) ProtoMessage

func (*ChatCompletionChunk_Choice_Delta_ToolCall_Function) ProtoReflect

func (*ChatCompletionChunk_Choice_Delta_ToolCall_Function) Reset

func (*ChatCompletionChunk_Choice_Delta_ToolCall_Function) String

type ChatCompletion_Choice

type ChatCompletion_Choice struct {
	FinishReason string                         `protobuf:"bytes,1,opt,name=finish_reason,json=finishReason,proto3" json:"finish_reason,omitempty"`
	Index        int32                          `protobuf:"varint,2,opt,name=index,proto3" json:"index,omitempty"`
	Message      *ChatCompletion_Choice_Message `protobuf:"bytes,3,opt,name=message,proto3" json:"message,omitempty"`
	Logprobs     *Logprobs                      `protobuf:"bytes,4,opt,name=logprobs,proto3" json:"logprobs,omitempty"`
	// contains filtered or unexported fields
}

func (*ChatCompletion_Choice) Descriptor deprecated

func (*ChatCompletion_Choice) Descriptor() ([]byte, []int)

Deprecated: Use ChatCompletion_Choice.ProtoReflect.Descriptor instead.

func (*ChatCompletion_Choice) GetFinishReason

func (x *ChatCompletion_Choice) GetFinishReason() string

func (*ChatCompletion_Choice) GetIndex

func (x *ChatCompletion_Choice) GetIndex() int32

func (*ChatCompletion_Choice) GetLogprobs

func (x *ChatCompletion_Choice) GetLogprobs() *Logprobs

func (*ChatCompletion_Choice) GetMessage

func (*ChatCompletion_Choice) ProtoMessage

func (*ChatCompletion_Choice) ProtoMessage()

func (*ChatCompletion_Choice) ProtoReflect

func (x *ChatCompletion_Choice) ProtoReflect() protoreflect.Message

func (*ChatCompletion_Choice) Reset

func (x *ChatCompletion_Choice) Reset()

func (*ChatCompletion_Choice) String

func (x *ChatCompletion_Choice) String() string

type ChatCompletion_Choice_Message

type ChatCompletion_Choice_Message struct {
	Content   string      `protobuf:"bytes,1,opt,name=content,proto3" json:"content,omitempty"`
	ToolCalls []*ToolCall `protobuf:"bytes,2,rep,name=tool_calls,json=toolCalls,proto3" json:"tool_calls,omitempty"`
	Role      string      `protobuf:"bytes,3,opt,name=role,proto3" json:"role,omitempty"`
	// contains filtered or unexported fields
}

func (*ChatCompletion_Choice_Message) Descriptor deprecated

func (*ChatCompletion_Choice_Message) Descriptor() ([]byte, []int)

Deprecated: Use ChatCompletion_Choice_Message.ProtoReflect.Descriptor instead.

func (*ChatCompletion_Choice_Message) GetContent

func (x *ChatCompletion_Choice_Message) GetContent() string

func (*ChatCompletion_Choice_Message) GetRole

func (*ChatCompletion_Choice_Message) GetToolCalls

func (x *ChatCompletion_Choice_Message) GetToolCalls() []*ToolCall

func (*ChatCompletion_Choice_Message) ProtoMessage

func (*ChatCompletion_Choice_Message) ProtoMessage()

func (*ChatCompletion_Choice_Message) ProtoReflect

func (*ChatCompletion_Choice_Message) Reset

func (x *ChatCompletion_Choice_Message) Reset()

func (*ChatCompletion_Choice_Message) String

type ChatServiceClient

type ChatServiceClient interface {
}

ChatServiceClient is the client API for ChatService service.

For semantics around ctx use and closing/ending streaming RPCs, please refer to https://pkg.go.dev/google.golang.org/grpc/?tab=doc#ClientConn.NewStream.

type ChatServiceServer

type ChatServiceServer interface {
	// contains filtered or unexported methods
}

ChatServiceServer is the server API for ChatService service. All implementations must embed UnimplementedChatServiceServer for forward compatibility

type ClusterStatus added in v1.15.0

type ClusterStatus struct {
	Id   string `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	Name string `protobuf:"bytes,2,opt,name=name,proto3" json:"name,omitempty"`
	// TODO(kenji): Revisit. Each engine in the same cluster reports the same information on models.
	// It might be better to just report the model information.
	EngineStatuses      []*EngineStatus `protobuf:"bytes,3,rep,name=engine_statuses,json=engineStatuses,proto3" json:"engine_statuses,omitempty"`
	ModelCount          int32           `protobuf:"varint,4,opt,name=model_count,json=modelCount,proto3" json:"model_count,omitempty"`
	InProgressTaskCount int32           `protobuf:"varint,5,opt,name=in_progress_task_count,json=inProgressTaskCount,proto3" json:"in_progress_task_count,omitempty"`
	GpuAllocated        int32           `protobuf:"varint,6,opt,name=gpu_allocated,json=gpuAllocated,proto3" json:"gpu_allocated,omitempty"`
	// contains filtered or unexported fields
}

func (*ClusterStatus) Descriptor deprecated added in v1.15.0

func (*ClusterStatus) Descriptor() ([]byte, []int)

Deprecated: Use ClusterStatus.ProtoReflect.Descriptor instead.

func (*ClusterStatus) GetEngineStatuses added in v1.15.0

func (x *ClusterStatus) GetEngineStatuses() []*EngineStatus

func (*ClusterStatus) GetGpuAllocated added in v1.16.0

func (x *ClusterStatus) GetGpuAllocated() int32

func (*ClusterStatus) GetId added in v1.15.0

func (x *ClusterStatus) GetId() string

func (*ClusterStatus) GetInProgressTaskCount added in v1.16.0

func (x *ClusterStatus) GetInProgressTaskCount() int32

func (*ClusterStatus) GetModelCount added in v1.16.0

func (x *ClusterStatus) GetModelCount() int32

func (*ClusterStatus) GetName added in v1.15.0

func (x *ClusterStatus) GetName() string

func (*ClusterStatus) ProtoMessage added in v1.15.0

func (*ClusterStatus) ProtoMessage()

func (*ClusterStatus) ProtoReflect added in v1.15.0

func (x *ClusterStatus) ProtoReflect() protoreflect.Message

func (*ClusterStatus) Reset added in v1.15.0

func (x *ClusterStatus) Reset()

func (*ClusterStatus) String added in v1.15.0

func (x *ClusterStatus) String() string

type Completion

type Completion struct {
	Id                string               `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	Choices           []*Completion_Choice `protobuf:"bytes,2,rep,name=choices,proto3" json:"choices,omitempty"`
	Created           int32                `protobuf:"varint,3,opt,name=created,proto3" json:"created,omitempty"`
	Model             string               `protobuf:"bytes,4,opt,name=model,proto3" json:"model,omitempty"`
	SystemFingerprint string               `protobuf:"bytes,5,opt,name=system_fingerprint,json=systemFingerprint,proto3" json:"system_fingerprint,omitempty"`
	Object            string               `protobuf:"bytes,6,opt,name=object,proto3" json:"object,omitempty"`
	Usage             *Usage               `protobuf:"bytes,7,opt,name=usage,proto3" json:"usage,omitempty"`
	// contains filtered or unexported fields
}

func (*Completion) Descriptor deprecated

func (*Completion) Descriptor() ([]byte, []int)

Deprecated: Use Completion.ProtoReflect.Descriptor instead.

func (*Completion) GetChoices

func (x *Completion) GetChoices() []*Completion_Choice

func (*Completion) GetCreated

func (x *Completion) GetCreated() int32

func (*Completion) GetId

func (x *Completion) GetId() string

func (*Completion) GetModel

func (x *Completion) GetModel() string

func (*Completion) GetObject

func (x *Completion) GetObject() string

func (*Completion) GetSystemFingerprint

func (x *Completion) GetSystemFingerprint() string

func (*Completion) GetUsage

func (x *Completion) GetUsage() *Usage

func (*Completion) ProtoMessage

func (*Completion) ProtoMessage()

func (*Completion) ProtoReflect

func (x *Completion) ProtoReflect() protoreflect.Message

func (*Completion) Reset

func (x *Completion) Reset()

func (*Completion) String

func (x *Completion) String() string

type Completion_Choice

type Completion_Choice struct {
	FinishReason string                      `protobuf:"bytes,1,opt,name=finish_reason,json=finishReason,proto3" json:"finish_reason,omitempty"`
	Index        int32                       `protobuf:"varint,2,opt,name=index,proto3" json:"index,omitempty"`
	Logprobs     *Completion_Choice_Logprobs `protobuf:"bytes,3,opt,name=logprobs,proto3" json:"logprobs,omitempty"`
	Text         string                      `protobuf:"bytes,4,opt,name=text,proto3" json:"text,omitempty"`
	// contains filtered or unexported fields
}

func (*Completion_Choice) Descriptor deprecated

func (*Completion_Choice) Descriptor() ([]byte, []int)

Deprecated: Use Completion_Choice.ProtoReflect.Descriptor instead.

func (*Completion_Choice) GetFinishReason

func (x *Completion_Choice) GetFinishReason() string

func (*Completion_Choice) GetIndex

func (x *Completion_Choice) GetIndex() int32

func (*Completion_Choice) GetLogprobs

func (*Completion_Choice) GetText

func (x *Completion_Choice) GetText() string

func (*Completion_Choice) ProtoMessage

func (*Completion_Choice) ProtoMessage()

func (*Completion_Choice) ProtoReflect

func (x *Completion_Choice) ProtoReflect() protoreflect.Message

func (*Completion_Choice) Reset

func (x *Completion_Choice) Reset()

func (*Completion_Choice) String

func (x *Completion_Choice) String() string

type Completion_Choice_Logprobs

type Completion_Choice_Logprobs struct {

	// TODO: Revisit this. The types of the fields are not clearly specified in the spec.
	TextOffset    int32   `protobuf:"varint,1,opt,name=text_offset,json=textOffset,proto3" json:"text_offset,omitempty"`
	TokenLogprobs float64 `protobuf:"fixed64,2,opt,name=token_logprobs,json=tokenLogprobs,proto3" json:"token_logprobs,omitempty"`
	Tokens        string  `protobuf:"bytes,3,opt,name=tokens,proto3" json:"tokens,omitempty"`
	TopLogprobs   float64 `protobuf:"fixed64,4,opt,name=top_logprobs,json=topLogprobs,proto3" json:"top_logprobs,omitempty"`
	// contains filtered or unexported fields
}

func (*Completion_Choice_Logprobs) Descriptor deprecated

func (*Completion_Choice_Logprobs) Descriptor() ([]byte, []int)

Deprecated: Use Completion_Choice_Logprobs.ProtoReflect.Descriptor instead.

func (*Completion_Choice_Logprobs) GetTextOffset

func (x *Completion_Choice_Logprobs) GetTextOffset() int32

func (*Completion_Choice_Logprobs) GetTokenLogprobs

func (x *Completion_Choice_Logprobs) GetTokenLogprobs() float64

func (*Completion_Choice_Logprobs) GetTokens

func (x *Completion_Choice_Logprobs) GetTokens() string

func (*Completion_Choice_Logprobs) GetTopLogprobs

func (x *Completion_Choice_Logprobs) GetTopLogprobs() float64

func (*Completion_Choice_Logprobs) ProtoMessage

func (*Completion_Choice_Logprobs) ProtoMessage()

func (*Completion_Choice_Logprobs) ProtoReflect

func (*Completion_Choice_Logprobs) Reset

func (x *Completion_Choice_Logprobs) Reset()

func (*Completion_Choice_Logprobs) String

func (x *Completion_Choice_Logprobs) String() string

type CreateChatCompletionRequest

type CreateChatCompletionRequest struct {

	// TODO(kenji): Revisit this.
	Messages         []*CreateChatCompletionRequest_Message `protobuf:"bytes,1,rep,name=messages,proto3" json:"messages,omitempty"`
	Model            string                                 `protobuf:"bytes,2,opt,name=model,proto3" json:"model,omitempty"`
	FrequencyPenalty float64                                `protobuf:"fixed64,3,opt,name=frequency_penalty,json=frequencyPenalty,proto3" json:"frequency_penalty,omitempty"`
	LogitBias        map[string]float64                     `` /* 178-byte string literal not displayed */
	Logprobs         bool                                   `protobuf:"varint,5,opt,name=logprobs,proto3" json:"logprobs,omitempty"`
	TopLogprobs      int32                                  `protobuf:"varint,6,opt,name=top_logprobs,json=topLogprobs,proto3" json:"top_logprobs,omitempty"`
	// MaxTokens
	// Deprecated: This value is now deprecated in favor of MaxCompletionTokens
	MaxTokens       int32                                       `protobuf:"varint,7,opt,name=max_tokens,json=maxTokens,proto3" json:"max_tokens,omitempty"`
	N               int32                                       `protobuf:"varint,8,opt,name=n,proto3" json:"n,omitempty"`
	PresencePenalty float64                                     `protobuf:"fixed64,9,opt,name=presence_penalty,json=presencePenalty,proto3" json:"presence_penalty,omitempty"`
	ResponseFormat  *CreateChatCompletionRequest_ResponseFormat `protobuf:"bytes,10,opt,name=response_format,json=responseFormat,proto3" json:"response_format,omitempty"`
	Seed            int32                                       `protobuf:"varint,11,opt,name=seed,proto3" json:"seed,omitempty"`
	// string / arrary/ null
	Stop          []string                                   `protobuf:"bytes,12,rep,name=stop,proto3" json:"stop,omitempty"`
	Stream        bool                                       `protobuf:"varint,13,opt,name=stream,proto3" json:"stream,omitempty"`
	StreamOptions *CreateChatCompletionRequest_StreamOptions `protobuf:"bytes,19,opt,name=stream_options,json=streamOptions,proto3" json:"stream_options,omitempty"`
	Temperature   float64                                    `protobuf:"fixed64,14,opt,name=temperature,proto3" json:"temperature,omitempty"`
	TopP          float64                                    `protobuf:"fixed64,15,opt,name=top_p,json=topP,proto3" json:"top_p,omitempty"`
	Tools         []*CreateChatCompletionRequest_Tool        `protobuf:"bytes,16,rep,name=tools,proto3" json:"tools,omitempty"`
	// The type of the "tool_choice" field is a string or an object.
	// As we cannot have a string or an object in the proto, we use the "tool_choice_obj"
	// if a request sets the "tool_choice" field as an object.
	//
	// The "tool_choice_object" field is converted to the "tool_choice" field when the request is being
	// sent to an inference runtime.
	ToolChoice       string                                  `protobuf:"bytes,17,opt,name=tool_choice,json=toolChoice,proto3" json:"tool_choice,omitempty"`
	ToolChoiceObject *CreateChatCompletionRequest_ToolChoice `protobuf:"bytes,20,opt,name=tool_choice_object,json=toolChoiceObject,proto3" json:"tool_choice_object,omitempty"`
	User             string                                  `protobuf:"bytes,18,opt,name=user,proto3" json:"user,omitempty"`
	// MaxCompletionTokens specifies the maximum limit on the number of tokens that can be generated during a completion.`
	MaxCompletionTokens int32 `protobuf:"varint,21,opt,name=max_completion_tokens,json=maxCompletionTokens,proto3" json:"max_completion_tokens,omitempty"`
	// encoded_chat_template_kwargs is encoded value of "chat_template_kwargs". This is a special parameter
	// that only vLLM uses.
	//
	// The field is converted to the "chat_template_kwargs" field when the request is being
	// sent to vLLM.
	//
	// https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#id7
	EncodedChatTemplateKwargs string `` /* 141-byte string literal not displayed */
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest) Descriptor deprecated

func (*CreateChatCompletionRequest) Descriptor() ([]byte, []int)

Deprecated: Use CreateChatCompletionRequest.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest) GetEncodedChatTemplateKwargs added in v1.27.0

func (x *CreateChatCompletionRequest) GetEncodedChatTemplateKwargs() string

func (*CreateChatCompletionRequest) GetFrequencyPenalty

func (x *CreateChatCompletionRequest) GetFrequencyPenalty() float64

func (*CreateChatCompletionRequest) GetLogitBias

func (x *CreateChatCompletionRequest) GetLogitBias() map[string]float64

func (*CreateChatCompletionRequest) GetLogprobs

func (x *CreateChatCompletionRequest) GetLogprobs() bool

func (*CreateChatCompletionRequest) GetMaxCompletionTokens added in v1.15.0

func (x *CreateChatCompletionRequest) GetMaxCompletionTokens() int32

func (*CreateChatCompletionRequest) GetMaxTokens

func (x *CreateChatCompletionRequest) GetMaxTokens() int32

func (*CreateChatCompletionRequest) GetMessages

func (*CreateChatCompletionRequest) GetModel

func (x *CreateChatCompletionRequest) GetModel() string

func (*CreateChatCompletionRequest) GetN

func (*CreateChatCompletionRequest) GetPresencePenalty

func (x *CreateChatCompletionRequest) GetPresencePenalty() float64

func (*CreateChatCompletionRequest) GetResponseFormat

func (*CreateChatCompletionRequest) GetSeed

func (x *CreateChatCompletionRequest) GetSeed() int32

func (*CreateChatCompletionRequest) GetStop

func (x *CreateChatCompletionRequest) GetStop() []string

func (*CreateChatCompletionRequest) GetStream

func (x *CreateChatCompletionRequest) GetStream() bool

func (*CreateChatCompletionRequest) GetStreamOptions added in v0.368.0

func (*CreateChatCompletionRequest) GetTemperature

func (x *CreateChatCompletionRequest) GetTemperature() float64

func (*CreateChatCompletionRequest) GetToolChoice

func (x *CreateChatCompletionRequest) GetToolChoice() string

func (*CreateChatCompletionRequest) GetToolChoiceObject added in v1.14.0

func (*CreateChatCompletionRequest) GetTools

func (*CreateChatCompletionRequest) GetTopLogprobs

func (x *CreateChatCompletionRequest) GetTopLogprobs() int32

func (*CreateChatCompletionRequest) GetTopP

func (x *CreateChatCompletionRequest) GetTopP() float64

func (*CreateChatCompletionRequest) GetUser

func (x *CreateChatCompletionRequest) GetUser() string

func (*CreateChatCompletionRequest) ProtoMessage

func (*CreateChatCompletionRequest) ProtoMessage()

func (*CreateChatCompletionRequest) ProtoReflect

func (*CreateChatCompletionRequest) Reset

func (x *CreateChatCompletionRequest) Reset()

func (*CreateChatCompletionRequest) String

func (x *CreateChatCompletionRequest) String() string

type CreateChatCompletionRequest_Message

type CreateChatCompletionRequest_Message struct {

	// The type of the content is either string or array in the OpenAI API spec, but
	// we only support the array type here. When a client sends a string, it is converted before
	// the request is being unmarshalled.
	Content   []*CreateChatCompletionRequest_Message_Content  `protobuf:"bytes,5,rep,name=content,proto3" json:"content,omitempty"`
	Role      string                                          `protobuf:"bytes,2,opt,name=role,proto3" json:"role,omitempty"`
	Name      string                                          `protobuf:"bytes,3,opt,name=name,proto3" json:"name,omitempty"`
	ToolCalls []*CreateChatCompletionRequest_Message_ToolCall `protobuf:"bytes,4,rep,name=tool_calls,json=toolCalls,proto3" json:"tool_calls,omitempty"`
	// Used by the "Tool message".
	ToolCallId string `protobuf:"bytes,6,opt,name=tool_call_id,json=toolCallId,proto3" json:"tool_call_id,omitempty"`
	// contains filtered or unexported fields
}

Message has fields for system message, user message, assistant message, and tool message.

func (*CreateChatCompletionRequest_Message) Descriptor deprecated

func (*CreateChatCompletionRequest_Message) Descriptor() ([]byte, []int)

Deprecated: Use CreateChatCompletionRequest_Message.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_Message) GetContent

func (*CreateChatCompletionRequest_Message) GetName

func (*CreateChatCompletionRequest_Message) GetRole

func (*CreateChatCompletionRequest_Message) GetToolCallId added in v1.14.1

func (x *CreateChatCompletionRequest_Message) GetToolCallId() string

func (*CreateChatCompletionRequest_Message) GetToolCalls

func (*CreateChatCompletionRequest_Message) ProtoMessage

func (*CreateChatCompletionRequest_Message) ProtoMessage()

func (*CreateChatCompletionRequest_Message) ProtoReflect

func (*CreateChatCompletionRequest_Message) Reset

func (*CreateChatCompletionRequest_Message) String

type CreateChatCompletionRequest_Message_Content added in v1.5.0

type CreateChatCompletionRequest_Message_Content struct {
	Type       string                                                  `protobuf:"bytes,1,opt,name=type,proto3" json:"type,omitempty"`
	Text       string                                                  `protobuf:"bytes,2,opt,name=text,proto3" json:"text,omitempty"`
	ImageUrl   *CreateChatCompletionRequest_Message_Content_ImageUrl   `protobuf:"bytes,3,opt,name=image_url,json=imageUrl,proto3" json:"image_url,omitempty"`
	InputAudio *CreateChatCompletionRequest_Message_Content_InputAudio `protobuf:"bytes,4,opt,name=input_audio,json=inputAudio,proto3" json:"input_audio,omitempty"`
	AudioUrl   *CreateChatCompletionRequest_Message_Content_AudioUrl   `protobuf:"bytes,5,opt,name=audio_url,json=audioUrl,proto3" json:"audio_url,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest_Message_Content) Descriptor deprecated added in v1.5.0

Deprecated: Use CreateChatCompletionRequest_Message_Content.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_Message_Content) GetAudioUrl added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content) GetImageUrl added in v1.5.0

func (*CreateChatCompletionRequest_Message_Content) GetInputAudio added in v1.5.0

func (*CreateChatCompletionRequest_Message_Content) GetText added in v1.5.0

func (*CreateChatCompletionRequest_Message_Content) GetType added in v1.5.0

func (*CreateChatCompletionRequest_Message_Content) ProtoMessage added in v1.5.0

func (*CreateChatCompletionRequest_Message_Content) ProtoReflect added in v1.5.0

func (*CreateChatCompletionRequest_Message_Content) Reset added in v1.5.0

func (*CreateChatCompletionRequest_Message_Content) String added in v1.5.0

type CreateChatCompletionRequest_Message_Content_AudioUrl added in v1.9.0

type CreateChatCompletionRequest_Message_Content_AudioUrl struct {
	Url string `protobuf:"bytes,1,opt,name=url,proto3" json:"url,omitempty"`
	// contains filtered or unexported fields
}

AudioUrl is non-openai compatible. It is used by vLLM to handle audio input.

func (*CreateChatCompletionRequest_Message_Content_AudioUrl) Descriptor deprecated added in v1.9.0

Deprecated: Use CreateChatCompletionRequest_Message_Content_AudioUrl.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_Message_Content_AudioUrl) GetUrl added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_AudioUrl) ProtoMessage added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_AudioUrl) ProtoReflect added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_AudioUrl) Reset added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_AudioUrl) String added in v1.9.0

type CreateChatCompletionRequest_Message_Content_ImageUrl added in v1.9.0

type CreateChatCompletionRequest_Message_Content_ImageUrl struct {
	Url    string `protobuf:"bytes,1,opt,name=url,proto3" json:"url,omitempty"`
	Detail string `protobuf:"bytes,2,opt,name=detail,proto3" json:"detail,omitempty"`
	// contains filtered or unexported fields
}

Refer to https://platform.openai.com/docs/api-reference/chat/create#chat-create-messages

func (*CreateChatCompletionRequest_Message_Content_ImageUrl) Descriptor deprecated added in v1.9.0

Deprecated: Use CreateChatCompletionRequest_Message_Content_ImageUrl.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_Message_Content_ImageUrl) GetDetail added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_ImageUrl) GetUrl added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_ImageUrl) ProtoMessage added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_ImageUrl) ProtoReflect added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_ImageUrl) Reset added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_ImageUrl) String added in v1.9.0

type CreateChatCompletionRequest_Message_Content_InputAudio added in v1.9.0

type CreateChatCompletionRequest_Message_Content_InputAudio struct {
	Data   string `protobuf:"bytes,1,opt,name=data,proto3" json:"data,omitempty"`
	Format string `protobuf:"bytes,2,opt,name=format,proto3" json:"format,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest_Message_Content_InputAudio) Descriptor deprecated added in v1.9.0

Deprecated: Use CreateChatCompletionRequest_Message_Content_InputAudio.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_Message_Content_InputAudio) GetData added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_InputAudio) GetFormat added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_InputAudio) ProtoMessage added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_InputAudio) ProtoReflect added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_InputAudio) Reset added in v1.9.0

func (*CreateChatCompletionRequest_Message_Content_InputAudio) String added in v1.9.0

type CreateChatCompletionRequest_Message_ToolCall

type CreateChatCompletionRequest_Message_ToolCall struct {
	Id       string                                                 `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	Type     string                                                 `protobuf:"bytes,2,opt,name=type,proto3" json:"type,omitempty"`
	Function *CreateChatCompletionRequest_Message_ToolCall_Function `protobuf:"bytes,3,opt,name=function,proto3" json:"function,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest_Message_ToolCall) Descriptor deprecated

Deprecated: Use CreateChatCompletionRequest_Message_ToolCall.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_Message_ToolCall) GetFunction

func (*CreateChatCompletionRequest_Message_ToolCall) GetId

func (*CreateChatCompletionRequest_Message_ToolCall) GetType

func (*CreateChatCompletionRequest_Message_ToolCall) ProtoMessage

func (*CreateChatCompletionRequest_Message_ToolCall) ProtoReflect

func (*CreateChatCompletionRequest_Message_ToolCall) Reset

func (*CreateChatCompletionRequest_Message_ToolCall) String

type CreateChatCompletionRequest_Message_ToolCall_Function

type CreateChatCompletionRequest_Message_ToolCall_Function struct {
	Name      string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	Arguments string `protobuf:"bytes,2,opt,name=arguments,proto3" json:"arguments,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest_Message_ToolCall_Function) Descriptor deprecated

Deprecated: Use CreateChatCompletionRequest_Message_ToolCall_Function.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_Message_ToolCall_Function) GetArguments

func (*CreateChatCompletionRequest_Message_ToolCall_Function) GetName

func (*CreateChatCompletionRequest_Message_ToolCall_Function) ProtoMessage

func (*CreateChatCompletionRequest_Message_ToolCall_Function) ProtoReflect

func (*CreateChatCompletionRequest_Message_ToolCall_Function) Reset

func (*CreateChatCompletionRequest_Message_ToolCall_Function) String

type CreateChatCompletionRequest_ResponseFormat

type CreateChatCompletionRequest_ResponseFormat struct {
	Type string `protobuf:"bytes,1,opt,name=type,proto3" json:"type,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest_ResponseFormat) Descriptor deprecated

Deprecated: Use CreateChatCompletionRequest_ResponseFormat.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_ResponseFormat) GetType

func (*CreateChatCompletionRequest_ResponseFormat) ProtoMessage

func (*CreateChatCompletionRequest_ResponseFormat) ProtoReflect

func (*CreateChatCompletionRequest_ResponseFormat) Reset

func (*CreateChatCompletionRequest_ResponseFormat) String

type CreateChatCompletionRequest_StreamOptions added in v0.368.0

type CreateChatCompletionRequest_StreamOptions struct {
	IncludeUsage bool `protobuf:"varint,1,opt,name=include_usage,json=includeUsage,proto3" json:"include_usage,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest_StreamOptions) Descriptor deprecated added in v0.368.0

func (*CreateChatCompletionRequest_StreamOptions) Descriptor() ([]byte, []int)

Deprecated: Use CreateChatCompletionRequest_StreamOptions.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_StreamOptions) GetIncludeUsage added in v0.368.0

func (x *CreateChatCompletionRequest_StreamOptions) GetIncludeUsage() bool

func (*CreateChatCompletionRequest_StreamOptions) ProtoMessage added in v0.368.0

func (*CreateChatCompletionRequest_StreamOptions) ProtoReflect added in v0.368.0

func (*CreateChatCompletionRequest_StreamOptions) Reset added in v0.368.0

func (*CreateChatCompletionRequest_StreamOptions) String added in v0.368.0

type CreateChatCompletionRequest_Tool

type CreateChatCompletionRequest_Tool struct {
	Type     string                                     `protobuf:"bytes,1,opt,name=type,proto3" json:"type,omitempty"`
	Function *CreateChatCompletionRequest_Tool_Function `protobuf:"bytes,2,opt,name=function,proto3" json:"function,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest_Tool) Descriptor deprecated

func (*CreateChatCompletionRequest_Tool) Descriptor() ([]byte, []int)

Deprecated: Use CreateChatCompletionRequest_Tool.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_Tool) GetFunction

func (*CreateChatCompletionRequest_Tool) GetType

func (*CreateChatCompletionRequest_Tool) ProtoMessage

func (*CreateChatCompletionRequest_Tool) ProtoMessage()

func (*CreateChatCompletionRequest_Tool) ProtoReflect

func (*CreateChatCompletionRequest_Tool) Reset

func (*CreateChatCompletionRequest_Tool) String

type CreateChatCompletionRequest_ToolChoice

type CreateChatCompletionRequest_ToolChoice struct {
	Type     string                                           `protobuf:"bytes,2,opt,name=type,proto3" json:"type,omitempty"`
	Function *CreateChatCompletionRequest_ToolChoice_Function `protobuf:"bytes,3,opt,name=function,proto3" json:"function,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest_ToolChoice) Descriptor deprecated

func (*CreateChatCompletionRequest_ToolChoice) Descriptor() ([]byte, []int)

Deprecated: Use CreateChatCompletionRequest_ToolChoice.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_ToolChoice) GetFunction

func (*CreateChatCompletionRequest_ToolChoice) GetType

func (*CreateChatCompletionRequest_ToolChoice) ProtoMessage

func (*CreateChatCompletionRequest_ToolChoice) ProtoReflect

func (*CreateChatCompletionRequest_ToolChoice) Reset

func (*CreateChatCompletionRequest_ToolChoice) String

type CreateChatCompletionRequest_ToolChoice_Function

type CreateChatCompletionRequest_ToolChoice_Function struct {
	Name string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest_ToolChoice_Function) Descriptor deprecated

Deprecated: Use CreateChatCompletionRequest_ToolChoice_Function.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_ToolChoice_Function) GetName

func (*CreateChatCompletionRequest_ToolChoice_Function) ProtoMessage

func (*CreateChatCompletionRequest_ToolChoice_Function) ProtoReflect

func (*CreateChatCompletionRequest_ToolChoice_Function) Reset

func (*CreateChatCompletionRequest_ToolChoice_Function) String

type CreateChatCompletionRequest_Tool_Function

type CreateChatCompletionRequest_Tool_Function struct {
	Description string `protobuf:"bytes,1,opt,name=description,proto3" json:"description,omitempty"`
	Name        string `protobuf:"bytes,2,opt,name=name,proto3" json:"name,omitempty"`
	// OpenAI API has the "parameters" field that stores a JSON Schema object.
	// As we cannot have a JSON Schema object in the proto, we encode the JSON Schema object
	// with base64 and store it before unmarshalling it in the server.
	//
	// The field is converted to the "parameters" field when the request is being
	// sent to an inference runtime.
	EncodedParameters string `protobuf:"bytes,3,opt,name=encoded_parameters,json=encodedParameters,proto3" json:"encoded_parameters,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateChatCompletionRequest_Tool_Function) Descriptor deprecated

func (*CreateChatCompletionRequest_Tool_Function) Descriptor() ([]byte, []int)

Deprecated: Use CreateChatCompletionRequest_Tool_Function.ProtoReflect.Descriptor instead.

func (*CreateChatCompletionRequest_Tool_Function) GetDescription

func (*CreateChatCompletionRequest_Tool_Function) GetEncodedParameters added in v1.14.0

func (x *CreateChatCompletionRequest_Tool_Function) GetEncodedParameters() string

func (*CreateChatCompletionRequest_Tool_Function) GetName

func (*CreateChatCompletionRequest_Tool_Function) ProtoMessage

func (*CreateChatCompletionRequest_Tool_Function) ProtoReflect

func (*CreateChatCompletionRequest_Tool_Function) Reset

func (*CreateChatCompletionRequest_Tool_Function) String

type CreateCompletionRequest

type CreateCompletionRequest struct {
	Model string `protobuf:"bytes,1,opt,name=model,proto3" json:"model,omitempty"`
	// This can be a string or an array of strings, but we use string assuming that it is more common.
	Prompt           string                                `protobuf:"bytes,2,opt,name=prompt,proto3" json:"prompt,omitempty"`
	BestOf           int32                                 `protobuf:"varint,3,opt,name=best_of,json=bestOf,proto3" json:"best_of,omitempty"`
	Echo             bool                                  `protobuf:"varint,4,opt,name=echo,proto3" json:"echo,omitempty"`
	FrequencyPenalty float64                               `protobuf:"fixed64,5,opt,name=frequency_penalty,json=frequencyPenalty,proto3" json:"frequency_penalty,omitempty"`
	LogitBias        map[string]float64                    `` /* 178-byte string literal not displayed */
	Logprobs         int32                                 `protobuf:"varint,7,opt,name=logprobs,proto3" json:"logprobs,omitempty"`
	MaxTokens        int32                                 `protobuf:"varint,8,opt,name=max_tokens,json=maxTokens,proto3" json:"max_tokens,omitempty"`
	N                int32                                 `protobuf:"varint,9,opt,name=n,proto3" json:"n,omitempty"`
	PresencePenalty  float64                               `protobuf:"fixed64,10,opt,name=presence_penalty,json=presencePenalty,proto3" json:"presence_penalty,omitempty"`
	Seed             int32                                 `protobuf:"varint,11,opt,name=seed,proto3" json:"seed,omitempty"`
	Stop             []string                              `protobuf:"bytes,12,rep,name=stop,proto3" json:"stop,omitempty"`
	Stream           bool                                  `protobuf:"varint,13,opt,name=stream,proto3" json:"stream,omitempty"`
	StreamOption     *CreateCompletionRequest_StreamOption `protobuf:"bytes,14,opt,name=stream_option,json=streamOption,proto3" json:"stream_option,omitempty"`
	Suffix           string                                `protobuf:"bytes,15,opt,name=suffix,proto3" json:"suffix,omitempty"`
	Temperature      float64                               `protobuf:"fixed64,16,opt,name=temperature,proto3" json:"temperature,omitempty"`
	TopP             float64                               `protobuf:"fixed64,17,opt,name=top_p,json=topP,proto3" json:"top_p,omitempty"`
	User             string                                `protobuf:"bytes,18,opt,name=user,proto3" json:"user,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateCompletionRequest) Descriptor deprecated

func (*CreateCompletionRequest) Descriptor() ([]byte, []int)

Deprecated: Use CreateCompletionRequest.ProtoReflect.Descriptor instead.

func (*CreateCompletionRequest) GetBestOf

func (x *CreateCompletionRequest) GetBestOf() int32

func (*CreateCompletionRequest) GetEcho

func (x *CreateCompletionRequest) GetEcho() bool

func (*CreateCompletionRequest) GetFrequencyPenalty

func (x *CreateCompletionRequest) GetFrequencyPenalty() float64

func (*CreateCompletionRequest) GetLogitBias

func (x *CreateCompletionRequest) GetLogitBias() map[string]float64

func (*CreateCompletionRequest) GetLogprobs

func (x *CreateCompletionRequest) GetLogprobs() int32

func (*CreateCompletionRequest) GetMaxTokens

func (x *CreateCompletionRequest) GetMaxTokens() int32

func (*CreateCompletionRequest) GetModel

func (x *CreateCompletionRequest) GetModel() string

func (*CreateCompletionRequest) GetN

func (x *CreateCompletionRequest) GetN() int32

func (*CreateCompletionRequest) GetPresencePenalty

func (x *CreateCompletionRequest) GetPresencePenalty() float64

func (*CreateCompletionRequest) GetPrompt

func (x *CreateCompletionRequest) GetPrompt() string

func (*CreateCompletionRequest) GetSeed

func (x *CreateCompletionRequest) GetSeed() int32

func (*CreateCompletionRequest) GetStop

func (x *CreateCompletionRequest) GetStop() []string

func (*CreateCompletionRequest) GetStream

func (x *CreateCompletionRequest) GetStream() bool

func (*CreateCompletionRequest) GetStreamOption

func (*CreateCompletionRequest) GetSuffix

func (x *CreateCompletionRequest) GetSuffix() string

func (*CreateCompletionRequest) GetTemperature

func (x *CreateCompletionRequest) GetTemperature() float64

func (*CreateCompletionRequest) GetTopP

func (x *CreateCompletionRequest) GetTopP() float64

func (*CreateCompletionRequest) GetUser

func (x *CreateCompletionRequest) GetUser() string

func (*CreateCompletionRequest) ProtoMessage

func (*CreateCompletionRequest) ProtoMessage()

func (*CreateCompletionRequest) ProtoReflect

func (x *CreateCompletionRequest) ProtoReflect() protoreflect.Message

func (*CreateCompletionRequest) Reset

func (x *CreateCompletionRequest) Reset()

func (*CreateCompletionRequest) String

func (x *CreateCompletionRequest) String() string

type CreateCompletionRequest_StreamOption

type CreateCompletionRequest_StreamOption struct {
	IncludeUsage bool `protobuf:"varint,1,opt,name=include_usage,json=includeUsage,proto3" json:"include_usage,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateCompletionRequest_StreamOption) Descriptor deprecated

func (*CreateCompletionRequest_StreamOption) Descriptor() ([]byte, []int)

Deprecated: Use CreateCompletionRequest_StreamOption.ProtoReflect.Descriptor instead.

func (*CreateCompletionRequest_StreamOption) GetIncludeUsage

func (x *CreateCompletionRequest_StreamOption) GetIncludeUsage() bool

func (*CreateCompletionRequest_StreamOption) ProtoMessage

func (*CreateCompletionRequest_StreamOption) ProtoMessage()

func (*CreateCompletionRequest_StreamOption) ProtoReflect

func (*CreateCompletionRequest_StreamOption) Reset

func (*CreateCompletionRequest_StreamOption) String

type CreateEmbeddingRequest

type CreateEmbeddingRequest struct {

	// The "input" field can be a string, an array of strings, an array of integers, or an array of arrays of integers.
	// As that is not supported by proto, if the input is not a stryg, we move the value of the "input" field to "encoded_input"
	// and remove the field before unmarshalling.
	Input          string `protobuf:"bytes,1,opt,name=input,proto3" json:"input,omitempty"`
	EncodedInput   string `protobuf:"bytes,6,opt,name=encoded_input,json=encodedInput,proto3" json:"encoded_input,omitempty"`
	Model          string `protobuf:"bytes,2,opt,name=model,proto3" json:"model,omitempty"`
	EncodingFormat string `protobuf:"bytes,3,opt,name=encoding_format,json=encodingFormat,proto3" json:"encoding_format,omitempty"`
	Dimensions     int32  `protobuf:"varint,4,opt,name=dimensions,proto3" json:"dimensions,omitempty"`
	User           string `protobuf:"bytes,5,opt,name=user,proto3" json:"user,omitempty"`
	// contains filtered or unexported fields
}

func (*CreateEmbeddingRequest) Descriptor deprecated

func (*CreateEmbeddingRequest) Descriptor() ([]byte, []int)

Deprecated: Use CreateEmbeddingRequest.ProtoReflect.Descriptor instead.

func (*CreateEmbeddingRequest) GetDimensions

func (x *CreateEmbeddingRequest) GetDimensions() int32

func (*CreateEmbeddingRequest) GetEncodedInput added in v1.14.0

func (x *CreateEmbeddingRequest) GetEncodedInput() string

func (*CreateEmbeddingRequest) GetEncodingFormat

func (x *CreateEmbeddingRequest) GetEncodingFormat() string

func (*CreateEmbeddingRequest) GetInput

func (x *CreateEmbeddingRequest) GetInput() string

func (*CreateEmbeddingRequest) GetModel

func (x *CreateEmbeddingRequest) GetModel() string

func (*CreateEmbeddingRequest) GetUser

func (x *CreateEmbeddingRequest) GetUser() string

func (*CreateEmbeddingRequest) ProtoMessage

func (*CreateEmbeddingRequest) ProtoMessage()

func (*CreateEmbeddingRequest) ProtoReflect

func (x *CreateEmbeddingRequest) ProtoReflect() protoreflect.Message

func (*CreateEmbeddingRequest) Reset

func (x *CreateEmbeddingRequest) Reset()

func (*CreateEmbeddingRequest) String

func (x *CreateEmbeddingRequest) String() string

type DeactivateModelRequest added in v1.21.0

type DeactivateModelRequest struct {
	Id string `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	// contains filtered or unexported fields
}

func (*DeactivateModelRequest) Descriptor deprecated added in v1.21.0

func (*DeactivateModelRequest) Descriptor() ([]byte, []int)

Deprecated: Use DeactivateModelRequest.ProtoReflect.Descriptor instead.

func (*DeactivateModelRequest) GetId added in v1.21.0

func (x *DeactivateModelRequest) GetId() string

func (*DeactivateModelRequest) ProtoMessage added in v1.21.0

func (*DeactivateModelRequest) ProtoMessage()

func (*DeactivateModelRequest) ProtoReflect added in v1.21.0

func (x *DeactivateModelRequest) ProtoReflect() protoreflect.Message

func (*DeactivateModelRequest) Reset added in v1.21.0

func (x *DeactivateModelRequest) Reset()

func (*DeactivateModelRequest) String added in v1.21.0

func (x *DeactivateModelRequest) String() string

type DeactivateModelResponse added in v1.21.0

type DeactivateModelResponse struct {
	// contains filtered or unexported fields
}

func (*DeactivateModelResponse) Descriptor deprecated added in v1.21.0

func (*DeactivateModelResponse) Descriptor() ([]byte, []int)

Deprecated: Use DeactivateModelResponse.ProtoReflect.Descriptor instead.

func (*DeactivateModelResponse) ProtoMessage added in v1.21.0

func (*DeactivateModelResponse) ProtoMessage()

func (*DeactivateModelResponse) ProtoReflect added in v1.21.0

func (x *DeactivateModelResponse) ProtoReflect() protoreflect.Message

func (*DeactivateModelResponse) Reset added in v1.21.0

func (x *DeactivateModelResponse) Reset()

func (*DeactivateModelResponse) String added in v1.21.0

func (x *DeactivateModelResponse) String() string

type Embedding

type Embedding struct {
	Index     int32     `protobuf:"varint,1,opt,name=index,proto3" json:"index,omitempty"`
	Embedding []float64 `protobuf:"fixed64,2,rep,packed,name=embedding,proto3" json:"embedding,omitempty"`
	Object    string    `protobuf:"bytes,3,opt,name=object,proto3" json:"object,omitempty"`
	// contains filtered or unexported fields
}

func (*Embedding) Descriptor deprecated

func (*Embedding) Descriptor() ([]byte, []int)

Deprecated: Use Embedding.ProtoReflect.Descriptor instead.

func (*Embedding) GetEmbedding

func (x *Embedding) GetEmbedding() []float64

func (*Embedding) GetIndex

func (x *Embedding) GetIndex() int32

func (*Embedding) GetObject

func (x *Embedding) GetObject() string

func (*Embedding) ProtoMessage

func (*Embedding) ProtoMessage()

func (*Embedding) ProtoReflect

func (x *Embedding) ProtoReflect() protoreflect.Message

func (*Embedding) Reset

func (x *Embedding) Reset()

func (*Embedding) String

func (x *Embedding) String() string

type Embeddings

type Embeddings struct {
	Object string            `protobuf:"bytes,1,opt,name=object,proto3" json:"object,omitempty"`
	Data   []*Embedding      `protobuf:"bytes,2,rep,name=data,proto3" json:"data,omitempty"`
	Model  string            `protobuf:"bytes,3,opt,name=model,proto3" json:"model,omitempty"`
	Usage  *Embeddings_Usage `protobuf:"bytes,4,opt,name=usage,proto3" json:"usage,omitempty"`
	// contains filtered or unexported fields
}

func (*Embeddings) Descriptor deprecated

func (*Embeddings) Descriptor() ([]byte, []int)

Deprecated: Use Embeddings.ProtoReflect.Descriptor instead.

func (*Embeddings) GetData

func (x *Embeddings) GetData() []*Embedding

func (*Embeddings) GetModel

func (x *Embeddings) GetModel() string

func (*Embeddings) GetObject

func (x *Embeddings) GetObject() string

func (*Embeddings) GetUsage

func (x *Embeddings) GetUsage() *Embeddings_Usage

func (*Embeddings) ProtoMessage

func (*Embeddings) ProtoMessage()

func (*Embeddings) ProtoReflect

func (x *Embeddings) ProtoReflect() protoreflect.Message

func (*Embeddings) Reset

func (x *Embeddings) Reset()

func (*Embeddings) String

func (x *Embeddings) String() string

type Embeddings_Usage

type Embeddings_Usage struct {
	PromptTokens int32 `protobuf:"varint,1,opt,name=prompt_tokens,json=promptTokens,proto3" json:"prompt_tokens,omitempty"`
	TotalTokens  int32 `protobuf:"varint,2,opt,name=total_tokens,json=totalTokens,proto3" json:"total_tokens,omitempty"`
	// contains filtered or unexported fields
}

func (*Embeddings_Usage) Descriptor deprecated

func (*Embeddings_Usage) Descriptor() ([]byte, []int)

Deprecated: Use Embeddings_Usage.ProtoReflect.Descriptor instead.

func (*Embeddings_Usage) GetPromptTokens

func (x *Embeddings_Usage) GetPromptTokens() int32

func (*Embeddings_Usage) GetTotalTokens

func (x *Embeddings_Usage) GetTotalTokens() int32

func (*Embeddings_Usage) ProtoMessage

func (*Embeddings_Usage) ProtoMessage()

func (*Embeddings_Usage) ProtoReflect

func (x *Embeddings_Usage) ProtoReflect() protoreflect.Message

func (*Embeddings_Usage) Reset

func (x *Embeddings_Usage) Reset()

func (*Embeddings_Usage) String

func (x *Embeddings_Usage) String() string

type EngineStatus

type EngineStatus struct {
	EngineId string `protobuf:"bytes,1,opt,name=engine_id,json=engineId,proto3" json:"engine_id,omitempty"`
	// Deprecated: Marked as deprecated in api/v1/inference_server_management.proto.
	ModelIds []string `protobuf:"bytes,2,rep,name=model_ids,json=modelIds,proto3" json:"model_ids,omitempty"`
	// Deprecated: Marked as deprecated in api/v1/inference_server_management.proto.
	SyncStatus *EngineStatus_SyncStatus `protobuf:"bytes,3,opt,name=sync_status,json=syncStatus,proto3" json:"sync_status,omitempty"`
	Ready      bool                     `protobuf:"varint,4,opt,name=ready,proto3" json:"ready,omitempty"`
	Models     []*EngineStatus_Model    `protobuf:"bytes,5,rep,name=models,proto3" json:"models,omitempty"`
	ClusterId  string                   `protobuf:"bytes,6,opt,name=cluster_id,json=clusterId,proto3" json:"cluster_id,omitempty"`
	// contains filtered or unexported fields
}

func (*EngineStatus) Descriptor deprecated

func (*EngineStatus) Descriptor() ([]byte, []int)

Deprecated: Use EngineStatus.ProtoReflect.Descriptor instead.

func (*EngineStatus) GetClusterId added in v1.15.0

func (x *EngineStatus) GetClusterId() string

func (*EngineStatus) GetEngineId

func (x *EngineStatus) GetEngineId() string

func (*EngineStatus) GetModelIds deprecated

func (x *EngineStatus) GetModelIds() []string

Deprecated: Marked as deprecated in api/v1/inference_server_management.proto.

func (*EngineStatus) GetModels added in v1.15.0

func (x *EngineStatus) GetModels() []*EngineStatus_Model

func (*EngineStatus) GetReady

func (x *EngineStatus) GetReady() bool

func (*EngineStatus) GetSyncStatus deprecated

func (x *EngineStatus) GetSyncStatus() *EngineStatus_SyncStatus

Deprecated: Marked as deprecated in api/v1/inference_server_management.proto.

func (*EngineStatus) ProtoMessage

func (*EngineStatus) ProtoMessage()

func (*EngineStatus) ProtoReflect

func (x *EngineStatus) ProtoReflect() protoreflect.Message

func (*EngineStatus) Reset

func (x *EngineStatus) Reset()

func (*EngineStatus) String

func (x *EngineStatus) String() string

type EngineStatus_Model added in v1.15.0

type EngineStatus_Model struct {
	Id                  string `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	IsReady             bool   `protobuf:"varint,2,opt,name=is_ready,json=isReady,proto3" json:"is_ready,omitempty"`
	InProgressTaskCount int32  `protobuf:"varint,3,opt,name=in_progress_task_count,json=inProgressTaskCount,proto3" json:"in_progress_task_count,omitempty"`
	GpuAllocated        int32  `protobuf:"varint,4,opt,name=gpu_allocated,json=gpuAllocated,proto3" json:"gpu_allocated,omitempty"`
	// contains filtered or unexported fields
}

func (*EngineStatus_Model) Descriptor deprecated added in v1.15.0

func (*EngineStatus_Model) Descriptor() ([]byte, []int)

Deprecated: Use EngineStatus_Model.ProtoReflect.Descriptor instead.

func (*EngineStatus_Model) GetGpuAllocated added in v1.15.0

func (x *EngineStatus_Model) GetGpuAllocated() int32

func (*EngineStatus_Model) GetId added in v1.15.0

func (x *EngineStatus_Model) GetId() string

func (*EngineStatus_Model) GetInProgressTaskCount added in v1.15.0

func (x *EngineStatus_Model) GetInProgressTaskCount() int32

func (*EngineStatus_Model) GetIsReady added in v1.15.0

func (x *EngineStatus_Model) GetIsReady() bool

func (*EngineStatus_Model) ProtoMessage added in v1.15.0

func (*EngineStatus_Model) ProtoMessage()

func (*EngineStatus_Model) ProtoReflect added in v1.15.0

func (x *EngineStatus_Model) ProtoReflect() protoreflect.Message

func (*EngineStatus_Model) Reset added in v1.15.0

func (x *EngineStatus_Model) Reset()

func (*EngineStatus_Model) String added in v1.15.0

func (x *EngineStatus_Model) String() string

type EngineStatus_SyncStatus

type EngineStatus_SyncStatus struct {

	// in_progress_model_ids is a list of model ids that are currently being synced.
	InProgressModelIds []string `protobuf:"bytes,1,rep,name=in_progress_model_ids,json=inProgressModelIds,proto3" json:"in_progress_model_ids,omitempty"`
	// contains filtered or unexported fields
}

func (*EngineStatus_SyncStatus) Descriptor deprecated

func (*EngineStatus_SyncStatus) Descriptor() ([]byte, []int)

Deprecated: Use EngineStatus_SyncStatus.ProtoReflect.Descriptor instead.

func (*EngineStatus_SyncStatus) GetInProgressModelIds

func (x *EngineStatus_SyncStatus) GetInProgressModelIds() []string

func (*EngineStatus_SyncStatus) ProtoMessage

func (*EngineStatus_SyncStatus) ProtoMessage()

func (*EngineStatus_SyncStatus) ProtoReflect

func (x *EngineStatus_SyncStatus) ProtoReflect() protoreflect.Message

func (*EngineStatus_SyncStatus) Reset

func (x *EngineStatus_SyncStatus) Reset()

func (*EngineStatus_SyncStatus) String

func (x *EngineStatus_SyncStatus) String() string

type GetInferenceStatusRequest added in v1.15.2

type GetInferenceStatusRequest struct {
	// contains filtered or unexported fields
}

func (*GetInferenceStatusRequest) Descriptor deprecated added in v1.15.2

func (*GetInferenceStatusRequest) Descriptor() ([]byte, []int)

Deprecated: Use GetInferenceStatusRequest.ProtoReflect.Descriptor instead.

func (*GetInferenceStatusRequest) ProtoMessage added in v1.15.2

func (*GetInferenceStatusRequest) ProtoMessage()

func (*GetInferenceStatusRequest) ProtoReflect added in v1.15.2

func (*GetInferenceStatusRequest) Reset added in v1.15.2

func (x *GetInferenceStatusRequest) Reset()

func (*GetInferenceStatusRequest) String added in v1.15.2

func (x *GetInferenceStatusRequest) String() string

type GoAwayRequest added in v1.25.0

type GoAwayRequest struct {
	// contains filtered or unexported fields
}

func (*GoAwayRequest) Descriptor deprecated added in v1.25.0

func (*GoAwayRequest) Descriptor() ([]byte, []int)

Deprecated: Use GoAwayRequest.ProtoReflect.Descriptor instead.

func (*GoAwayRequest) ProtoMessage added in v1.25.0

func (*GoAwayRequest) ProtoMessage()

func (*GoAwayRequest) ProtoReflect added in v1.25.0

func (x *GoAwayRequest) ProtoReflect() protoreflect.Message

func (*GoAwayRequest) Reset added in v1.25.0

func (x *GoAwayRequest) Reset()

func (*GoAwayRequest) String added in v1.25.0

func (x *GoAwayRequest) String() string

type HeaderValue

type HeaderValue struct {
	Values []string `protobuf:"bytes,1,rep,name=values,proto3" json:"values,omitempty"`
	// contains filtered or unexported fields
}

func (*HeaderValue) Descriptor deprecated

func (*HeaderValue) Descriptor() ([]byte, []int)

Deprecated: Use HeaderValue.ProtoReflect.Descriptor instead.

func (*HeaderValue) GetValues

func (x *HeaderValue) GetValues() []string

func (*HeaderValue) ProtoMessage

func (*HeaderValue) ProtoMessage()

func (*HeaderValue) ProtoReflect

func (x *HeaderValue) ProtoReflect() protoreflect.Message

func (*HeaderValue) Reset

func (x *HeaderValue) Reset()

func (*HeaderValue) String

func (x *HeaderValue) String() string

type HeartbeatRequest added in v1.27.0

type HeartbeatRequest struct {
	// contains filtered or unexported fields
}

func (*HeartbeatRequest) Descriptor deprecated added in v1.27.0

func (*HeartbeatRequest) Descriptor() ([]byte, []int)

Deprecated: Use HeartbeatRequest.ProtoReflect.Descriptor instead.

func (*HeartbeatRequest) ProtoMessage added in v1.27.0

func (*HeartbeatRequest) ProtoMessage()

func (*HeartbeatRequest) ProtoReflect added in v1.27.0

func (x *HeartbeatRequest) ProtoReflect() protoreflect.Message

func (*HeartbeatRequest) Reset added in v1.27.0

func (x *HeartbeatRequest) Reset()

func (*HeartbeatRequest) String added in v1.27.0

func (x *HeartbeatRequest) String() string

type HttpResponse

type HttpResponse struct {
	StatusCode int32                   `protobuf:"varint,1,opt,name=status_code,json=statusCode,proto3" json:"status_code,omitempty"`
	Status     string                  `protobuf:"bytes,2,opt,name=status,proto3" json:"status,omitempty"`
	Header     map[string]*HeaderValue `` /* 153-byte string literal not displayed */
	// body is empty for server sent events.
	Body []byte `protobuf:"bytes,4,opt,name=body,proto3" json:"body,omitempty"`
	// contains filtered or unexported fields
}

func (*HttpResponse) Descriptor deprecated

func (*HttpResponse) Descriptor() ([]byte, []int)

Deprecated: Use HttpResponse.ProtoReflect.Descriptor instead.

func (*HttpResponse) GetBody

func (x *HttpResponse) GetBody() []byte

func (*HttpResponse) GetHeader

func (x *HttpResponse) GetHeader() map[string]*HeaderValue

func (*HttpResponse) GetStatus

func (x *HttpResponse) GetStatus() string

func (*HttpResponse) GetStatusCode

func (x *HttpResponse) GetStatusCode() int32

func (*HttpResponse) ProtoMessage

func (*HttpResponse) ProtoMessage()

func (*HttpResponse) ProtoReflect

func (x *HttpResponse) ProtoReflect() protoreflect.Message

func (*HttpResponse) Reset

func (x *HttpResponse) Reset()

func (*HttpResponse) String

func (x *HttpResponse) String() string

type InferenceInternalServiceClient added in v1.4.0

type InferenceInternalServiceClient interface {
	ProcessTasksInternal(ctx context.Context, opts ...grpc.CallOption) (InferenceInternalService_ProcessTasksInternalClient, error)
}

InferenceInternalServiceClient is the client API for InferenceInternalService service.

For semantics around ctx use and closing/ending streaming RPCs, please refer to https://pkg.go.dev/google.golang.org/grpc/?tab=doc#ClientConn.NewStream.

func NewInferenceInternalServiceClient added in v1.4.0

func NewInferenceInternalServiceClient(cc grpc.ClientConnInterface) InferenceInternalServiceClient

type InferenceInternalServiceServer added in v1.4.0

type InferenceInternalServiceServer interface {
	ProcessTasksInternal(InferenceInternalService_ProcessTasksInternalServer) error
	// contains filtered or unexported methods
}

InferenceInternalServiceServer is the server API for InferenceInternalService service. All implementations must embed UnimplementedInferenceInternalServiceServer for forward compatibility

type InferenceInternalService_ProcessTasksInternalClient added in v1.4.0

type InferenceInternalService_ProcessTasksInternalClient interface {
	Send(*ProcessTasksInternalRequest) error
	Recv() (*ProcessTasksInternalResponse, error)
	grpc.ClientStream
}

type InferenceInternalService_ProcessTasksInternalServer added in v1.4.0

type InferenceInternalService_ProcessTasksInternalServer interface {
	Send(*ProcessTasksInternalResponse) error
	Recv() (*ProcessTasksInternalRequest, error)
	grpc.ServerStream
}

type InferenceServiceClient added in v1.15.0

type InferenceServiceClient interface {
	GetInferenceStatus(ctx context.Context, in *GetInferenceStatusRequest, opts ...grpc.CallOption) (*InferenceStatus, error)
	ActivateModel(ctx context.Context, in *ActivateModelRequest, opts ...grpc.CallOption) (*ActivateModelResponse, error)
	DeactivateModel(ctx context.Context, in *DeactivateModelRequest, opts ...grpc.CallOption) (*DeactivateModelResponse, error)
}

InferenceServiceClient is the client API for InferenceService service.

For semantics around ctx use and closing/ending streaming RPCs, please refer to https://pkg.go.dev/google.golang.org/grpc/?tab=doc#ClientConn.NewStream.

func NewInferenceServiceClient added in v1.15.0

func NewInferenceServiceClient(cc grpc.ClientConnInterface) InferenceServiceClient

type InferenceServiceServer added in v1.15.0

type InferenceServiceServer interface {
	GetInferenceStatus(context.Context, *GetInferenceStatusRequest) (*InferenceStatus, error)
	ActivateModel(context.Context, *ActivateModelRequest) (*ActivateModelResponse, error)
	DeactivateModel(context.Context, *DeactivateModelRequest) (*DeactivateModelResponse, error)
	// contains filtered or unexported methods
}

InferenceServiceServer is the server API for InferenceService service. All implementations must embed UnimplementedInferenceServiceServer for forward compatibility

type InferenceStatus added in v1.15.0

type InferenceStatus struct {
	ClusterStatuses []*ClusterStatus `protobuf:"bytes,1,rep,name=cluster_statuses,json=clusterStatuses,proto3" json:"cluster_statuses,omitempty"`
	TaskStatus      *TaskStatus      `protobuf:"bytes,2,opt,name=task_status,json=taskStatus,proto3" json:"task_status,omitempty"`
	// contains filtered or unexported fields
}

func (*InferenceStatus) Descriptor deprecated added in v1.15.0

func (*InferenceStatus) Descriptor() ([]byte, []int)

Deprecated: Use InferenceStatus.ProtoReflect.Descriptor instead.

func (*InferenceStatus) GetClusterStatuses added in v1.15.0

func (x *InferenceStatus) GetClusterStatuses() []*ClusterStatus

func (*InferenceStatus) GetTaskStatus added in v1.15.0

func (x *InferenceStatus) GetTaskStatus() *TaskStatus

func (*InferenceStatus) ProtoMessage added in v1.15.0

func (*InferenceStatus) ProtoMessage()

func (*InferenceStatus) ProtoReflect added in v1.15.0

func (x *InferenceStatus) ProtoReflect() protoreflect.Message

func (*InferenceStatus) Reset added in v1.15.0

func (x *InferenceStatus) Reset()

func (*InferenceStatus) String added in v1.15.0

func (x *InferenceStatus) String() string

type InferenceWorkerServiceClient

type InferenceWorkerServiceClient interface {
	ProcessTasks(ctx context.Context, opts ...grpc.CallOption) (InferenceWorkerService_ProcessTasksClient, error)
}

InferenceWorkerServiceClient is the client API for InferenceWorkerService service.

For semantics around ctx use and closing/ending streaming RPCs, please refer to https://pkg.go.dev/google.golang.org/grpc/?tab=doc#ClientConn.NewStream.

type InferenceWorkerServiceServer

type InferenceWorkerServiceServer interface {
	ProcessTasks(InferenceWorkerService_ProcessTasksServer) error
	// contains filtered or unexported methods
}

InferenceWorkerServiceServer is the server API for InferenceWorkerService service. All implementations must embed UnimplementedInferenceWorkerServiceServer for forward compatibility

type InferenceWorkerService_ProcessTasksClient

type InferenceWorkerService_ProcessTasksClient interface {
	Send(*ProcessTasksRequest) error
	Recv() (*ProcessTasksResponse, error)
	grpc.ClientStream
}

type InferenceWorkerService_ProcessTasksServer

type InferenceWorkerService_ProcessTasksServer interface {
	Send(*ProcessTasksResponse) error
	Recv() (*ProcessTasksRequest, error)
	grpc.ServerStream
}

type Logprobs

type Logprobs struct {
	Content []*Logprobs_Content `protobuf:"bytes,1,rep,name=content,proto3" json:"content,omitempty"`
	// contains filtered or unexported fields
}

func (*Logprobs) Descriptor deprecated

func (*Logprobs) Descriptor() ([]byte, []int)

Deprecated: Use Logprobs.ProtoReflect.Descriptor instead.

func (*Logprobs) GetContent

func (x *Logprobs) GetContent() []*Logprobs_Content

func (*Logprobs) ProtoMessage

func (*Logprobs) ProtoMessage()

func (*Logprobs) ProtoReflect

func (x *Logprobs) ProtoReflect() protoreflect.Message

func (*Logprobs) Reset

func (x *Logprobs) Reset()

func (*Logprobs) String

func (x *Logprobs) String() string

type Logprobs_Content

type Logprobs_Content struct {
	Token   string  `protobuf:"bytes,1,opt,name=token,proto3" json:"token,omitempty"`
	Logprob float64 `protobuf:"fixed64,2,opt,name=logprob,proto3" json:"logprob,omitempty"`
	// A list of integers representing the UTF-8 bytes representation of the token.
	Bytes       []byte                        `protobuf:"bytes,3,opt,name=bytes,proto3" json:"bytes,omitempty"`
	TopLogprobs *Logprobs_Content_TopLogprobs `protobuf:"bytes,4,opt,name=top_logprobs,json=topLogprobs,proto3" json:"top_logprobs,omitempty"`
	// contains filtered or unexported fields
}

func (*Logprobs_Content) Descriptor deprecated

func (*Logprobs_Content) Descriptor() ([]byte, []int)

Deprecated: Use Logprobs_Content.ProtoReflect.Descriptor instead.

func (*Logprobs_Content) GetBytes

func (x *Logprobs_Content) GetBytes() []byte

func (*Logprobs_Content) GetLogprob

func (x *Logprobs_Content) GetLogprob() float64

func (*Logprobs_Content) GetToken

func (x *Logprobs_Content) GetToken() string

func (*Logprobs_Content) GetTopLogprobs

func (x *Logprobs_Content) GetTopLogprobs() *Logprobs_Content_TopLogprobs

func (*Logprobs_Content) ProtoMessage

func (*Logprobs_Content) ProtoMessage()

func (*Logprobs_Content) ProtoReflect

func (x *Logprobs_Content) ProtoReflect() protoreflect.Message

func (*Logprobs_Content) Reset

func (x *Logprobs_Content) Reset()

func (*Logprobs_Content) String

func (x *Logprobs_Content) String() string

type Logprobs_Content_TopLogprobs

type Logprobs_Content_TopLogprobs struct {
	Token   string  `protobuf:"bytes,1,opt,name=token,proto3" json:"token,omitempty"`
	Logprob float64 `protobuf:"fixed64,2,opt,name=logprob,proto3" json:"logprob,omitempty"`
	Bytes   []byte  `protobuf:"bytes,3,opt,name=bytes,proto3" json:"bytes,omitempty"`
	// contains filtered or unexported fields
}

func (*Logprobs_Content_TopLogprobs) Descriptor deprecated

func (*Logprobs_Content_TopLogprobs) Descriptor() ([]byte, []int)

Deprecated: Use Logprobs_Content_TopLogprobs.ProtoReflect.Descriptor instead.

func (*Logprobs_Content_TopLogprobs) GetBytes

func (x *Logprobs_Content_TopLogprobs) GetBytes() []byte

func (*Logprobs_Content_TopLogprobs) GetLogprob

func (x *Logprobs_Content_TopLogprobs) GetLogprob() float64

func (*Logprobs_Content_TopLogprobs) GetToken

func (x *Logprobs_Content_TopLogprobs) GetToken() string

func (*Logprobs_Content_TopLogprobs) ProtoMessage

func (*Logprobs_Content_TopLogprobs) ProtoMessage()

func (*Logprobs_Content_TopLogprobs) ProtoReflect

func (*Logprobs_Content_TopLogprobs) Reset

func (x *Logprobs_Content_TopLogprobs) Reset()

func (*Logprobs_Content_TopLogprobs) String

type ProcessTasksInternalRequest added in v1.4.0

type ProcessTasksInternalRequest struct {

	// Types that are assignable to Message:
	//
	//	*ProcessTasksInternalRequest_ServerStatus
	//	*ProcessTasksInternalRequest_TaskResult
	Message isProcessTasksInternalRequest_Message `protobuf_oneof:"message"`
	// contains filtered or unexported fields
}

func (*ProcessTasksInternalRequest) Descriptor deprecated added in v1.4.0

func (*ProcessTasksInternalRequest) Descriptor() ([]byte, []int)

Deprecated: Use ProcessTasksInternalRequest.ProtoReflect.Descriptor instead.

func (*ProcessTasksInternalRequest) GetMessage added in v1.4.0

func (m *ProcessTasksInternalRequest) GetMessage() isProcessTasksInternalRequest_Message

func (*ProcessTasksInternalRequest) GetServerStatus added in v1.4.0

func (x *ProcessTasksInternalRequest) GetServerStatus() *ServerStatus

func (*ProcessTasksInternalRequest) GetTaskResult added in v1.4.0

func (x *ProcessTasksInternalRequest) GetTaskResult() *TaskResult

func (*ProcessTasksInternalRequest) ProtoMessage added in v1.4.0

func (*ProcessTasksInternalRequest) ProtoMessage()

func (*ProcessTasksInternalRequest) ProtoReflect added in v1.4.0

func (*ProcessTasksInternalRequest) Reset added in v1.4.0

func (x *ProcessTasksInternalRequest) Reset()

func (*ProcessTasksInternalRequest) String added in v1.4.0

func (x *ProcessTasksInternalRequest) String() string

type ProcessTasksInternalRequest_ServerStatus added in v1.4.0

type ProcessTasksInternalRequest_ServerStatus struct {
	ServerStatus *ServerStatus `protobuf:"bytes,1,opt,name=server_status,json=serverStatus,proto3,oneof"`
}

type ProcessTasksInternalRequest_TaskResult added in v1.4.0

type ProcessTasksInternalRequest_TaskResult struct {
	TaskResult *TaskResult `protobuf:"bytes,2,opt,name=task_result,json=taskResult,proto3,oneof"`
}

type ProcessTasksInternalResponse added in v1.4.0

type ProcessTasksInternalResponse struct {
	NewTask  *Task  `protobuf:"bytes,1,opt,name=new_task,json=newTask,proto3" json:"new_task,omitempty"`
	TenantId string `protobuf:"bytes,2,opt,name=tenant_id,json=tenantId,proto3" json:"tenant_id,omitempty"`
	// contains filtered or unexported fields
}

func (*ProcessTasksInternalResponse) Descriptor deprecated added in v1.4.0

func (*ProcessTasksInternalResponse) Descriptor() ([]byte, []int)

Deprecated: Use ProcessTasksInternalResponse.ProtoReflect.Descriptor instead.

func (*ProcessTasksInternalResponse) GetNewTask added in v1.4.0

func (x *ProcessTasksInternalResponse) GetNewTask() *Task

func (*ProcessTasksInternalResponse) GetTenantId added in v1.4.0

func (x *ProcessTasksInternalResponse) GetTenantId() string

func (*ProcessTasksInternalResponse) ProtoMessage added in v1.4.0

func (*ProcessTasksInternalResponse) ProtoMessage()

func (*ProcessTasksInternalResponse) ProtoReflect added in v1.4.0

func (*ProcessTasksInternalResponse) Reset added in v1.4.0

func (x *ProcessTasksInternalResponse) Reset()

func (*ProcessTasksInternalResponse) String added in v1.4.0

type ProcessTasksRequest

type ProcessTasksRequest struct {

	// Types that are assignable to Message:
	//
	//	*ProcessTasksRequest_EngineStatus
	//	*ProcessTasksRequest_TaskResult
	Message isProcessTasksRequest_Message `protobuf_oneof:"message"`
	// contains filtered or unexported fields
}

func (*ProcessTasksRequest) Descriptor deprecated

func (*ProcessTasksRequest) Descriptor() ([]byte, []int)

Deprecated: Use ProcessTasksRequest.ProtoReflect.Descriptor instead.

func (*ProcessTasksRequest) GetEngineStatus

func (x *ProcessTasksRequest) GetEngineStatus() *EngineStatus

func (*ProcessTasksRequest) GetMessage

func (m *ProcessTasksRequest) GetMessage() isProcessTasksRequest_Message

func (*ProcessTasksRequest) GetTaskResult

func (x *ProcessTasksRequest) GetTaskResult() *TaskResult

func (*ProcessTasksRequest) ProtoMessage

func (*ProcessTasksRequest) ProtoMessage()

func (*ProcessTasksRequest) ProtoReflect

func (x *ProcessTasksRequest) ProtoReflect() protoreflect.Message

func (*ProcessTasksRequest) Reset

func (x *ProcessTasksRequest) Reset()

func (*ProcessTasksRequest) String

func (x *ProcessTasksRequest) String() string

type ProcessTasksRequest_EngineStatus

type ProcessTasksRequest_EngineStatus struct {
	EngineStatus *EngineStatus `protobuf:"bytes,1,opt,name=engine_status,json=engineStatus,proto3,oneof"`
}

type ProcessTasksRequest_TaskResult

type ProcessTasksRequest_TaskResult struct {
	TaskResult *TaskResult `protobuf:"bytes,2,opt,name=task_result,json=taskResult,proto3,oneof"`
}

type ProcessTasksResponse

type ProcessTasksResponse struct {
	NewTask *Task `protobuf:"bytes,1,opt,name=new_task,json=newTask,proto3" json:"new_task,omitempty"`
	// contains filtered or unexported fields
}

func (*ProcessTasksResponse) Descriptor deprecated

func (*ProcessTasksResponse) Descriptor() ([]byte, []int)

Deprecated: Use ProcessTasksResponse.ProtoReflect.Descriptor instead.

func (*ProcessTasksResponse) GetNewTask

func (x *ProcessTasksResponse) GetNewTask() *Task

func (*ProcessTasksResponse) ProtoMessage

func (*ProcessTasksResponse) ProtoMessage()

func (*ProcessTasksResponse) ProtoReflect

func (x *ProcessTasksResponse) ProtoReflect() protoreflect.Message

func (*ProcessTasksResponse) Reset

func (x *ProcessTasksResponse) Reset()

func (*ProcessTasksResponse) String

func (x *ProcessTasksResponse) String() string

type RagFunction

type RagFunction struct {
	VectorStoreName string `protobuf:"bytes,1,opt,name=vector_store_name,json=vectorStoreName,proto3" json:"vector_store_name,omitempty"`
	// contains filtered or unexported fields
}

RagFunction is used to unmarshal the json string specified in `Parameters` of Tool message.

func (*RagFunction) Descriptor deprecated

func (*RagFunction) Descriptor() ([]byte, []int)

Deprecated: Use RagFunction.ProtoReflect.Descriptor instead.

func (*RagFunction) GetVectorStoreName

func (x *RagFunction) GetVectorStoreName() string

func (*RagFunction) ProtoMessage

func (*RagFunction) ProtoMessage()

func (*RagFunction) ProtoReflect

func (x *RagFunction) ProtoReflect() protoreflect.Message

func (*RagFunction) Reset

func (x *RagFunction) Reset()

func (*RagFunction) String

func (x *RagFunction) String() string

type ServerSentEvent

type ServerSentEvent struct {
	Data        []byte `protobuf:"bytes,1,opt,name=data,proto3" json:"data,omitempty"`
	IsLastEvent bool   `protobuf:"varint,2,opt,name=is_last_event,json=isLastEvent,proto3" json:"is_last_event,omitempty"`
	// contains filtered or unexported fields
}

func (*ServerSentEvent) Descriptor deprecated

func (*ServerSentEvent) Descriptor() ([]byte, []int)

Deprecated: Use ServerSentEvent.ProtoReflect.Descriptor instead.

func (*ServerSentEvent) GetData

func (x *ServerSentEvent) GetData() []byte

func (*ServerSentEvent) GetIsLastEvent

func (x *ServerSentEvent) GetIsLastEvent() bool

func (*ServerSentEvent) ProtoMessage

func (*ServerSentEvent) ProtoMessage()

func (*ServerSentEvent) ProtoReflect

func (x *ServerSentEvent) ProtoReflect() protoreflect.Message

func (*ServerSentEvent) Reset

func (x *ServerSentEvent) Reset()

func (*ServerSentEvent) String

func (x *ServerSentEvent) String() string

type ServerStatus added in v1.4.0

type ServerStatus struct {
	PodName        string                                   `protobuf:"bytes,1,opt,name=pod_name,json=podName,proto3" json:"pod_name,omitempty"`
	EngineStatuses []*ServerStatus_EngineStatusWithTenantID `protobuf:"bytes,4,rep,name=engine_statuses,json=engineStatuses,proto3" json:"engine_statuses,omitempty"`
	// contains filtered or unexported fields
}

func (*ServerStatus) Descriptor deprecated added in v1.4.0

func (*ServerStatus) Descriptor() ([]byte, []int)

Deprecated: Use ServerStatus.ProtoReflect.Descriptor instead.

func (*ServerStatus) GetEngineStatuses added in v1.4.0

func (x *ServerStatus) GetEngineStatuses() []*ServerStatus_EngineStatusWithTenantID

func (*ServerStatus) GetPodName added in v1.4.0

func (x *ServerStatus) GetPodName() string

func (*ServerStatus) ProtoMessage added in v1.4.0

func (*ServerStatus) ProtoMessage()

func (*ServerStatus) ProtoReflect added in v1.4.0

func (x *ServerStatus) ProtoReflect() protoreflect.Message

func (*ServerStatus) Reset added in v1.4.0

func (x *ServerStatus) Reset()

func (*ServerStatus) String added in v1.4.0

func (x *ServerStatus) String() string

type ServerStatus_EngineStatusWithTenantID added in v1.4.0

type ServerStatus_EngineStatusWithTenantID struct {
	EngineStatus *EngineStatus `protobuf:"bytes,2,opt,name=engine_status,json=engineStatus,proto3" json:"engine_status,omitempty"`
	TenantId     string        `protobuf:"bytes,3,opt,name=tenant_id,json=tenantId,proto3" json:"tenant_id,omitempty"`
	// contains filtered or unexported fields
}

func (*ServerStatus_EngineStatusWithTenantID) Descriptor deprecated added in v1.4.0

func (*ServerStatus_EngineStatusWithTenantID) Descriptor() ([]byte, []int)

Deprecated: Use ServerStatus_EngineStatusWithTenantID.ProtoReflect.Descriptor instead.

func (*ServerStatus_EngineStatusWithTenantID) GetEngineStatus added in v1.4.0

func (*ServerStatus_EngineStatusWithTenantID) GetTenantId added in v1.4.0

func (*ServerStatus_EngineStatusWithTenantID) ProtoMessage added in v1.4.0

func (*ServerStatus_EngineStatusWithTenantID) ProtoMessage()

func (*ServerStatus_EngineStatusWithTenantID) ProtoReflect added in v1.4.0

func (*ServerStatus_EngineStatusWithTenantID) Reset added in v1.4.0

func (*ServerStatus_EngineStatusWithTenantID) String added in v1.4.0

type Task

type Task struct {
	Id       string                  `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	Request  *TaskRequest            `protobuf:"bytes,4,opt,name=request,proto3" json:"request,omitempty"`
	Header   map[string]*HeaderValue `` /* 153-byte string literal not displayed */
	EngineId string                  `protobuf:"bytes,5,opt,name=engine_id,json=engineId,proto3" json:"engine_id,omitempty"`
	// contains filtered or unexported fields
}

func (*Task) Descriptor deprecated

func (*Task) Descriptor() ([]byte, []int)

Deprecated: Use Task.ProtoReflect.Descriptor instead.

func (*Task) GetEngineId added in v1.27.0

func (x *Task) GetEngineId() string

func (*Task) GetHeader

func (x *Task) GetHeader() map[string]*HeaderValue

func (*Task) GetId

func (x *Task) GetId() string

func (*Task) GetRequest

func (x *Task) GetRequest() *TaskRequest

func (*Task) ProtoMessage

func (*Task) ProtoMessage()

func (*Task) ProtoReflect

func (x *Task) ProtoReflect() protoreflect.Message

func (*Task) Reset

func (x *Task) Reset()

func (*Task) String

func (x *Task) String() string

type TaskRequest

type TaskRequest struct {

	// Types that are assignable to Request:
	//
	//	*TaskRequest_ChatCompletion
	//	*TaskRequest_Embedding
	//	*TaskRequest_ModelActivation
	//	*TaskRequest_ModelDeactivation
	//	*TaskRequest_GoAway
	//	*TaskRequest_Heartbeat
	Request isTaskRequest_Request `protobuf_oneof:"request"`
	// contains filtered or unexported fields
}

func (*TaskRequest) Descriptor deprecated

func (*TaskRequest) Descriptor() ([]byte, []int)

Deprecated: Use TaskRequest.ProtoReflect.Descriptor instead.

func (*TaskRequest) GetChatCompletion

func (x *TaskRequest) GetChatCompletion() *CreateChatCompletionRequest

func (*TaskRequest) GetEmbedding

func (x *TaskRequest) GetEmbedding() *CreateEmbeddingRequest

func (*TaskRequest) GetGoAway added in v1.25.0

func (x *TaskRequest) GetGoAway() *GoAwayRequest

func (*TaskRequest) GetHeartbeat added in v1.27.0

func (x *TaskRequest) GetHeartbeat() *HeartbeatRequest

func (*TaskRequest) GetModelActivation added in v1.21.0

func (x *TaskRequest) GetModelActivation() *ActivateModelRequest

func (*TaskRequest) GetModelDeactivation added in v1.21.0

func (x *TaskRequest) GetModelDeactivation() *DeactivateModelRequest

func (*TaskRequest) GetRequest

func (m *TaskRequest) GetRequest() isTaskRequest_Request

func (*TaskRequest) ProtoMessage

func (*TaskRequest) ProtoMessage()

func (*TaskRequest) ProtoReflect

func (x *TaskRequest) ProtoReflect() protoreflect.Message

func (*TaskRequest) Reset

func (x *TaskRequest) Reset()

func (*TaskRequest) String

func (x *TaskRequest) String() string

type TaskRequest_ChatCompletion

type TaskRequest_ChatCompletion struct {
	ChatCompletion *CreateChatCompletionRequest `protobuf:"bytes,1,opt,name=chat_completion,json=chatCompletion,proto3,oneof"`
}

type TaskRequest_Embedding

type TaskRequest_Embedding struct {
	Embedding *CreateEmbeddingRequest `protobuf:"bytes,2,opt,name=embedding,proto3,oneof"`
}

type TaskRequest_GoAway added in v1.25.0

type TaskRequest_GoAway struct {
	// go_away is used to signal the worker to disconnect and
	// reconnect to other server.
	GoAway *GoAwayRequest `protobuf:"bytes,5,opt,name=go_away,json=goAway,proto3,oneof"`
}

type TaskRequest_Heartbeat added in v1.27.0

type TaskRequest_Heartbeat struct {
	Heartbeat *HeartbeatRequest `protobuf:"bytes,6,opt,name=heartbeat,proto3,oneof"`
}

type TaskRequest_ModelActivation added in v1.21.0

type TaskRequest_ModelActivation struct {
	ModelActivation *ActivateModelRequest `protobuf:"bytes,3,opt,name=model_activation,json=modelActivation,proto3,oneof"`
}

type TaskRequest_ModelDeactivation added in v1.21.0

type TaskRequest_ModelDeactivation struct {
	ModelDeactivation *DeactivateModelRequest `protobuf:"bytes,4,opt,name=model_deactivation,json=modelDeactivation,proto3,oneof"`
}

type TaskResult

type TaskResult struct {
	TaskId string `protobuf:"bytes,1,opt,name=task_id,json=taskId,proto3" json:"task_id,omitempty"`
	// Types that are assignable to Message:
	//
	//	*TaskResult_HttpResponse
	//	*TaskResult_ServerSentEvent
	Message isTaskResult_Message `protobuf_oneof:"message"`
	// contains filtered or unexported fields
}

func (*TaskResult) Descriptor deprecated

func (*TaskResult) Descriptor() ([]byte, []int)

Deprecated: Use TaskResult.ProtoReflect.Descriptor instead.

func (*TaskResult) GetHttpResponse

func (x *TaskResult) GetHttpResponse() *HttpResponse

func (*TaskResult) GetMessage

func (m *TaskResult) GetMessage() isTaskResult_Message

func (*TaskResult) GetServerSentEvent

func (x *TaskResult) GetServerSentEvent() *ServerSentEvent

func (*TaskResult) GetTaskId

func (x *TaskResult) GetTaskId() string

func (*TaskResult) ProtoMessage

func (*TaskResult) ProtoMessage()

func (*TaskResult) ProtoReflect

func (x *TaskResult) ProtoReflect() protoreflect.Message

func (*TaskResult) Reset

func (x *TaskResult) Reset()

func (*TaskResult) String

func (x *TaskResult) String() string

type TaskResult_HttpResponse

type TaskResult_HttpResponse struct {
	HttpResponse *HttpResponse `protobuf:"bytes,2,opt,name=http_response,json=httpResponse,proto3,oneof"`
}

type TaskResult_ServerSentEvent

type TaskResult_ServerSentEvent struct {
	ServerSentEvent *ServerSentEvent `protobuf:"bytes,3,opt,name=server_sent_event,json=serverSentEvent,proto3,oneof"`
}

type TaskStatus added in v1.15.0

type TaskStatus struct {

	// in_progress_task_counts tracks the number of in-progress tasks grouped by model id.
	InProgressTaskCounts map[string]int32 `` /* 214-byte string literal not displayed */
	// contains filtered or unexported fields
}

func (*TaskStatus) Descriptor deprecated added in v1.15.0

func (*TaskStatus) Descriptor() ([]byte, []int)

Deprecated: Use TaskStatus.ProtoReflect.Descriptor instead.

func (*TaskStatus) GetInProgressTaskCounts added in v1.15.0

func (x *TaskStatus) GetInProgressTaskCounts() map[string]int32

func (*TaskStatus) ProtoMessage added in v1.15.0

func (*TaskStatus) ProtoMessage()

func (*TaskStatus) ProtoReflect added in v1.15.0

func (x *TaskStatus) ProtoReflect() protoreflect.Message

func (*TaskStatus) Reset added in v1.15.0

func (x *TaskStatus) Reset()

func (*TaskStatus) String added in v1.15.0

func (x *TaskStatus) String() string

type ToolCall

type ToolCall struct {
	Id       string             `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	Type     string             `protobuf:"bytes,2,opt,name=type,proto3" json:"type,omitempty"`
	Function *ToolCall_Function `protobuf:"bytes,3,opt,name=function,proto3" json:"function,omitempty"`
	// contains filtered or unexported fields
}

func (*ToolCall) Descriptor deprecated

func (*ToolCall) Descriptor() ([]byte, []int)

Deprecated: Use ToolCall.ProtoReflect.Descriptor instead.

func (*ToolCall) GetFunction

func (x *ToolCall) GetFunction() *ToolCall_Function

func (*ToolCall) GetId

func (x *ToolCall) GetId() string

func (*ToolCall) GetType

func (x *ToolCall) GetType() string

func (*ToolCall) ProtoMessage

func (*ToolCall) ProtoMessage()

func (*ToolCall) ProtoReflect

func (x *ToolCall) ProtoReflect() protoreflect.Message

func (*ToolCall) Reset

func (x *ToolCall) Reset()

func (*ToolCall) String

func (x *ToolCall) String() string

type ToolCall_Function

type ToolCall_Function struct {
	Name      string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	Arguments string `protobuf:"bytes,2,opt,name=arguments,proto3" json:"arguments,omitempty"`
	// contains filtered or unexported fields
}

func (*ToolCall_Function) Descriptor deprecated

func (*ToolCall_Function) Descriptor() ([]byte, []int)

Deprecated: Use ToolCall_Function.ProtoReflect.Descriptor instead.

func (*ToolCall_Function) GetArguments

func (x *ToolCall_Function) GetArguments() string

func (*ToolCall_Function) GetName

func (x *ToolCall_Function) GetName() string

func (*ToolCall_Function) ProtoMessage

func (*ToolCall_Function) ProtoMessage()

func (*ToolCall_Function) ProtoReflect

func (x *ToolCall_Function) ProtoReflect() protoreflect.Message

func (*ToolCall_Function) Reset

func (x *ToolCall_Function) Reset()

func (*ToolCall_Function) String

func (x *ToolCall_Function) String() string

type UnimplementedChatServiceServer

type UnimplementedChatServiceServer struct {
}

UnimplementedChatServiceServer must be embedded to have forward compatible implementations.

type UnimplementedInferenceInternalServiceServer added in v1.4.0

type UnimplementedInferenceInternalServiceServer struct {
}

UnimplementedInferenceInternalServiceServer must be embedded to have forward compatible implementations.

func (UnimplementedInferenceInternalServiceServer) ProcessTasksInternal added in v1.4.0

type UnimplementedInferenceServiceServer added in v1.15.0

type UnimplementedInferenceServiceServer struct {
}

UnimplementedInferenceServiceServer must be embedded to have forward compatible implementations.

func (UnimplementedInferenceServiceServer) ActivateModel added in v1.21.0

func (UnimplementedInferenceServiceServer) DeactivateModel added in v1.21.0

func (UnimplementedInferenceServiceServer) GetInferenceStatus added in v1.15.2

type UnimplementedInferenceWorkerServiceServer

type UnimplementedInferenceWorkerServiceServer struct {
}

UnimplementedInferenceWorkerServiceServer must be embedded to have forward compatible implementations.

func (UnimplementedInferenceWorkerServiceServer) ProcessTasks

type UnsafeChatServiceServer

type UnsafeChatServiceServer interface {
	// contains filtered or unexported methods
}

UnsafeChatServiceServer may be embedded to opt out of forward compatibility for this service. Use of this interface is not recommended, as added methods to ChatServiceServer will result in compilation errors.

type UnsafeInferenceInternalServiceServer added in v1.4.0

type UnsafeInferenceInternalServiceServer interface {
	// contains filtered or unexported methods
}

UnsafeInferenceInternalServiceServer may be embedded to opt out of forward compatibility for this service. Use of this interface is not recommended, as added methods to InferenceInternalServiceServer will result in compilation errors.

type UnsafeInferenceServiceServer added in v1.15.0

type UnsafeInferenceServiceServer interface {
	// contains filtered or unexported methods
}

UnsafeInferenceServiceServer may be embedded to opt out of forward compatibility for this service. Use of this interface is not recommended, as added methods to InferenceServiceServer will result in compilation errors.

type UnsafeInferenceWorkerServiceServer

type UnsafeInferenceWorkerServiceServer interface {
	// contains filtered or unexported methods
}

UnsafeInferenceWorkerServiceServer may be embedded to opt out of forward compatibility for this service. Use of this interface is not recommended, as added methods to InferenceWorkerServiceServer will result in compilation errors.

type Usage

type Usage struct {
	CompletionTokens int32 `protobuf:"varint,1,opt,name=completion_tokens,json=completionTokens,proto3" json:"completion_tokens,omitempty"`
	PromptTokens     int32 `protobuf:"varint,2,opt,name=prompt_tokens,json=promptTokens,proto3" json:"prompt_tokens,omitempty"`
	TotalTokens      int32 `protobuf:"varint,3,opt,name=total_tokens,json=totalTokens,proto3" json:"total_tokens,omitempty"`
	// contains filtered or unexported fields
}

func (*Usage) Descriptor deprecated

func (*Usage) Descriptor() ([]byte, []int)

Deprecated: Use Usage.ProtoReflect.Descriptor instead.

func (*Usage) GetCompletionTokens

func (x *Usage) GetCompletionTokens() int32

func (*Usage) GetPromptTokens

func (x *Usage) GetPromptTokens() int32

func (*Usage) GetTotalTokens

func (x *Usage) GetTotalTokens() int32

func (*Usage) ProtoMessage

func (*Usage) ProtoMessage()

func (*Usage) ProtoReflect

func (x *Usage) ProtoReflect() protoreflect.Message

func (*Usage) Reset

func (x *Usage) Reset()

func (*Usage) String

func (x *Usage) String() string

Jump to

Keyboard shortcuts

? : This menu
/ : Search site
f or F : Jump to
y or Y : Canonical URL