v1

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
}

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
}

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
}

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
}

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
}

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
}

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
}

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
}

type ChatServiceClient interface {
}

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

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
}

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
}

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
}

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
}

type CreateAudioTranscriptionRequest struct {
	File []byte `protobuf:"bytes,1,opt,name=file,proto3" json:"file,omitempty"`
	// filename is not in the OpenAI API, but it is useful to reserve the filename
	// in the original form request.
	Filename       string  `protobuf:"bytes,2,opt,name=filename,proto3" json:"filename,omitempty"`
	Model          string  `protobuf:"bytes,3,opt,name=model,proto3" json:"model,omitempty"`
	Language       string  `protobuf:"bytes,5,opt,name=language,proto3" json:"language,omitempty"`
	Prompt         string  `protobuf:"bytes,4,opt,name=prompt,proto3" json:"prompt,omitempty"`
	ResponseFormat string  `protobuf:"bytes,6,opt,name=response_format,json=responseFormat,proto3" json:"response_format,omitempty"`
	Stream         bool    `protobuf:"varint,7,opt,name=stream,proto3" json:"stream,omitempty"`
	Temperature    float64 `protobuf:"fixed64,8,opt,name=temperature,proto3" json:"temperature,omitempty"`
	// contains filtered or unexported fields
}

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 */
	// is_temperature_set is used to indicate whether the temperature is set or not.
	// This is required as the OpenAI API spec uses 1.0 as the default value for temperature while
	// setting temperature to 0.0 in the proto is equivalent to unset. If the user sets temperature to 0.0,
	// it becomes unset when the request is sent to the engine (and then the inference runtime sets temperature to 1.0
	// as that's the default value).
	IsTemperatureSet bool `protobuf:"varint,23,opt,name=is_temperature_set,json=isTemperatureSet,proto3" json:"is_temperature_set,omitempty"`
	// is_top_p_set is used to indicate whether the top_p is set or not.
	// This is required as the OpenAI API spec uses 1.0 as the default value for top_p while
	// setting top_p to 0.0 in the proto is equivalent to unset. If the user sets top_p to 0.0,
	// it becomes unset when the request is sent to the engine (and then the inference runtime sets top_p to 1.0
	// as that's the default value).
	IsTopPSet bool `protobuf:"varint,24,opt,name=is_top_p_set,json=isTopPSet,proto3" json:"is_top_p_set,omitempty"`
	// contains filtered or unexported fields
}

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
}

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
}

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

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
}

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
}

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
}

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
}

type CreateChatCompletionRequest_ResponseFormat struct {

	// type is one of 'text', 'json_schema', or 'json_object'.
	Type       string                                                 `protobuf:"bytes,1,opt,name=type,proto3" json:"type,omitempty"`
	JsonSchema *CreateChatCompletionRequest_ResponseFormat_JsonSchema `protobuf:"bytes,2,opt,name=json_schema,json=jsonSchema,proto3" json:"json_schema,omitempty"`
	// contains filtered or unexported fields
}

type CreateChatCompletionRequest_ResponseFormat_JsonSchema struct {
	Name        string `protobuf:"bytes,1,opt,name=name,proto3" json:"name,omitempty"`
	Description string `protobuf:"bytes,2,opt,name=description,proto3" json:"description,omitempty"`
	// encoded_schema is a base64 encoded JSON Schema object.
	//
	// The original value in the "schema" field is stripped by the server and converted
	// to "encoded_schema".
	//
	// The value of the field is converted back to the "schema" field when the request is being
	// sent to vLLM.
	EncodedSchema string `protobuf:"bytes,3,opt,name=encoded_schema,json=encodedSchema,proto3" json:"encoded_schema,omitempty"`
	Strict        bool   `protobuf:"varint,4,opt,name=strict,proto3" json:"strict,omitempty"`
	// contains filtered or unexported fields
}

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
}

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
}

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
}

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

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
}

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"`
	// is_temperature_set is used to indicate whether the temperature is set or not.
	// This is required as the OpenAI API spec uses 1.0 as the default value for temperature while
	// setting temperature to 0.0 in the proto is equivalent to unset. If the user sets temperature to 0.0,
	// it becomes unset when the request is sent to the engine (and then the inference runtime sets temperature to 1.0
	// as that's the default value).
	IsTemperatureSet bool `protobuf:"varint,19,opt,name=is_temperature_set,json=isTemperatureSet,proto3" json:"is_temperature_set,omitempty"`
	// is_top_p_set is used to indicate whether the top_p is set or not.
	// This is required as the OpenAI API spec uses 1.0 as the default value for top_p while
	// setting top_p to 0.0 in the proto is equivalent to unset. If the user sets top_p to 0.0,
	// it becomes unset when the request is sent to the engine (and then the inference runtime sets top_p to 1.0
	// as that's the default value).
	IsTopPSet bool `protobuf:"varint,20,opt,name=is_top_p_set,json=isTopPSet,proto3" json:"is_top_p_set,omitempty"`
	// contains filtered or unexported fields
}

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
}

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 string, 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
}

type CreateModelResponseRequest struct {
	Background bool     `protobuf:"varint,1,opt,name=background,proto3" json:"background,omitempty"`
	Include    []string `protobuf:"bytes,2,rep,name=include,proto3" json:"include,omitempty"`
	// 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 string, we move the value of the "input" field to "encoded_input"
	// and remove the field before unmarshalling.
	Input              string                                    `protobuf:"bytes,3,opt,name=input,proto3" json:"input,omitempty"`
	EncodedInput       string                                    `protobuf:"bytes,4,opt,name=encoded_input,json=encodedInput,proto3" json:"encoded_input,omitempty"`
	Instructions       string                                    `protobuf:"bytes,5,opt,name=instructions,proto3" json:"instructions,omitempty"`
	MaxOutputTokens    int32                                     `protobuf:"varint,6,opt,name=max_output_tokens,json=maxOutputTokens,proto3" json:"max_output_tokens,omitempty"`
	MaxToolCalls       int32                                     `protobuf:"varint,7,opt,name=max_tool_calls,json=maxToolCalls,proto3" json:"max_tool_calls,omitempty"`
	Metadata           map[string]string                         `` /* 157-byte string literal not displayed */
	Model              string                                    `protobuf:"bytes,9,opt,name=model,proto3" json:"model,omitempty"`
	ParallelToolCalls  bool                                      `protobuf:"varint,10,opt,name=parallel_tool_calls,json=parallelToolCalls,proto3" json:"parallel_tool_calls,omitempty"`
	PreviousResponseId string                                    `protobuf:"bytes,11,opt,name=previous_response_id,json=previousResponseId,proto3" json:"previous_response_id,omitempty"`
	Prompt             *CreateModelResponseRequest_Prompt        `protobuf:"bytes,12,opt,name=prompt,proto3" json:"prompt,omitempty"`
	PromptCacheKey     string                                    `protobuf:"bytes,13,opt,name=prompt_cache_key,json=promptCacheKey,proto3" json:"prompt_cache_key,omitempty"`
	Reasoning          *CreateModelResponseRequest_Reasoning     `protobuf:"bytes,14,opt,name=reasoning,proto3" json:"reasoning,omitempty"`
	SafetyIdentifier   string                                    `protobuf:"bytes,15,opt,name=safety_identifier,json=safetyIdentifier,proto3" json:"safety_identifier,omitempty"`
	ServiceTier        string                                    `protobuf:"bytes,16,opt,name=service_tier,json=serviceTier,proto3" json:"service_tier,omitempty"`
	Store              bool                                      `protobuf:"varint,17,opt,name=store,proto3" json:"store,omitempty"`
	Stream             bool                                      `protobuf:"varint,18,opt,name=stream,proto3" json:"stream,omitempty"`
	StreamOptions      *CreateModelResponseRequest_StreamOptions `protobuf:"bytes,19,opt,name=stream_options,json=streamOptions,proto3" json:"stream_options,omitempty"`
	Temperature        float64                                   `protobuf:"fixed64,20,opt,name=temperature,proto3" json:"temperature,omitempty"`
	// is_temperature_set is used to indicate whether the temperature is set or not.
	// This is required as the OpenAI API spec uses 1.0 as the default value for temperature while
	// setting temperature to 0.0 in the proto is equivalent to unset. If the user sets temperature to 0.0,
	// it becomes unset when the request is sent to the engine (and then the inference runtime sets temperature to 1.0
	// as that's the default value).
	IsTemperatureSet bool                             `protobuf:"varint,21,opt,name=is_temperature_set,json=isTemperatureSet,proto3" json:"is_temperature_set,omitempty"`
	Text             *CreateModelResponseRequest_Text `protobuf:"bytes,22,opt,name=text,proto3" json:"text,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_object"
	// 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,23,opt,name=tool_choice,json=toolChoice,proto3" json:"tool_choice,omitempty"`
	ToolChoiceObject *CreateModelResponseRequest_ToolChoice `protobuf:"bytes,24,opt,name=tool_choice_object,json=toolChoiceObject,proto3" json:"tool_choice_object,omitempty"`
	// The original value in the "tools" field is stripped by the server and converted
	// to "encoded_tools".
	//
	// The value of the field is converted back to the "tools" field when the request is being
	// sent to vLLM.
	EncodedTools string  `protobuf:"bytes,30,opt,name=encoded_tools,json=encodedTools,proto3" json:"encoded_tools,omitempty"`
	TopLogprobs  int32   `protobuf:"varint,25,opt,name=top_logprobs,json=topLogprobs,proto3" json:"top_logprobs,omitempty"`
	TopP         float64 `protobuf:"fixed64,26,opt,name=top_p,json=topP,proto3" json:"top_p,omitempty"`
	// is_top_p_set is used to indicate whether the top_p is set or not.
	// This is required as the OpenAI API spec uses 1.0 as the default value for top_p while
	// setting top_p to 0.0 in the proto is equivalent to unset. If the user sets top_p to 0.0,
	// it becomes unset when the request is sent to the engine (and then the inference runtime sets top_p to 1.0
	// as that's the default value).
	IsTopPSet  bool   `protobuf:"varint,27,opt,name=is_top_p_set,json=isTopPSet,proto3" json:"is_top_p_set,omitempty"`
	Truncation bool   `protobuf:"varint,28,opt,name=truncation,proto3" json:"truncation,omitempty"`
	User       string `protobuf:"bytes,29,opt,name=user,proto3" json:"user,omitempty"`
	// contains filtered or unexported fields
}

type CreateModelResponseRequest_Input struct {
	Type string `protobuf:"bytes,1,opt,name=type,proto3" json:"type,omitempty"`
	// 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 []*CreateModelResponseRequest_Input_Content `protobuf:"bytes,2,rep,name=content,proto3" json:"content,omitempty"`
	Role    string                                      `protobuf:"bytes,3,opt,name=role,proto3" json:"role,omitempty"`
	Status  string                                      `protobuf:"bytes,4,opt,name=status,proto3" json:"status,omitempty"`
	// id is only meaningful when the type is "item_reference" or "message" (and the item is an output message).
	Id string `protobuf:"bytes,5,opt,name=id,proto3" json:"id,omitempty"`
	// contains filtered or unexported fields
}

type CreateModelResponseRequest_Input_Content struct {
	Type string `protobuf:"bytes,1,opt,name=type,proto3" json:"type,omitempty"`
	// This field is meaningful when the type is "input_text".
	Text string `protobuf:"bytes,2,opt,name=text,proto3" json:"text,omitempty"`
	// These fields are meaningful when the type is "input_image".
	Detail   string `protobuf:"bytes,3,opt,name=detail,proto3" json:"detail,omitempty"`
	ImageUrl string `protobuf:"bytes,4,opt,name=image_url,json=imageUrl,proto3" json:"image_url,omitempty"`
	// This field is meaningful when the type is "input_image" or "input_file".
	FileId string `protobuf:"bytes,5,opt,name=file_id,json=fileId,proto3" json:"file_id,omitempty"`
	// These fields are meaningful when the type is "input_file".
	FileData string `protobuf:"bytes,6,opt,name=file_data,json=fileData,proto3" json:"file_data,omitempty"`
	FileUrl  string `protobuf:"bytes,7,opt,name=file_url,json=fileUrl,proto3" json:"file_url,omitempty"`
	Filename string `protobuf:"bytes,8,opt,name=filename,proto3" json:"filename,omitempty"`
	// contains filtered or unexported fields
}

type CreateModelResponseRequest_Prompt struct {
	Id string `protobuf:"bytes,1,opt,name=id,proto3" json:"id,omitempty"`
	// TODO(kenji): Support variables
	Version string `protobuf:"bytes,3,opt,name=version,proto3" json:"version,omitempty"`
	// contains filtered or unexported fields
}

type CreateModelResponseRequest_Reasoning struct {
	Effort          string `protobuf:"bytes,1,opt,name=effort,proto3" json:"effort,omitempty"`
	GenerateSummary string `protobuf:"bytes,2,opt,name=generate_summary,json=generateSummary,proto3" json:"generate_summary,omitempty"`
	Summary         string `protobuf:"bytes,3,opt,name=summary,proto3" json:"summary,omitempty"`
	// contains filtered or unexported fields
}

type CreateModelResponseRequest_StreamOptions struct {
	IncludeObfuscation bool `protobuf:"varint,1,opt,name=include_obfuscation,json=includeObfuscation,proto3" json:"include_obfuscation,omitempty"`
	// contains filtered or unexported fields
}

type CreateModelResponseRequest_Text struct {
	Format    *CreateModelResponseRequest_Text_Format `protobuf:"bytes,1,opt,name=format,proto3" json:"format,omitempty"`
	Verbosity string                                  `protobuf:"bytes,2,opt,name=verbosity,proto3" json:"verbosity,omitempty"`
	// contains filtered or unexported fields
}

type CreateModelResponseRequest_Text_Format struct {

	// Set to "text", "json_schema", or "json_object".
	Type string `protobuf:"bytes,1,opt,name=type,proto3" json:"type,omitempty"`
	// The following fields are only meaningful when the type is "json_schema".
	Name string `protobuf:"bytes,2,opt,name=name,proto3" json:"name,omitempty"`
	// encoded_schema is a base64 encoded JSON Schema object.
	//
	// The original value in the "schema" field is stripped by the server and converted
	// to "encoded_schema".
	//
	// The value of the field is converted back to the "schema" field when the request is being
	// sent to vLLM.
	EncodedSchema string `protobuf:"bytes,3,opt,name=encoded_schema,json=encodedSchema,proto3" json:"encoded_schema,omitempty"`
	Description   string `protobuf:"bytes,4,opt,name=description,proto3" json:"description,omitempty"`
	Strict        bool   `protobuf:"varint,5,opt,name=strict,proto3" json:"strict,omitempty"`
	// contains filtered or unexported fields
}

type CreateModelResponseRequest_ToolChoice struct {
	Type string `protobuf:"bytes,1,opt,name=type,proto3" json:"type,omitempty"`
	// name is meaningful for the hosted tool, function tool, MC tool, and custom tool.
	Name string `protobuf:"bytes,2,opt,name=name,proto3" json:"name,omitempty"`
	// mode is meaningful for the allowed tools.
	Mode string `protobuf:"bytes,3,opt,name=mode,proto3" json:"mode,omitempty"`
	// encoded_tools is meaningful for the allowed tools. It is a base64 encoded JSON object.
	//
	// The original value in the "tools" field is stripped by the server and converted
	// to "encoded_tools".
	//
	// The value of the field is converted back to the "tools" field when the request is being
	// sent to vLLM.
	EncodedTools string `protobuf:"bytes,4,opt,name=encoded_tools,json=encodedTools,proto3" json:"encoded_tools,omitempty"`
	// server_label is meaningful for the MCP tool.
	ServerLabel string `protobuf:"bytes,5,opt,name=server_label,json=serverLabel,proto3" json:"server_label,omitempty"`
	// contains filtered or unexported fields
}

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
}

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
}

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
}