schema

type ChatMessagePartType string

type CompletionTokensDetails struct {
	// ReasoningTokens tokens generated by the model for reasoning.
	// This is currently supported by OpenAI, Gemini, ARK and Qwen  chat models.
	// For other models, this field will be 0.
	ReasoningTokens int `json:"reasoning_tokens,omitempty"`
}

type ConvertOption func(*convertOptions)

type DataType string

type Document struct {
	// ID is the unique identifier of the document.
	ID string `json:"id"`
	// Content is the content of the document.
	Content string `json:"content"`
	// MetaData is the metadata of the document, can be used to store extra information.
	MetaData map[string]any `json:"meta_data"`
}

type FormatType uint8

type FunctionCall struct {
	// Name is the name of the function to call, it can be used to identify the specific function.
	Name string `json:"name,omitempty"`
	// Arguments is the arguments to call the function with, in JSON format.
	Arguments string `json:"arguments,omitempty"`
}

type ImageURLDetail string

type LogProb struct {
	// Token represents the text of the token, which is a contiguous sequence of characters
	// (e.g., a word, part of a word, or punctuation) as understood by the tokenization process used by the language model.
	Token string `json:"token"`
	// LogProb is the log probability of this token, if it is within the top 20 most likely tokens.
	// Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.
	LogProb float64 `json:"logprob"`
	// Bytes is a list of integers representing the UTF-8 bytes representation of the token.
	// Useful in instances where characters are represented by multiple tokens and
	// their byte representations must be combined to generate the correct text
	// representation. Can be `null` if there is no bytes representation for the token.
	Bytes []int64 `json:"bytes,omitempty"` // Omitting the field if it is null
	// TopLogProbs is a list of the most likely tokens and their log probability, at this token position.
	// In rare cases, there may be fewer than the number of requested top_logprobs returned.
	TopLogProbs []TopLogProb `json:"top_logprobs"`
}

type LogProbs struct {
	// Content is a list of message content tokens with log probability information.
	Content []LogProb `json:"content"`
}

type Message struct {
	Role RoleType `json:"role"`

	// Content is for user text input and model text output.
	Content string `json:"content"`

	// if MultiContent is not empty, use this instead of Content
	// if MultiContent is empty, use Content
	// Deprecated: Use UserInputMultiContent for user multimodal inputs and AssistantGenMultiContent for model multimodal outputs.
	MultiContent []ChatMessagePart `json:"multi_content,omitempty"`

	// UserInputMultiContent passes multimodal content provided by the user to the model.
	UserInputMultiContent []MessageInputPart `json:"user_input_multi_content,omitempty"`

	// AssistantGenMultiContent is for receiving multimodal output from the model.
	AssistantGenMultiContent []MessageOutputPart `json:"assistant_output_multi_content,omitempty"`

	Name string `json:"name,omitempty"`

	// only for AssistantMessage
	ToolCalls []ToolCall `json:"tool_calls,omitempty"`

	// only for ToolMessage
	ToolCallID string `json:"tool_call_id,omitempty"`
	// only for ToolMessage
	ToolName string `json:"tool_name,omitempty"`

	ResponseMeta *ResponseMeta `json:"response_meta,omitempty"`

	// ReasoningContent is the thinking process of the model, which will be included when the model returns reasoning content.
	ReasoningContent string `json:"reasoning_content,omitempty"`

	// customized information for model implementation
	Extra map[string]any `json:"extra,omitempty"`
}

type MessageInputAudio struct {
	MessagePartCommon
}

type MessageInputFile struct {
	MessagePartCommon

	// Name represents the filename.
	// Optional.
	Name string `json:"name,omitempty"`
}

type MessageInputImage struct {
	MessagePartCommon

	// Detail is the quality of the image url.
	Detail ImageURLDetail `json:"detail,omitempty"`
}

type MessageInputPart struct {
	Type ChatMessagePartType `json:"type"`

	Text string `json:"text,omitempty"`

	// Image is the image input of the part, it's used when Type is "image_url".
	Image *MessageInputImage `json:"image,omitempty"`

	// Audio  is the audio input of the part, it's used when Type is "audio_url".
	Audio *MessageInputAudio `json:"audio,omitempty"`

	// Video is the video input of the part, it's used when Type is "video_url".
	Video *MessageInputVideo `json:"video,omitempty"`

	// File is the file input of the part, it's used when Type is "file_url".
	File *MessageInputFile `json:"file,omitempty"`

	// Extra is used to store extra information.
	Extra map[string]any `json:"extra,omitempty"`
}

type MessageInputVideo struct {
	MessagePartCommon
}

type MessageJSONParseConfig struct {
	// parse from content or tool call, default is content.
	ParseFrom MessageParseFrom `json:"parse_from,omitempty"`

	// parse key path, default is empty.
	// must be a valid json path expression, eg: field.sub_field
	ParseKeyPath string `json:"parse_key_path,omitempty"`
}

type MessageJSONParser[T any] struct {
	ParseFrom    MessageParseFrom
	ParseKeyPath string
}

type MessageOutputAudio struct {
	MessagePartCommon
}

type MessageOutputImage struct {
	MessagePartCommon
}

type MessageOutputPart struct {
	// Type is the type of the part, e.g. "text", "image_url", "audio_url", "video_url".
	Type ChatMessagePartType `json:"type"`

	// Text is the text of the part, it's used when Type is "text".
	Text string `json:"text,omitempty"`

	// Image is the image output of the part, used when Type is ChatMessagePartTypeImageURL.
	Image *MessageOutputImage `json:"image,omitempty"`

	// Audio is the audio output of the part, used when Type is ChatMessagePartTypeAudioURL.
	Audio *MessageOutputAudio `json:"audio,omitempty"`

	// Video is the video output of the part, used when Type is ChatMessagePartTypeVideoURL.
	Video *MessageOutputVideo `json:"video,omitempty"`

	// Reasoning contains the reasoning content generated by the model.
	// Used when Type is ChatMessagePartTypeReasoning.
	Reasoning *MessageOutputReasoning `json:"reasoning,omitempty"`

	// Extra is used to store extra information.
	Extra map[string]any `json:"extra,omitempty"`

	// StreamingMeta contains metadata for streaming responses.
	// This field is typically used at runtime and not serialized.
	StreamingMeta *MessageStreamingMeta `json:"-"`
}

type MessageOutputReasoning struct {
	// Text is either the thought summary or the raw reasoning text itself.
	Text string `json:"text,omitempty"`

	// Signature contains encrypted reasoning tokens.
	// Required by some models when passing reasoning context back in subsequent requests.
	Signature string `json:"signature,omitempty"`
}

type MessageOutputVideo struct {
	MessagePartCommon
}

type MessageParseFrom string

type MessageParser[T any] interface {
	Parse(ctx context.Context, m *Message) (T, error)
}

type MessagePartCommon struct {
	// URL is primarily used for HTTP or HTTPS access links.
	// For data in the format 'data:[<mediatype>][;base64],<data>' (the 'data' URL Schema of RFC-2397 (https://www.rfc-editor.org/rfc/rfc2397)),
	// it is recommended to use Base64Data and MIMEType fields separately instead.
	URL *string `json:"url,omitempty"`

	// Base64Data represents the binary data in Base64 encoded string format.
	Base64Data *string `json:"base64data,omitempty"`

	// MIMEType is the mime type , eg."image/png",""audio/wav" etc.
	MIMEType string `json:"mime_type,omitempty"`

	// Deprecated: Use MessageOutputPart.Extra or MessageInputPart.Extra to set additional metadata instead.
	Extra map[string]any `json:"extra,omitempty"`
}

type MessageStreamingMeta struct {
	// Index specifies the index position of this part in the final response.
	// This is useful for reassembling multiple reasoning/content parts in correct order.
	Index int `json:"index,omitempty"`
}

type MessagesTemplate interface {
	Format(ctx context.Context, vs map[string]any, formatType FormatType) ([]*Message, error)
}

type ParameterInfo struct {
	// The type of the parameter.
	Type DataType
	// The element type of the parameter, only for array.
	ElemInfo *ParameterInfo
	// The sub parameters of the parameter, only for object.
	SubParams map[string]*ParameterInfo
	// The description of the parameter.
	Desc string
	// The enum values of the parameter, only for string.
	Enum []string
	// Whether the parameter is required.
	Required bool
}

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

type PromptTokenDetails struct {
	// Cached tokens present in the prompt.
	CachedTokens int `json:"cached_tokens"`
}

type ResponseMeta struct {
	// FinishReason is the reason why the chat response is finished.
	// It's usually "stop", "length", "tool_calls", "content_filter", "null". This is defined by chat model implementation.
	FinishReason string `json:"finish_reason,omitempty"`
	// Usage is the token usage of the chat response, whether usage exists depends on whether the chat model implementation returns.
	Usage *TokenUsage `json:"usage,omitempty"`
	// LogProbs is Log probability information.
	LogProbs *LogProbs `json:"logprobs,omitempty"`
}

type RoleType string

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

type StreamReader[T any] struct {
	// contains filtered or unexported fields
}

type StreamWriter[T any] struct {
	// contains filtered or unexported fields
}

type TokenUsage struct {
	// PromptTokens is the number of prompt tokens, including all the input tokens of this request.
	PromptTokens int `json:"prompt_tokens"`
	// PromptTokenDetails is a breakdown of the prompt tokens.
	PromptTokenDetails PromptTokenDetails `json:"prompt_token_details"`
	// CompletionTokens is the number of completion tokens.
	CompletionTokens int `json:"completion_tokens"`
	// TotalTokens is the total number of tokens.
	TotalTokens int `json:"total_tokens"`
	// CompletionTokensDetails is breakdown of completion tokens.
	CompletionTokensDetails CompletionTokensDetails `json:"completion_token_details"`
}

type ToolArgument struct {
	// Text contains the arguments for the tool call in JSON format.
	Text string `json:"text,omitempty"`
}

type ToolCall struct {
	// Index is used when there are multiple tool calls in a message.
	// In stream mode, it's used to identify the chunk of the tool call for merging.
	Index *int `json:"index,omitempty"`
	// ID is the id of the tool call, it can be used to identify the specific tool call.
	ID string `json:"id"`
	// Type is the type of the tool call, default is "function".
	Type string `json:"type"`
	// Function is the function call to be made.
	Function FunctionCall `json:"function"`

	// Extra is used to store extra information for the tool call.
	Extra map[string]any `json:"extra,omitempty"`
}

type ToolChoice string

type ToolInfo struct {
	// The unique name of the tool that clearly communicates its purpose.
	Name string
	// Used to tell the model how/when/why to use the tool.
	// You can provide few-shot examples as a part of the description.
	Desc string
	// Extra is the extra information for the tool.
	Extra map[string]any

	// The parameters the functions accepts (different models may require different parameter types).
	// can be described in two ways:
	//  - use params: schema.NewParamsOneOfByParams(params)
	//  - use jsonschema: schema.NewParamsOneOfByJSONSchema(jsonschema)
	// If is nil, signals that the tool does not need any input parameter
	*ParamsOneOf
}

type ToolMessageOption func(*toolMessageOptions)

type ToolOutputAudio struct {
	MessagePartCommon
}

type ToolOutputFile struct {
	MessagePartCommon
}

type ToolOutputImage struct {
	MessagePartCommon
}

type ToolOutputPart struct {

	// Type is the type of the part, e.g., "text", "image_url", "audio_url", "video_url".
	Type ToolPartType `json:"type"`

	// Text is the text content, used when Type is "text".
	Text string `json:"text,omitempty"`

	// Image is the image content, used when Type is ToolPartTypeImage.
	Image *ToolOutputImage `json:"image,omitempty"`

	// Audio is the audio content, used when Type is ToolPartTypeAudio.
	Audio *ToolOutputAudio `json:"audio,omitempty"`

	// Video is the video content, used when Type is ToolPartTypeVideo.
	Video *ToolOutputVideo `json:"video,omitempty"`

	// File is the file content, used when Type is ToolPartTypeFile.
	File *ToolOutputFile `json:"file,omitempty"`

	// Extra is used to store extra information.
	Extra map[string]any `json:"extra,omitempty"`
}

type ToolOutputVideo struct {
	MessagePartCommon
}

type ToolPartType string

type ToolResult struct {
	// Parts contains the multimodal output parts. Each part can be a different
	// type of content, like text, an image, or a file.
	Parts []ToolOutputPart `json:"parts,omitempty"`
}

type TopLogProb struct {
	// Token represents the text of the token, which is a contiguous sequence of characters
	// (e.g., a word, part of a word, or punctuation) as understood by the tokenization process used by the language model.
	Token string `json:"token"`
	// LogProb is the log probability of this token, if it is within the top 20 most likely tokens.
	// Otherwise, the value `-9999.0` is used to signify that the token is very unlikely.
	LogProb float64 `json:"logprob"`
	// Bytes is a list of integers representing the UTF-8 bytes representation of the token.
	// Useful in instances where characters are represented by multiple tokens and
	// their byte representations must be combined to generate the correct text
	// representation. Can be `null` if there is no bytes representation for the token.
	Bytes []int64 `json:"bytes,omitempty"`
}