mllm

type Call[T any] struct {
	ID       string `json:"id"`
	Index    int    `json:"index"`
	Type     string `json:"type"` // "function" always?
	Function struct {
		Name      string `json:"name"`
		Arguments T      `json:"arguments,omitempty"`
	} `json:"function"`
}

type ChatHandlerT interface {
	HandleChat(cr ChatResponse) error
}

type ChatMessage struct {
	MessageID uuid.UUID `gorm:"type:uuid;primaryKey;default:null;" json:"message_id,omitempty"` // MessageID is unique identifier for each message
	Message
	From      string    `json:"from,omitempty" gorm:"default:null"`
	CreatedAt time.Time `json:"created_at"`
}

type ChatMessageFormatter = func(cm ChatMessage) ([]Message, bool)

type ChatMessages []ChatMessage

type ChatRequest struct {
	Model     string           `json:"model,omitempty"`
	Messages  []Message        `json:"messages,omitempty"`
	Stream    bool             `json:"stream"`
	Think     *Think           `json:"reasoning_effort,omitempty"` // ollama endpoint "think" but /v1/chat/completions is "thinking"
	KeepAlive int              `json:"keep_alive,omitempty"`
	Tools     []json.Marshaler `json:"tools,omitempty"`
	*Options  `gorm:"type:jsonb;serializer:json;default:null"`
}

type ChatResponse struct {
	LLMID string `json:"id,omitempty" gorm:"-"`
	//	Object string
	Model       string          `json:"model"`
	Created     json.RawMessage `json:"created,omitempty"`
	Done        bool            `json:"done"` // for stream
	DoneReason  string          `json:"done_reason,omitempty"`
	DoneReason2 string          `json:"finish_reason,omitempty" gorm:"-"` // INTERNAL do not use
	Message     Message         `json:"message"`                          // for stream, handlers
	Stats       `gorm:"embedded"`
	Choices     []Choice `json:"choices,omitempty"` // INTERNAL do not use
}

type Choice struct {
	Index        int     `json:"index"`
	FinishReason *string `json:"finish_reason,omitempty"`
	Delta        Message `json:"delta"`
}

type E struct {
	Host  url.URL // the LLM API (required)
	Model string  // the model name (required)

	Client  *http.Client      `json:"-"` // custom http client (optional)
	Headers map[string]string `json:"-"` // custom headers (optional)
	Tools   []json.Marshaler  // Bring your own tools (optional)
	Options *Options          // e options (optional)

	// Writer if non-nil will be automatically added as a stream handler to [[E.Get]] and [[E.Stream]]
	Writer    io.Writer `json:"-"`
	ThinkPre  string    // optional, default used in [NewEndpoint]
	ThinkPost string    // optional, default used in [NewEndpoint]

	// Handlers added to all requests
	Handlers []StreamHandler `json:"-"`
}

type EmbedRequest struct {
	Model     string `json:"model"`
	Input     string `json:"input"`
	KeepAlive int    `json:"keep_alive,omitempty"`
	// Dimensions truncates the output embedding to the specified dimension.
	Dimensions int   `json:"dimensions,omitempty"`
	Truncate   *bool `json:"truncate,omitempty"`
	// Options lists model-specific options.
	Options map[string]any `json:"options,omitempty"`

	Host url.URL `json:"-"` // optional: override E.Host and LLM_EMBED_HOST env
}

type EmbedResponse struct {
	Model      string                `json:"model"`
	Embeddings []vector256.Vector256 `json:"embeddings"` // get resp.Embeddings[0]
	Data       []*struct {
		Embedding vector256.Vector256
	} `json:"data,omitempty"`
	Stats // limited for this endpoint
}

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

type Message struct {
	Role       string            `json:"role,omitempty"`
	Content    string            `json:"content,omitempty"`
	Reasoning  string            `json:"thinking,omitempty" gorm:"default:null"`
	Reasoning2 string            `json:"reasoning,omitempty" gorm:"-"` // Internal, DO NOT USE
	Reasoning3 string            `json:"reasoning_content,omitempty" gorm:"-"`
	ToolCalls  []json.RawMessage `json:"tool_calls,omitempty" gorm:"type:jsonb;serializer:json;default:null;"`
	ToolName   string            `json:"tool_name,omitempty" gorm:"default:null"`
	ToolCallID string            `json:"tool_call_id,omitempty" gorm:"default:null"`
	Images     [][]byte          `json:"images,omitempty" gorm:"serializer:json;type:jsonb;default:null;"`
}

type Messages []Message

type Options struct {
	Seed             int64    `json:"seed,omitempty"`
	Temperature      *float64 `json:"temperature,omitempty"` // 0.0 to 2.0
	NumCtx           int      `json:"num_ctx,omitempty"`
	TopP             *float64 `json:"top_p,omitempty"`             // 0.0 to 1.0
	TopK             *int     `json:"top_k,omitempty"`             // 1 to ???
	FrequencyPenalty *float64 `json:"frequency_penalty,omitempty"` // -2.0 to 2.0
	PresencePenalty  *float64 `json:"presence_penalty,omitempty"`  // -2.0 to 2.0
	//
	Debug bool `json:"-"` // internal, for printing full chatrequest before sending
}

type RawToolCall = Call[json.RawMessage]

type Stats struct {
	LoadDuration       time.Duration `json:"load_duration,omitempty"`
	PromptEvalDuration time.Duration `json:"prompt_eval_duration,omitempty"`
	EvalDuration       time.Duration `json:"eval_duration,omitempty"`
	TotalDuration      time.Duration `json:"total_duration,omitempty"`
	PromptEvalCount    int           `json:"prompt_eval_count,omitempty"`
	EvalCount          int           `json:"eval_count,omitempty"`
	Usage
}

type StreamHandler func(cr ChatResponse) error

type Think struct {
	Value `json:"-"`
}

type Tool struct {
	Spec json.RawMessage
	Exec any `json:"-"`
}

type Usage struct {
	TotalTokens  int `json:"total_tokens,omitempty"`
	PromptTokens int `json:"prompt_tokens,omitempty"`
}

type Value = any