inference

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

type GenOptions struct {
	ModelID     string  `json:"modelId"`
	MaxTokens   int     `json:"max_tokens"`
	Temperature float32 `json:"temperature"`
}

type InferenceProvider interface {
	// Generate performs a full generation request to the provider
	Generate(ctx context.Context, prompt string, options GenOptions) (string, error)
	// TestConnection verifies that the provider is reachable and functional
	TestConnection(ctx context.Context) (string, error)
	// ListModels retrieves a list of available models from the provider
	ListModels(ctx context.Context) ([]string, error)
	// PullModel requests the provider to download a new model
	PullModel(ctx context.Context, modelID string) error
}

type InferenceRequest struct {
	ModelID     string  `json:"modelId"`
	Prompt      string  `json:"prompt"`
	Context     string  `json:"context"`
	MaxTokens   int     `json:"max_tokens"`
	Temperature float32 `json:"temperature"`
}

type InferenceResponse struct {
	Text  string `json:"text"`
	Error string `json:"error,omitempty"`
}

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

type LMStudioProvider struct {
	BaseURL string
	Client  *http.Client
}

type ModelInfo struct {
	ID          string `json:"id"`
	Name        string `json:"name"`
	Size        int64  `json:"size"`
	Path        string `json:"path"`
	Downloaded  bool   `json:"downloaded"`
	DownloadURL string `json:"downloadUrl"`
	Description string `json:"description"`
	LastUsed    string `json:"lastUsed"`
}

type OllamaProvider struct {
	BaseURL string
	Client  *http.Client
}

type OpenAIProvider struct {
	BaseURL string
	Client  *http.Client
}

type WriteCounter struct {
	Total      int64
	Downloaded int64
	OnProgress func(float64)
}