gemini

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

type ModelsClient interface {
	GenerateContent(ctx context.Context, model string, contents []*genai.Content, config *genai.GenerateContentConfig) (*genai.GenerateContentResponse, error)
}

type Options struct {
	// Client is the underlying Gen AI models client.
	Client ModelsClient

	// DefaultModel is the model identifier used when Request.Model is empty.
	DefaultModel string

	// HighModel is used when Request.ModelClass is high-reasoning and
	// Request.Model is empty.
	HighModel string

	// SmallModel is used when Request.ModelClass is small and Request.Model is
	// empty.
	SmallModel string

	// MaxTokens is the default completion token cap when Request.MaxTokens is
	// unset.
	MaxTokens int

	// Temperature is the default sampling temperature when Request.Temperature
	// is unset.
	Temperature float32

	// ThinkingBudget is the default thinking-token budget when thinking is
	// enabled without a per-request budget.
	ThinkingBudget int
}

type VertexOptions struct {
	// ProjectID is the Google Cloud project used for Vertex AI requests.
	ProjectID string

	// Location is the Google Cloud location or region used for Vertex AI
	// requests.
	Location string

	// APIKey optionally configures API-key auth for Vertex AI. Leave empty
	// to use Credentials or Application Default Credentials.
	APIKey string

	// Credentials optionally supplies explicit Google Cloud credentials.
	Credentials *auth.Credentials

	// HTTPClient optionally supplies the HTTP client used by the Gen AI SDK.
	HTTPClient *http.Client

	// HTTPOptions optionally overrides Gen AI SDK HTTP behavior.
	HTTPOptions genai.HTTPOptions

	// DefaultModel is the model identifier used when Request.Model is empty.
	DefaultModel string

	// HighModel is used when Request.ModelClass is high-reasoning and
	// Request.Model is empty.
	HighModel string

	// SmallModel is used when Request.ModelClass is small and Request.Model is
	// empty.
	SmallModel string

	// MaxTokens is the default completion token cap when Request.MaxTokens is
	// unset.
	MaxTokens int

	// Temperature is the default sampling temperature when Request.Temperature
	// is unset.
	Temperature float32

	// ThinkingBudget is the default thinking-token budget when thinking is
	// enabled without a per-request budget.
	ThinkingBudget int
}