llm

type GenerateParams struct {
	Temperature      float64  // Controls randomness (0.0 to 1.0)
	MaxTokens        int      // Maximum number of tokens to generate
	TopP             float64  // Alternative to temperature for nucleus sampling
	FrequencyPenalty float64  // Penalize frequent tokens (-2.0 to 2.0)
	PresencePenalty  float64  // Penalize tokens already present (-2.0 to 2.0)
	StopSequences    []string // Stop generation at these sequences
	TopK             int      // Limit vocabulary to top K tokens
	RepeatPenalty    float64  // Penalize token repetition
}

type Message struct {
	Role    string // "system", "user", "assistant"
	Content string
}