glm

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

type ChatModelConfig struct {

	// APIKey is your authentication key
	// Use OpenAI API key or Azure API key depending on the service
	// Required
	APIKey string `json:"api_key"`

	// Timeout specifies the maximum duration to wait for API responses
	// If HTTPClient is set, Timeout will not be used.
	// Optional. Default: no timeout
	Timeout time.Duration `json:"timeout"`

	// HTTPClient specifies the client to send HTTP requests.
	// If HTTPClient is set, Timeout will not be used.
	// Optional. Default &http.Client{Timeout: Timeout}
	HTTPClient *http.Client `json:"http_client"`

	// BaseURL specifies the QLM endpoint URL
	BaseURL string `json:"base_url"`

	// Model specifies the ID of the model to use
	// Required
	Model string `json:"model"`

	// MaxTokens limits the maximum number of tokens that can be generated in the chat completion
	// Optional. Default: model's maximum
	MaxTokens *int `json:"max_tokens,omitempty"`

	// Temperature specifies what sampling temperature to use
	// Generally recommend altering this or TopP but not both.
	// Range: 0.0 to 2.0. Higher values make output more random
	// Optional. Default: 1.0
	Temperature *float32 `json:"temperature,omitempty"`

	// TopP controls diversity via nucleus sampling
	// Generally recommend altering this or Temperature but not both.
	// Range: 0.0 to 1.0. Lower values make output more focused
	// Optional. Default: 1.0
	TopP *float32 `json:"top_p,omitempty"`

	// Stop sequences where the API will stop generating further tokens
	// Optional. Example: []string{"\n", "User:"}
	Stop []string `json:"stop,omitempty"`

	// PresencePenalty prevents repetition by penalizing tokens based on presence
	// Range: -2.0 to 2.0. Positive values increase likelihood of new topics
	// Optional. Default: 0
	PresencePenalty *float32 `json:"presence_penalty,omitempty"`

	// ResponseFormat specifies the format of the model's response
	// Optional. Use for structured outputs
	ResponseFormat *openai.ChatCompletionResponseFormat `json:"response_format,omitempty"`

	// Seed enables deterministic sampling for consistent outputs
	// Optional. Set for reproducible results
	Seed *int `json:"seed,omitempty"`

	// FrequencyPenalty prevents repetition by penalizing tokens based on frequency
	// Range: -2.0 to 2.0. Positive values decrease likelihood of repetition
	// Optional. Default: 0
	FrequencyPenalty *float32 `json:"frequency_penalty,omitempty"`

	// LogitBias modifies likelihood of specific tokens appearing in completion
	// Optional. Map token IDs to bias values from -100 to 100
	LogitBias map[string]int `json:"logit_bias,omitempty"`

	// User unique identifier representing end-user
	// Optional. Helps OpenAI monitor and detect abuse
	User *string `json:"user,omitempty"`

	// Thinking enables thinking mode
	// Optional. Default: base on the Model
	Thinking *string `json:"thinking,omitempty"`
}