Type Alias LlmModelParams

LlmModelParams: {
    frequency_penalty?: number;
    max_tokens?: number;
    n?: number;
    presence_penalty?: number;
    temperature?: number;
    top_p?: number;
} & Record<string, any>

Model parameters for the LLM module configuration. These are set once at client construction and apply to every request made by this client. To use different parameters for a request, create a new OrchestrationClient instance. You can pass model-specific parameters, that are not specified in LlmModelParams (e.g. tool_choice, reasoning_effort), but behavior depends on the underlying model provider.

Example

params: { temperature: 0.7, max_tokens: 512 }

Example

params: { reasoning_effort: 'high' }

Type Alias LlmModelParams

Example

Example

Settings