output-sdk
    Preparing search index...

    Type Alias Prompt

    Configuration for LLM prompt generation.

    const prompt: Prompt = {
      name: 'summarizePrompt',
      config: {
        provider: 'anthropic',
        model: 'claude-opus-4-1',
        temperature: 0.7,
        maxTokens: 2048
      },
      messages: [...]
    };
    type Prompt = {
        config: {
            maxTokens?: number;
            model: string;
            provider: string;
            providerOptions?: Record<string, unknown>;
            temperature?: number;
            tools?: Record<string, Record<string, unknown>>;
        };
        messages: PromptMessage[];
        name: string;
    }
    Index

    Properties

    config messages name

    Properties

    config: {
        maxTokens?: number;
        model: string;
        provider: string;
        providerOptions?: Record<string, unknown>;
        temperature?: number;
        tools?: Record<string, Record<string, unknown>>;
    }

    General configuration for the LLM

    Type Declaration

    • OptionalmaxTokens?: number

      Maximum number of tokens in the response

    • model: string

      Model name/identifier

    • provider: string

      LLM provider (built-in: 'anthropic', 'openai', 'azure', 'vertex'; or any registered custom provider)

    • OptionalproviderOptions?: Record<string, unknown>

      Provider-specific options

    • Optionaltemperature?: number

      Generation temperature (0-2). Lower = more deterministic

    • Optionaltools?: Record<string, Record<string, unknown>>

      Provider-specific tools with configuration.

      tools:
        googleSearch:
          mode: MODE_DYNAMIC
          dynamicThreshold: 0.8

      tools:
        webSearch:
          searchContextSize: high
          filters:
            allowedDomains: [wikipedia.org]
    messages: PromptMessage[]

    Array of messages in the conversation

    name: string

    Name of the prompt file

    Settings

    Member Visibility

    On This Page

    Properties