Interface PromptComponents

Core components that form the foundation of any prompt construction. These are gathered from various sources (GMI state, user input, RAG) and then augmented with dynamically selected contextual elements. PromptComponents

interface PromptComponents {
    systemPrompts?: {
        content: string;
        priority?: number;
        source?: string;
    }[];
    conversationHistory?: ConversationMessage[];
    userInput?: null | string;
    visionInputs?: VisionInputData[];
    audioInput?: AudioInputData;
    tools?: ITool<any, any>[];
    toolSchemas?: Record<string, unknown>[];
    retrievedContext?: string | {
        source: string;
        content: string;
        relevance?: number;
        type?: string;
    }[];
    taskSpecificData?: Record<string, unknown>;
    customComponents?: Record<string, unknown>;
}

Properties

systemPrompts? conversationHistory? userInput? visionInputs? audioInput? tools? toolSchemas? retrievedContext? taskSpecificData? customComponents?

Properties

Optional systemPrompts

systemPrompts?: {
    content: string;
    priority?: number;
    source?: string;
}[]

System-level prompts with optional priority ordering. Higher priority usually means placed earlier or given more weight.

Type declaration

  • content: string
  • Optional priority?: number
  • Optional source?: string

Optional conversationHistory

conversationHistory?: ConversationMessage[]

Conversation history messages, typically an array of Message objects.

Optional userInput

userInput?: null | string

Current user input text.

Optional visionInputs

visionInputs?: VisionInputData[]

Visual inputs (images) if the target model supports vision.

Optional audioInput

audioInput?: AudioInputData

Audio input data references if the model or a pre-processing step handles audio.

Optional tools

tools?: ITool<any, any>[]

Available tools and their schemas, for models that support function/tool calling.

Optional toolSchemas

toolSchemas?: Record<string, unknown>[]

Pre-formatted tool/function schemas that should be forwarded to the model as-is. Useful when upstream logic has already normalized the schema definitions.

Optional retrievedContext

retrievedContext?: string | {
    source: string;
    content: string;
    relevance?: number;
    type?: string;
}[]

Retrieved context from a RAG system, to be incorporated into the prompt.

Optional taskSpecificData

taskSpecificData?: Record<string, unknown>

Task-specific data or parameters that need to be included in the prompt.

Optional customComponents

customComponents?: Record<string, unknown>

Additional custom components that templates might use.

Settings

Member Visibility

Theme

On This Page

systemPromptsconversationHistoryuserInputvisionInputsaudioInputtoolstoolSchemasretrievedContexttaskSpecificDatacustomComponents