langchain.js
    Preparing search index...

    Interface DynamicToolInput<ToolOutputT>

    Interface for the input parameters of the DynamicTool class.

    interface DynamicToolInput<ToolOutputT = ToolOutputType> {
        callbacks?: Callbacks;
        defaultConfig?: ToolRunnableConfig<Record<string, any>, any>;
        description: string;
        extras?: Record<string, unknown>;
        func: (
            input: string,
            runManager?: CallbackManagerForToolRun,
            config?: ToolRunnableConfig<Record<string, any>, any>,
        ) => Promise<ToolOutputT>;
        metadata?: Record<string, unknown>;
        name: string;
        responseFormat?: string;
        returnDirect?: boolean;
        tags?: string[];
        verbose?: boolean;
        verboseParsingErrors?: boolean;
    }

    Type Parameters

    • ToolOutputT = ToolOutputType

    Hierarchy (View Summary)

    Index

    Properties

    callbacks? defaultConfig? description extras? func metadata? name responseFormat? returnDirect? tags? verbose? verboseParsingErrors?

    Properties

    callbacks?: Callbacks
    defaultConfig?: ToolRunnableConfig<Record<string, any>, any>

    Default config object for the tool runnable.

    description: string
    extras?: Record<string, unknown>

    Optional provider-specific extra fields for the tool.

    This is used to pass provider-specific configuration that doesn't fit into standard tool fields.

    func: (
        input: string,
        runManager?: CallbackManagerForToolRun,
        config?: ToolRunnableConfig<Record<string, any>, any>,
    ) => Promise<ToolOutputT>
    metadata?: Record<string, unknown>

    Metadata for the tool.

    name: string
    responseFormat?: string

    The tool response format.

    If "content" then the output of the tool is interpreted as the contents of a ToolMessage. If "content_and_artifact" then the output is expected to be a two-tuple corresponding to the (content, artifact) of a ToolMessage.

    "content"
    returnDirect?: boolean

    Whether to return the tool's output directly.

    Setting this to true means that after the tool is called, an agent should stop looping.

    tags?: string[]
    verbose?: boolean
    verboseParsingErrors?: boolean

    Whether to show full details in the thrown parsing errors.

    false

    Settings

    Member Visibility

    On This Page

    Properties