ToolCall Class — langchain Architecture

Source Code

libs/core/langchain_core/messages/content.py lines 247–288

class ToolCall(TypedDict):
    """Represents an AI's request to call a tool.

    Example:
        ```python
        {"name": "foo", "args": {"a": 1}, "id": "123"}
        ```

        This represents a request to call the tool named "foo" with arguments {"a": 1}
        and an identifier of "123".

    !!! note "Factory function"

        `create_tool_call` may also be used as a factory to create a
        `ToolCall`. Benefits include:

        * Automatic ID generation (when not provided)
        * Required arguments strictly validated at creation time
    """

    type: Literal["tool_call"]
    """Used for discrimination."""

    id: str | None
    """An identifier associated with the tool call.

    An identifier is needed to associate a tool call request with a tool
    call result in events when multiple concurrent tool calls are made.
    """
    # TODO: Consider making this NotRequired[str] in the future.

    name: str
    """The name of the tool to be called."""

    args: dict[str, Any]
    """The arguments to the tool call."""

    index: NotRequired[int | str]
    """Index of block in aggregate response. Used during streaming."""

    extras: NotRequired[dict[str, Any]]
    """Provider-specific metadata."""