AgentAction Class — langchain Architecture

Architecture documentation for the AgentAction class in agents.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  a835cf98_21c1_0dc9_4dd3_8934600e2826["AgentAction"]
  f3658565_d05c_7f49_b7f8_622b7ef34f33["Serializable"]
  a835cf98_21c1_0dc9_4dd3_8934600e2826 -->|extends| f3658565_d05c_7f49_b7f8_622b7ef34f33
  81828515_0fcd_6cb4_96b8_62d4fca3e4ff["agents.py"]
  a835cf98_21c1_0dc9_4dd3_8934600e2826 -->|defined in| 81828515_0fcd_6cb4_96b8_62d4fca3e4ff
  c89b44dd_882c_3f11_5082_29934f6115e8["__init__()"]
  a835cf98_21c1_0dc9_4dd3_8934600e2826 -->|method| c89b44dd_882c_3f11_5082_29934f6115e8
  e36e696d_19cf_cd3e_d9b0_8307b2666490["is_lc_serializable()"]
  a835cf98_21c1_0dc9_4dd3_8934600e2826 -->|method| e36e696d_19cf_cd3e_d9b0_8307b2666490
  e5f8d2a5_9cb6_3841_758e_9fb4af8e44be["get_lc_namespace()"]
  a835cf98_21c1_0dc9_4dd3_8934600e2826 -->|method| e5f8d2a5_9cb6_3841_758e_9fb4af8e44be
  359cd72a_4765_207f_e3a1_6ec23bf7c8e4["messages()"]
  a835cf98_21c1_0dc9_4dd3_8934600e2826 -->|method| 359cd72a_4765_207f_e3a1_6ec23bf7c8e4

Relationship Graph

Source Code

libs/core/langchain_core/agents.py lines 44–102

class AgentAction(Serializable):
    """Represents a request to execute an action by an agent.

    The action consists of the name of the tool to execute and the input to pass
    to the tool. The log is used to pass along extra information about the action.
    """

    tool: str
    """The name of the `Tool` to execute."""

    tool_input: str | dict
    """The input to pass in to the `Tool`."""

    log: str
    """Additional information to log about the action.

    This log can be used in a few ways. First, it can be used to audit what exactly the
    LLM predicted to lead to this `(tool, tool_input)`.

    Second, it can be used in future iterations to show the LLMs prior thoughts. This is
    useful when `(tool, tool_input)` does not contain full information about the LLM
    prediction (for example, any `thought` before the tool/tool_input).
    """

    type: Literal["AgentAction"] = "AgentAction"

    # Override init to support instantiation by position for backward compat.
    def __init__(self, tool: str, tool_input: str | dict, log: str, **kwargs: Any):
        """Create an `AgentAction`.

        Args:
            tool: The name of the tool to execute.
            tool_input: The input to pass in to the `Tool`.
            log: Additional information to log about the action.
        """
        super().__init__(tool=tool, tool_input=tool_input, log=log, **kwargs)

    @classmethod
    def is_lc_serializable(cls) -> bool:
        """`AgentAction` is serializable.

        Returns:
            `True`
        """
        return True

    @classmethod
    def get_lc_namespace(cls) -> list[str]:
        """Get the namespace of the LangChain object.

        Returns:
            `["langchain", "schema", "agent"]`
        """
        return ["langchain", "schema", "agent"]

    @property
    def messages(self) -> Sequence[BaseMessage]:
        """Return the messages that correspond to this action."""
        return _convert_agent_action_to_messages(self)