BaseSingleActionAgent Class — langchain Architecture

Architecture documentation for the BaseSingleActionAgent class in agent.py from the langchain codebase.

Class python

Entity Profile

Dependency Diagram

graph TD
  2066c331_3189_1880_ba09_f5a3c375c553["BaseSingleActionAgent"]
  e1664047_3353_aa26_2a27_4fcd93c0a2f8["AgentType"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|extends| e1664047_3353_aa26_2a27_4fcd93c0a2f8
  0faae8c7_2812_be15_1073_b6537539cea8["agent.py"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|defined in| 0faae8c7_2812_be15_1073_b6537539cea8
  c0347dd9_4979_d672_ee07_20aa93cea076["return_values()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| c0347dd9_4979_d672_ee07_20aa93cea076
  1758f18d_e340_dd7b_0ea3_7bf08d14d9d7["get_allowed_tools()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| 1758f18d_e340_dd7b_0ea3_7bf08d14d9d7
  8994748a_d5a3_a0e6_1869_05215e6046e5["plan()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| 8994748a_d5a3_a0e6_1869_05215e6046e5
  3b577de0_fb5e_78d3_db9f_6c9a46325e38["aplan()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| 3b577de0_fb5e_78d3_db9f_6c9a46325e38
  b49ce6e7_0876_1c60_3f79_9d23060372b6["input_keys()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| b49ce6e7_0876_1c60_3f79_9d23060372b6
  a9280254_f4f8_cb71_2c6b_ad753985e93e["return_stopped_response()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| a9280254_f4f8_cb71_2c6b_ad753985e93e
  17edecaa_ea70_0ca0_a54a_689470a272cb["from_llm_and_tools()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| 17edecaa_ea70_0ca0_a54a_689470a272cb
  af16bc1c_c668_a100_0498_2bfa0da62b8e["_agent_type()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| af16bc1c_c668_a100_0498_2bfa0da62b8e
  7e22a32a_d4cd_934d_79bf_5d7579310aae["dict()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| 7e22a32a_d4cd_934d_79bf_5d7579310aae
  008c369d_f4fc_8ebd_1976_f8b1ae09e0b6["save()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| 008c369d_f4fc_8ebd_1976_f8b1ae09e0b6
  c66318ae_a2d5_5e44_2d5a_a995253a2e7b["tool_run_logging_kwargs()"]
  2066c331_3189_1880_ba09_f5a3c375c553 -->|method| c66318ae_a2d5_5e44_2d5a_a995253a2e7b

Relationship Graph

Source Code

libs/langchain/langchain_classic/agents/agent.py lines 55–218

class BaseSingleActionAgent(BaseModel):
    """Base Single Action Agent class."""

    @property
    def return_values(self) -> list[str]:
        """Return values of the agent."""
        return ["output"]

    def get_allowed_tools(self) -> list[str] | None:
        """Get allowed tools."""
        return None

    @abstractmethod
    def plan(
        self,
        intermediate_steps: list[tuple[AgentAction, str]],
        callbacks: Callbacks = None,
        **kwargs: Any,
    ) -> AgentAction | AgentFinish:
        """Given input, decided what to do.

        Args:
            intermediate_steps: Steps the LLM has taken to date,
                along with observations.
            callbacks: Callbacks to run.
            **kwargs: User inputs.

        Returns:
            Action specifying what tool to use.
        """

    @abstractmethod
    async def aplan(
        self,
        intermediate_steps: list[tuple[AgentAction, str]],
        callbacks: Callbacks = None,
        **kwargs: Any,
    ) -> AgentAction | AgentFinish:
        """Async given input, decided what to do.

        Args:
            intermediate_steps: Steps the LLM has taken to date,
                along with observations.
            callbacks: Callbacks to run.
            **kwargs: User inputs.

        Returns:
            Action specifying what tool to use.
        """

    @property
    @abstractmethod
    def input_keys(self) -> list[str]:
        """Return the input keys."""

    def return_stopped_response(
        self,
        early_stopping_method: str,
        intermediate_steps: list[tuple[AgentAction, str]],  # noqa: ARG002
        **_: Any,
    ) -> AgentFinish:
        """Return response when agent has been stopped due to max iterations.

        Args:
            early_stopping_method: Method to use for early stopping.
            intermediate_steps: Steps the LLM has taken to date,
                along with observations.

        Returns:
            Agent finish object.

        Raises:
            ValueError: If `early_stopping_method` is not supported.
        """
        if early_stopping_method == "force":
            # `force` just returns a constant string
            return AgentFinish(
                {"output": "Agent stopped due to iteration limit or time limit."},
                "",
            )
        msg = f"Got unsupported early_stopping_method `{early_stopping_method}`"