agents.py — langchain Source File

Source Code

"""Schema definitions for representing agent actions, observations, and return values.

!!! warning

    The schema definitions are provided for backwards compatibility.

!!! warning

    New agents should be built using the
    [`langchain` library](https://pypi.org/project/langchain/), which provides a
    simpler and more flexible way to define agents.

    See docs on [building agents](https://docs.langchain.com/oss/python/langchain/agents).

Agents use language models to choose a sequence of actions to take.

A basic agent works in the following manner:

1. Given a prompt an agent uses an LLM to request an action to take
    (e.g., a tool to run).
2. The agent executes the action (e.g., runs the tool), and receives an observation.
3. The agent returns the observation to the LLM, which can then be used to generate
    the next action.
4. When the agent reaches a stopping condition, it returns a final return value.

The schemas for the agents themselves are defined in `langchain.agents.agent`.
"""

from __future__ import annotations

import json
from collections.abc import Sequence
from typing import Any, Literal

from langchain_core.load.serializable import Serializable
from langchain_core.messages import (
    AIMessage,
    BaseMessage,
    FunctionMessage,
    HumanMessage,
)


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
// ... (197 more lines)