Agent#

class langchain.agents.agent.Agent[source]#

Bases: BaseSingleActionAgent

Deprecated since version 0.1.0: LangChain agents will continue to be supported, but it is recommended for new use cases to be built with LangGraph. LangGraph offers a more flexible and full-featured framework for building agents, including support for tool-calling, persistence of state, and human-in-the-loop workflows. See LangGraph documentation for more details: https://langchain-ai.github.io/langgraph/. Refer here for its pre-built ReAct agent: https://langchain-ai.github.io/langgraph/how-tos/create-react-agent/ It will be removed in None==1.0.

Agent that calls the language model and deciding the action.

This is driven by a LLMChain. The prompt in the LLMChain MUST include a variable called “agent_scratchpad” where the agent can put its intermediary work.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

param allowed_tools: List[str] | None = None#: Allowed tools for the agent. If None, all tools are allowed.

param llm_chain: LLMChain [Required]#: LLMChain to use for agent.

param output_parser: AgentOutputParser [Required]#: Output parser to use for agent.

async aplan(intermediate_steps: List[Tuple[AgentAction, str]], callbacks: list[BaseCallbackHandler] | BaseCallbackManager | None = None, **kwargs: Any) → AgentAction | AgentFinish[source]#

Async given input, decided what to do.

Parameters:

intermediate_steps (List[Tuple[AgentAction, str]]) – Steps the LLM has taken to date, along with observations.
callbacks (list[BaseCallbackHandler] | BaseCallbackManager | None) – Callbacks to run.
**kwargs (Any) – User inputs.

Returns:

Action specifying what tool to use.

Return type:

AgentAction | AgentFinish

abstract classmethod create_prompt(tools: Sequence[BaseTool]) → BasePromptTemplate[source]#

Create a prompt for this class.

Parameters:: tools (Sequence[BaseTool]) – Tools to use.
Returns:: Prompt template.
Return type:: BasePromptTemplate

classmethod from_llm_and_tools(llm: BaseLanguageModel, tools: Sequence[BaseTool], callback_manager: BaseCallbackManager | None = None, output_parser: AgentOutputParser | None = None, **kwargs: Any) → Agent[source]#

Construct an agent from an LLM and tools.

Parameters:

llm (BaseLanguageModel) – Language model to use.
tools (Sequence[BaseTool]) – Tools to use.
callback_manager (BaseCallbackManager | None) – Callback manager to use.
output_parser (AgentOutputParser | None) – Output parser to use.
kwargs (Any) – Additional arguments.

Returns:

Agent object.

Return type:

Agent

get_allowed_tools() → List[str] | None[source]#

Get allowed tools.

Return type:: List[str] | None

get_full_inputs(intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any) → Dict[str, Any][source]#

Create the full inputs for the LLMChain from intermediate steps.

Parameters:

intermediate_steps (List[Tuple[AgentAction, str]]) – Steps the LLM has taken to date, along with observations.
**kwargs (Any) – User inputs.

Returns:

Full inputs for the LLMChain.

Return type:

Dict[str, Any]

plan(intermediate_steps: List[Tuple[AgentAction, str]], callbacks: list[BaseCallbackHandler] | BaseCallbackManager | None = None, **kwargs: Any) → AgentAction | AgentFinish[source]#

Given input, decided what to do.

Parameters:

intermediate_steps (List[Tuple[AgentAction, str]]) – Steps the LLM has taken to date, along with observations.
callbacks (list[BaseCallbackHandler] | BaseCallbackManager | None) – Callbacks to run.
**kwargs (Any) – User inputs.

Returns:

Action specifying what tool to use.

Return type:

AgentAction | AgentFinish

return_stopped_response(early_stopping_method: str, intermediate_steps: List[Tuple[AgentAction, str]], **kwargs: Any) → AgentFinish[source]#

Return response when agent has been stopped due to max iterations.

Parameters:

early_stopping_method (str) – Method to use for early stopping.
intermediate_steps (List[Tuple[AgentAction, str]]) – Steps the LLM has taken to date, along with observations.
**kwargs (Any) – User inputs.

Returns:

Agent finish object.

Return type:

AgentFinish

Raises:

ValueError – If early_stopping_method is not in [‘force’, ‘generate’].

save(file_path: Path | str) → None#

Save the agent.

Parameters:: file_path (Path | str) – Path to file to save the agent to.
Return type:: None

Example: .. code-block:: python

# If working with agent executor agent.agent.save(file_path=”path/agent.yaml”)

tool_run_logging_kwargs() → Dict[source]#

Return logging kwargs for tool run.

Return type:: Dict

abstract property llm_prefix: str#: Prefix to append the LLM call with.

abstract property observation_prefix: str#: Prefix to append the observation with.

property return_values: List[str]#: Return values of the agent.