XMLAgent#
- class langchain.agents.xml.base.XMLAgent[source]#
Bases:
BaseSingleActionAgent
Deprecated since version 0.1.0: Use
create_xml_agent()
instead. It will not be removed until langchain==1.0.Agent that uses XML tags.
- Parameters:
tools β list of tools the agent can choose from
llm_chain β The LLMChain to call to predict the next action
Examples
from langchain.agents import XMLAgent from langchain tools = ... model =
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.
- classmethod from_llm_and_tools(
- llm: BaseLanguageModel,
- tools: Sequence[BaseTool],
- callback_manager: BaseCallbackManager | None = None,
- **kwargs: Any,
Construct an agent from an LLM and tools.
- Parameters:
llm (BaseLanguageModel) β Language model to use.
tools (Sequence[BaseTool]) β Tools to use.
callback_manager (BaseCallbackManager | None) β Callback manager to use.
kwargs (Any) β Additional arguments.
- Returns:
Agent object.
- Return type:
- static get_default_output_parser() XMLAgentOutputParser [source]#
- Return type:
- static get_default_prompt() ChatPromptTemplate [source]#
- Return type:
- async aplan(
- intermediate_steps: list[tuple[AgentAction, str]],
- callbacks: list[BaseCallbackHandler] | BaseCallbackManager | None = None,
- **kwargs: Any,
Async given input, decided what to do.
- Parameters:
intermediate_steps (list[tuple[AgentAction, str]]) β Steps the LLM has taken to date, along with observations.
callbacks (list[BaseCallbackHandler] | BaseCallbackManager | None) β Callbacks to run.
**kwargs (Any) β User inputs.
- Returns:
Action specifying what tool to use.
- Return type:
- get_allowed_tools() list[str] | None #
- Return type:
list[str] | None
- plan(
- intermediate_steps: list[tuple[AgentAction, str]],
- callbacks: list[BaseCallbackHandler] | BaseCallbackManager | None = None,
- **kwargs: Any,
Given input, decided what to do.
- Parameters:
intermediate_steps (list[tuple[AgentAction, str]]) β Steps the LLM has taken to date, along with observations.
callbacks (list[BaseCallbackHandler] | BaseCallbackManager | None) β Callbacks to run.
**kwargs (Any) β User inputs.
- Returns:
Action specifying what tool to use.
- Return type:
- return_stopped_response(
- early_stopping_method: str,
- intermediate_steps: list[tuple[AgentAction, str]],
- **kwargs: Any,
Return response when agent has been stopped due to max iterations.
- Parameters:
early_stopping_method (str) β Method to use for early stopping.
intermediate_steps (list[tuple[AgentAction, str]]) β Steps the LLM has taken to date, along with observations.
**kwargs (Any) β User inputs.
- Returns:
Agent finish object.
- Return type:
- Raises:
ValueError β If early_stopping_method is not supported.
- save(file_path: Path | str) None #
Save the agent.
- Parameters:
file_path (Path | str) β 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=βpath/agent.yamlβ)
- tool_run_logging_kwargs() dict #
Return logging kwargs for tool run.
- Return type:
dict
- property return_values: list[str]#
Return values of the agent.