ZeroShotAgent#

class langchain.agents.mrkl.base.ZeroShotAgent[source]#

Bases: Agent

Deprecated since version 0.1.0: Use create_react_agent() instead.

Agent for the MRKL chain.

Parameters:

output_parser – Output parser for the agent.

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 [Optional]#

Output parser to use for agent.

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

Async given input, decided what to do.

Parameters:
Returns:

Action specifying what tool to use.

Return type:

AgentAction | AgentFinish

classmethod create_prompt(tools: Sequence[BaseTool], prefix: str = 'Answer the following questions as best you can. You have access to the following tools:', suffix: str = 'Begin!\n\nQuestion: {input}\nThought:{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: List[str] | None = None) → PromptTemplate[source]#

Create prompt in the style of the zero shot agent.

Parameters:

  • tools (Sequence[BaseTool]) – List of tools the agent will have access to, used to format the prompt.

  • prefix (str) – String to put before the list of tools. Defaults to PREFIX.

  • suffix (str) – String to put after the list of tools. Defaults to SUFFIX.

  • format_instructions (str) – Instructions on how to use the tools. Defaults to FORMAT_INSTRUCTIONS

  • input_variables (List[str] | None) – List of input variables the final prompt will expect. Defaults to None.

Returns:

A PromptTemplate with the template assembled from the pieces here.

Return type:

PromptTemplate

classmethod from_llm_and_tools(llm: BaseLanguageModel, tools: Sequence[BaseTool], callback_manager: BaseCallbackManager | None = None, output_parser: AgentOutputParser | None = None, prefix: str = 'Answer the following questions as best you can. You have access to the following tools:', suffix: str = 'Begin!\n\nQuestion: {input}\nThought:{agent_scratchpad}', format_instructions: str = 'Use the following format:\n\nQuestion: the input question you must answer\nThought: you should always think about what to do\nAction: the action to take, should be one of [{tool_names}]\nAction Input: the input to the action\nObservation: the result of the action\n... (this Thought/Action/Action Input/Observation can repeat N times)\nThought: I now know the final answer\nFinal Answer: the final answer to the original input question', input_variables: List[str] | None = None, **kwargs: Any) → Agent[source]#

Construct an agent from an LLM and tools.

Parameters:

  • llm (BaseLanguageModel) – The LLM to use as the agent LLM.

  • tools (Sequence[BaseTool]) – The tools to use.

  • callback_manager (BaseCallbackManager | None) – The callback manager to use. Defaults to None.

  • output_parser (AgentOutputParser | None) – The output parser to use. Defaults to None.

  • prefix (str) – The prefix to use. Defaults to PREFIX.

  • suffix (str) – The suffix to use. Defaults to SUFFIX.

  • format_instructions (str) – The format instructions to use. Defaults to FORMAT_INSTRUCTIONS.

  • input_variables (List[str] | None) – The input variables to use. Defaults to None.

  • kwargs (Any) – Additional parameters to pass to the agent.

Return type:

Agent

get_allowed_tools() → List[str] | None#

Get allowed tools.

Return type:

List[str] | None

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

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#

Given input, decided what to do.

Parameters:
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#

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#

Return logging kwargs for tool run.

Return type:

Dict

property llm_prefix: str#

Prefix to append the llm call with.

Returns:

”

Return type:

“Thought

property observation_prefix: str#

Prefix to append the observation with.

Returns:

”

Return type:

“Observation

property return_values: List[str]#

Return values of the agent.