langchain.agents.mrkl.base.ZeroShotAgent

class langchain.agents.mrkl.base.ZeroShotAgent(*, llm_chain: LLMChain, output_parser: AgentOutputParser = None, allowed_tools: Optional[List[str]] = None)[source]

Bases: Agent

Agent for the MRKL chain.

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

Raises ValidationError if the input data cannot be parsed to form a valid model.

param allowed_tools: Optional[List[str]] = None
param llm_chain: langchain.chains.llm.LLMChain [Required]
param output_parser: langchain.agents.agent.AgentOutputParser [Optional]
async aplan(intermediate_steps: List[Tuple[AgentAction, str]], callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, **kwargs: Any) → Union[AgentAction, AgentFinish]

Given input, decided what to do.

Parameters

  • 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.

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: Optional[List[str]] = None) → PromptTemplate[source]

Create prompt in the style of the zero shot agent.

Parameters

  • tools – List of tools the agent will have access to, used to format the prompt.

  • prefix – String to put before the list of tools.

  • suffix – String to put after the list of tools.

  • input_variables – List of input variables the final prompt will expect.

Returns

A PromptTemplate with the template assembled from the pieces here.

dict(**kwargs: Any) → Dict

Return dictionary representation of agent.

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

Construct an agent from an LLM and tools.

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

Create the full inputs for the LLMChain from intermediate steps.

plan(intermediate_steps: List[Tuple[AgentAction, str]], callbacks: Optional[Union[List[BaseCallbackHandler], BaseCallbackManager]] = None, **kwargs: Any) → Union[AgentAction, AgentFinish]

Given input, decided what to do.

Parameters

  • 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.

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.

save(file_path: Union[Path, str]) → None

Save the agent.

Parameters

file_path – Path to file to save the agent to.

Example: .. code-block:: python

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

tool_run_logging_kwargs() → Dict
validator validate_prompt  »  all fields

Validate that prompt matches format.

property llm_prefix: str

Prefix to append the llm call with.

property observation_prefix: str

Prefix to append the observation with.

property return_values: List[str]

Return values of the agent.

Examples using ZeroShotAgent