motleycrew.applications.research_agent.question_prioritizer

Functions

create_question_prioritizer_langchain_tool([...])

Classes

QuestionPrioritizerInput(*, ...)	Input for the QuestionPrioritizerTool.
QuestionPrioritizerTool([prompt, llm])	Tool to prioritize subquestions based on the original question.

class motleycrew.applications.research_agent.question_prioritizer.QuestionPrioritizerTool(prompt: str | BasePromptTemplate = None, llm: BaseLanguageModel | None = None)

Bases: MotleyTool

Tool to prioritize subquestions based on the original question.

__init__(prompt: str | BasePromptTemplate = None, llm: BaseLanguageModel | None = None)

Initialize the MotleyTool.

Parameters:

• name – Name of the tool (required if tool is None).

• description – Description of the tool (required if tool is None).

• args_schema – Schema of the tool arguments (required if tool is None).

• tool – Langchain BaseTool to wrap.

• return_direct – If True, the tool’s output will be returned directly to the user.

• exceptions_to_reflect – List of exceptions to reflect back to the agent.

• retry_config – Configuration for retry behavior. If None, exceptions will not be retried.

class motleycrew.applications.research_agent.question_prioritizer.QuestionPrioritizerInput(*, original_question: Question, unanswered_questions: list[Question])

Bases: BaseModel

Input for the QuestionPrioritizerTool.

original_question: Question

unanswered_questions: list[Question]

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': True}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

motleycrew.applications.research_agent.question_prioritizer.create_question_prioritizer_langchain_tool(prompt: str | BasePromptTemplate = None, llm: BaseLanguageModel | None = None) → StructuredTool