causal_agent.parse_input

causal_agent.parse_input(query, dataset_path_arg=None, dataset_info=None, llm=None)[source]

Parse the user’s causal query using LLM and regex.

Parameters:

  • query (str) – The user’s causal question text.

  • dataset_path_arg (str | None) – Path to dataset if provided directly as an argument.

  • dataset_info (Dict | None) – Dictionary with dataset context (columns, types, etc.).

  • llm (langchain_core.language_models.BaseChatModel | None) – The shared LLM client instance.

Returns:

Dict containing parsed query information.

Return type:

Dict[str, Any]