uqlm.longform.qa.question_generator.QuestionGenerator#

class uqlm.longform.qa.question_generator.QuestionGenerator(question_generator_llm, max_calls_per_min=None)#

Bases: object

__init__(question_generator_llm, max_calls_per_min=None)#

Class for decomposing responses into individual claims or sentences. This class is used as an intermediate step for longform UQ methods.

Parameters:

  • question_generator_llm (langchain BaseChatModel, default=None) – A langchain llm BaseChatModel. User is responsible for specifying temperature and other relevant parameters to the constructor of their llm object.

  • max_calls_per_min (int, default=None) – Specifies how many api calls to make per minute to avoid a rate limit error. By default, no limit is specified.

Methods

__init__(question_generator_llm[, ...])

Class for decomposing responses into individual claims or sentences.

generate_questions(claim_sets[, responses, ...])

async generate_questions(claim_sets, responses=None, num_questions=1, progress_bar=None)#
Return type:

List[str]

Parameters:

  • claim_sets (List[List[str]]) – List of original responses decomposed into lists of claims

  • responses (Optional[List[str]], default=None) – List of original responses to which the claim_sets belong

  • num_questions (int, default=1) – The number of questions to generate for each claim/sentence.

  • progress_bar (rich.progress.Progress, default=None) – If provided, displays a progress bar while scoring responses

References