Skip to main content

agrag.eval.answer.correctness

correctness(judge:DeepEvalBaseLLM, *, threshold:float = 0.5) -> BaseMetric

Build the answer correctness metric against the reference.

Parameters:

  • judge (DeepEvalBaseLLM) – The judge model.
  • threshold (float) – The minimum score that counts as success.

Returns:

  • BaseMetric – The correctness metric.