diff --git a/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py b/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py index ffc178ca8..24388177a 100644 --- a/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py +++ b/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py @@ -23,8 +23,8 @@ from llama_stack.providers.utils.common.data_schema_validator import ( ) from .config import LlmAsJudgeScoringConfig -from .scoring_fn.llm_as_judge_scoring_fn import LlmAsJudgeScoringFn from .scoring_fn.llm_as_judge_math_match_fn import LlmAsJudgeMathMatchFn +from .scoring_fn.llm_as_judge_scoring_fn import LlmAsJudgeScoringFn LLM_JUDGE_FN = [LlmAsJudgeScoringFn, LlmAsJudgeMathMatchFn] diff --git a/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_math_match_fn.py b/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_math_match_fn.py index 286738b96..5ac85a624 100644 --- a/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_math_match_fn.py +++ b/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_math_match_fn.py @@ -10,9 +10,10 @@ from llama_stack.apis.scoring import ScoringResultRow from llama_stack.apis.scoring_functions import ScoringFnParams from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn +from ...basic.utils.math_utils import extract_result_from_boxed from .fn_defs.llm_as_judge_405b_math_match import llm_as_judge_405b_math_match from .fn_defs.llm_as_judge_base import llm_as_judge_base -from ...basic.utils.math_utils import extract_result_from_boxed + class LlmAsJudgeMathMatchFn(RegisteredBaseScoringFn): """ @@ -51,8 +52,6 @@ class LlmAsJudgeMathMatchFn(RegisteredBaseScoringFn): expression2=extract_result_from_boxed(generated_answer), ) - print("judge_input_msg", judge_input_msg) - judge_response = await self.inference_api.chat_completion( model_id=fn_def.params.judge_model, messages=[