forked from phoenix-oss/llama-stack-mirror
3a269c4635
# What does this PR do? - See https://github.com/meta-llama/llama-stack/pull/666 & https://github.com/meta-llama/llama-stack/pull/668 - Refactor BaseScoringFn to be just a minimal interface, add new RegistrableBaseScoring - Refactor data schema check - To separately evaluate retrieval component in RAG, we will have scoring functions needing "context" column additionally. - Refactor braintrust eval (more scoring fn added & tested in following PR) ## Test Plan ``` pytest -v -s -m llm_as_judge_scoring_together_inference scoring/test_scoring.py --judge-model meta-llama/Llama-3.2-3B-Instruct pytest -v -s -m basic_scoring_together_inference scoring/test_scoring.py pytest -v -s -m braintrust_scoring_together_inference scoring/test_scoring.py ``` <img width="847" alt="image" src="https://github.com/user-attachments/assets/d099cb2d-6f9c-4bdf-9d0d-f388cf758c0f" /> ``` pytest -v -s -m meta_reference_eval_together_inference eval/test_eval.py pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio eval/test_eval.py ``` <img width="850" alt="image" src="https://github.com/user-attachments/assets/dce28fc3-0493-4d34-820a-567260873cc8" /> ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.
59 lines
1.6 KiB
Python
59 lines
1.6 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from typing import Any, Dict, List, Optional, Protocol, runtime_checkable
|
|
|
|
from llama_models.schema_utils import json_schema_type, webmethod
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams
|
|
|
|
|
|
# mapping of metric to value
|
|
ScoringResultRow = Dict[str, Any]
|
|
|
|
|
|
@json_schema_type
|
|
class ScoringResult(BaseModel):
|
|
score_rows: List[ScoringResultRow]
|
|
# aggregated metrics to value
|
|
aggregated_results: Dict[str, Any]
|
|
|
|
|
|
@json_schema_type
|
|
class ScoreBatchResponse(BaseModel):
|
|
dataset_id: Optional[str] = None
|
|
results: Dict[str, ScoringResult]
|
|
|
|
|
|
@json_schema_type
|
|
class ScoreResponse(BaseModel):
|
|
# each key in the dict is a scoring function name
|
|
results: Dict[str, ScoringResult]
|
|
|
|
|
|
class ScoringFunctionStore(Protocol):
|
|
def get_scoring_function(self, scoring_fn_id: str) -> ScoringFn: ...
|
|
|
|
|
|
@runtime_checkable
|
|
class Scoring(Protocol):
|
|
scoring_function_store: ScoringFunctionStore
|
|
|
|
@webmethod(route="/scoring/score-batch")
|
|
async def score_batch(
|
|
self,
|
|
dataset_id: str,
|
|
scoring_functions: Dict[str, Optional[ScoringFnParams]],
|
|
save_results_dataset: bool = False,
|
|
) -> ScoreBatchResponse: ...
|
|
|
|
@webmethod(route="/scoring/score")
|
|
async def score(
|
|
self,
|
|
input_rows: List[Dict[str, Any]],
|
|
scoring_functions: Dict[str, Optional[ScoringFnParams]],
|
|
) -> ScoreResponse: ...
|