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.
87 lines
2.5 KiB
Python
87 lines
2.5 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 enum import Enum
|
|
from typing import Any, Dict, List
|
|
|
|
from llama_stack.apis.common.type_system import (
|
|
ChatCompletionInputType,
|
|
CompletionInputType,
|
|
StringType,
|
|
)
|
|
|
|
from llama_stack.distribution.datatypes import Api
|
|
|
|
|
|
class ColumnName(Enum):
|
|
input_query = "input_query"
|
|
expected_answer = "expected_answer"
|
|
chat_completion_input = "chat_completion_input"
|
|
completion_input = "completion_input"
|
|
generated_answer = "generated_answer"
|
|
context = "context"
|
|
|
|
|
|
VALID_SCHEMAS_FOR_SCORING = [
|
|
{
|
|
ColumnName.input_query.value: StringType(),
|
|
ColumnName.expected_answer.value: StringType(),
|
|
ColumnName.generated_answer.value: StringType(),
|
|
},
|
|
{
|
|
ColumnName.input_query.value: StringType(),
|
|
ColumnName.expected_answer.value: StringType(),
|
|
ColumnName.generated_answer.value: StringType(),
|
|
ColumnName.context.value: StringType(),
|
|
},
|
|
]
|
|
|
|
VALID_SCHEMAS_FOR_EVAL = [
|
|
{
|
|
ColumnName.input_query.value: StringType(),
|
|
ColumnName.expected_answer.value: StringType(),
|
|
ColumnName.chat_completion_input.value: ChatCompletionInputType(),
|
|
},
|
|
{
|
|
ColumnName.input_query.value: StringType(),
|
|
ColumnName.expected_answer.value: StringType(),
|
|
ColumnName.completion_input.value: CompletionInputType(),
|
|
},
|
|
]
|
|
|
|
|
|
def get_valid_schemas(api_str: str):
|
|
if api_str == Api.scoring.value:
|
|
return VALID_SCHEMAS_FOR_SCORING
|
|
elif api_str == Api.eval.value:
|
|
return VALID_SCHEMAS_FOR_EVAL
|
|
else:
|
|
raise ValueError(f"Invalid API string: {api_str}")
|
|
|
|
|
|
class DataSchemaValidatorMixin:
|
|
def validate_dataset_schema(
|
|
self,
|
|
dataset_schema: Dict[str, Any],
|
|
expected_schemas: List[Dict[str, Any]],
|
|
):
|
|
if dataset_schema not in expected_schemas:
|
|
raise ValueError(
|
|
f"Dataset {dataset_schema} does not have a correct input schema in {expected_schemas}"
|
|
)
|
|
|
|
def validate_row_schema(
|
|
self,
|
|
input_row: Dict[str, Any],
|
|
expected_schemas: List[Dict[str, Any]],
|
|
):
|
|
for schema in expected_schemas:
|
|
if all(key in input_row for key in schema):
|
|
return
|
|
|
|
raise ValueError(
|
|
f"Input row {input_row} does not match any of the expected schemas in {expected_schemas}"
|
|
)
|