llama-stack/llama_stack/providers/tests/scoring/fixtures.py
Xi Yan b4416b72fd
Folder restructure for evals/datasets/scoring (#419)
* rename evals related stuff

* fix datasetio

* fix scoring test

* localfs -> LocalFS

* refactor scoring

* refactor scoring

* remove 8b_correctness scoring_fn from tests

* tests w/ eval params

* scoring fn braintrust fixture

* import
2024-11-11 17:35:40 -05:00

68 lines
1.7 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.
import pytest
import pytest_asyncio
from llama_stack.distribution.datatypes import Api, Provider
from llama_stack.providers.tests.resolver import resolve_impls_for_test_v2
from ..conftest import ProviderFixture, remote_stack_fixture
@pytest.fixture(scope="session")
def scoring_remote() -> ProviderFixture:
return remote_stack_fixture()
@pytest.fixture(scope="session")
def scoring_meta_reference() -> ProviderFixture:
return ProviderFixture(
providers=[
Provider(
provider_id="meta-reference",
provider_type="meta-reference",
config={},
)
],
)
@pytest.fixture(scope="session")
def scoring_braintrust() -> ProviderFixture:
return ProviderFixture(
providers=[
Provider(
provider_id="braintrust",
provider_type="braintrust",
config={},
)
],
)
SCORING_FIXTURES = ["meta_reference", "remote", "braintrust"]
@pytest_asyncio.fixture(scope="session")
async def scoring_stack(request):
fixture_dict = request.param
providers = {}
provider_data = {}
for key in ["datasetio", "scoring", "inference"]:
fixture = request.getfixturevalue(f"{key}_{fixture_dict[key]}")
providers[key] = fixture.providers
if fixture.provider_data:
provider_data.update(fixture.provider_data)
impls = await resolve_impls_for_test_v2(
[Api.scoring, Api.datasetio, Api.inference],
providers,
provider_data,
)
return impls