llama-stack/llama_stack/providers/tests/eval/fixtures.py
Xi Yan 6192bf43a4
[Evals API][10/n] API updates for EvalTaskDef + new test migration (#379)
* wip

* scoring fn api

* eval api

* eval task

* evaluate api update

* pre commit

* unwrap context -> config

* config field doc

* typo

* naming fix

* separate benchmark / app eval

* api name

* rename

* wip tests

* wip

* datasetio test

* delete unused

* fixture

* scoring resolve

* fix scoring register

* scoring test pass

* score batch

* scoring fix

* fix eval

* test eval works

* remove type ignore

* api refactor

* add default task_eval_id for routing

* add eval_id for jobs

* remove type ignore

* only keep 1 run_eval

* fix optional

* register task required

* register task required

* delete old tests

* delete old tests

* fixture return impl
2024-11-07 21:24:12 -08:00

55 lines
1.5 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.
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 eval_remote() -> ProviderFixture:
return remote_stack_fixture()
@pytest.fixture(scope="session")
def eval_meta_reference() -> ProviderFixture:
return ProviderFixture(
providers=[
Provider(
provider_id="meta-reference",
provider_type="meta-reference",
config={},
)
],
)
EVAL_FIXTURES = ["meta_reference", "remote"]
@pytest_asyncio.fixture(scope="session")
async def eval_stack(request):
fixture_dict = request.param
providers = {}
provider_data = {}
for key in ["datasetio", "eval", "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.eval, Api.datasetio, Api.inference, Api.scoring],
providers,
provider_data,
)
return impls