mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
c9e5578151
See https://github.com/meta-llama/llama-stack/issues/827 for the broader design. This PR finishes off all the stragglers and migrates everything to the new naming.
87 lines
2.1 KiB
Python
87 lines
2.1 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, ModelInput, Provider
|
|
|
|
from llama_stack.providers.tests.resolver import construct_stack_for_test
|
|
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="inline::meta-reference",
|
|
config={},
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
EVAL_FIXTURES = ["meta_reference", "remote"]
|
|
|
|
|
|
@pytest_asyncio.fixture(scope="session")
|
|
async def eval_stack(
|
|
request,
|
|
inference_model,
|
|
judge_model,
|
|
tool_group_input_memory,
|
|
tool_group_input_tavily_search,
|
|
):
|
|
fixture_dict = request.param
|
|
|
|
providers = {}
|
|
provider_data = {}
|
|
for key in [
|
|
"datasetio",
|
|
"eval",
|
|
"scoring",
|
|
"inference",
|
|
"agents",
|
|
"safety",
|
|
"vector_io",
|
|
"tool_runtime",
|
|
]:
|
|
fixture = request.getfixturevalue(f"{key}_{fixture_dict[key]}")
|
|
providers[key] = fixture.providers
|
|
if fixture.provider_data:
|
|
provider_data.update(fixture.provider_data)
|
|
|
|
test_stack = await construct_stack_for_test(
|
|
[
|
|
Api.eval,
|
|
Api.datasetio,
|
|
Api.inference,
|
|
Api.scoring,
|
|
Api.agents,
|
|
Api.safety,
|
|
Api.vector_io,
|
|
Api.tool_runtime,
|
|
],
|
|
providers,
|
|
provider_data,
|
|
models=[
|
|
ModelInput(model_id=model)
|
|
for model in [
|
|
inference_model,
|
|
judge_model,
|
|
]
|
|
],
|
|
tool_groups=[tool_group_input_memory, tool_group_input_tavily_search],
|
|
)
|
|
|
|
return test_stack.impls
|