forked from phoenix-oss/llama-stack-mirror
12947ac19e
# What does this PR do? This PR kills the notion of "pure passthrough" remote providers. You cannot specify a single provider you must specify a whole distribution (stack) as remote. This PR also significantly fixes / upgrades testing infrastructure so you can now test against a remotely hosted stack server by just doing ```bash pytest -s -v -m remote test_agents.py \ --inference-model=Llama3.1-8B-Instruct --safety-shield=Llama-Guard-3-1B \ --env REMOTE_STACK_URL=http://localhost:5001 ``` Also fixed `test_agents_persistence.py` (which was broken) and killed some deprecated testing functions. ## Test Plan All the tests.
91 lines
2.3 KiB
Python
91 lines
2.3 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.apis.models import ModelInput
|
|
|
|
from llama_stack.distribution.datatypes import Api, Provider
|
|
|
|
from llama_stack.providers.tests.resolver import construct_stack_for_test
|
|
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_basic() -> ProviderFixture:
|
|
return ProviderFixture(
|
|
providers=[
|
|
Provider(
|
|
provider_id="basic",
|
|
provider_type="inline::basic",
|
|
config={},
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def scoring_braintrust() -> ProviderFixture:
|
|
return ProviderFixture(
|
|
providers=[
|
|
Provider(
|
|
provider_id="braintrust",
|
|
provider_type="inline::braintrust",
|
|
config={},
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def scoring_llm_as_judge() -> ProviderFixture:
|
|
return ProviderFixture(
|
|
providers=[
|
|
Provider(
|
|
provider_id="llm-as-judge",
|
|
provider_type="inline::llm-as-judge",
|
|
config={},
|
|
)
|
|
],
|
|
)
|
|
|
|
|
|
SCORING_FIXTURES = ["basic", "remote", "braintrust", "llm_as_judge"]
|
|
|
|
|
|
@pytest_asyncio.fixture(scope="session")
|
|
async def scoring_stack(request, inference_model):
|
|
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)
|
|
|
|
test_stack = await construct_stack_for_test(
|
|
[Api.scoring, Api.datasetio, Api.inference],
|
|
providers,
|
|
provider_data,
|
|
models=[
|
|
ModelInput(model_id=model)
|
|
for model in [
|
|
inference_model,
|
|
"Llama3.1-405B-Instruct",
|
|
"Llama3.1-8B-Instruct",
|
|
]
|
|
],
|
|
)
|
|
|
|
return test_stack.impls
|