forked from phoenix-oss/llama-stack-mirror
09269e2a44
# What does this PR do? This is a follow-up to #425. That PR allows for specifying models in the registry, but each entry needs to look like: ```yaml - identifier: ... provider_id: ... provider_resource_identifier: ... ``` This is headache-inducing. The current PR makes this situation better by adopting the shape of our APIs. Namely, we need the user to only specify `model-id`. The rest should be optional and figured out by the Stack. You can always override it. Here's what example `ollama` "full stack" registry looks like (we still need to kill or simplify shield_type crap): ```yaml models: - model_id: Llama3.2-3B-Instruct - model_id: Llama-Guard-3-1B shields: - shield_id: llama_guard shield_type: llama_guard ``` ## Test Plan See test plan for #425. Re-ran it.
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 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_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)
|
|
|
|
impls = await resolve_impls_for_test_v2(
|
|
[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 impls
|