forked from phoenix-oss/llama-stack-mirror
c79b087552
# Context For test automation, the end goal is to run a single pytest command from root test directory (llama_stack/providers/tests/.) such that we execute push-blocking tests The work plan: 1) trigger pytest from llama_stack/providers/tests/. 2) use config file to determine what tests and parametrization we want to run # What does this PR do? 1) consolidates the "inference-models" / "embedding-model" / "judge-model" ... options in root conftest.py. Without this change, we will hit into error when trying to run `pytest /Users/sxyi/llama-stack/llama_stack/providers/tests/.` because of duplicated `addoptions` definitions across child conftest files. 2) Add a `config` option to specify test config in YAML. (see [`ci_test_config.yaml`](https://gist.github.com/sixianyi0721/5b37fbce4069139445c2f06f6e42f87e) for example config file) For provider_fixtures, we allow users to use either a default fixture combination or define their own {api:provider} combinations. ``` memory: .... fixtures: provider_fixtures: - default_fixture_param_id: ollama // use default fixture combination with param_id="ollama" in [providers/tests/memory/conftest.py](https://fburl.com/mtjzwsmk) - inference: sentence_transformers memory: faiss - default_fixture_param_id: chroma ``` 3) generate tests according to the config. Logic lives in two places: a) in `{api}/conftest.py::pytest_generate_tests`, we read from config to do parametrization. b) after test collection, in `pytest_collection_modifyitems`, we filter the tests to include only functions listed in config. ## Test Plan 1) `pytest /Users/sxyi/llama-stack/llama_stack/providers/tests/. --collect-only --config=ci_test_config.yaml` Using `--collect-only` tag to print the pytests listed in the config file (`ci_test_config.yaml`). output: [gist](https://gist.github.com/sixianyi0721/05145e60d4d085c17cfb304beeb1e60e) 2) sanity check on `--inference-model` option ``` pytest -v -s -k "ollama" --inference-model="meta-llama/Llama-3.1-8B-Instruct" ./llama_stack/providers/tests/inference/test_text_inference.py ``` ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [x] Ran pre-commit to handle lint / formatting issues. - [x] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.
102 lines
2.8 KiB
Python
102 lines
2.8 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
|
|
|
|
from ..conftest import get_provider_fixture_overrides
|
|
|
|
from ..inference.fixtures import INFERENCE_FIXTURES
|
|
from .fixtures import SAFETY_FIXTURES
|
|
|
|
|
|
DEFAULT_PROVIDER_COMBINATIONS = [
|
|
pytest.param(
|
|
{
|
|
"inference": "meta_reference",
|
|
"safety": "llama_guard",
|
|
},
|
|
id="meta_reference",
|
|
marks=pytest.mark.meta_reference,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "ollama",
|
|
"safety": "llama_guard",
|
|
},
|
|
id="ollama",
|
|
marks=pytest.mark.ollama,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "together",
|
|
"safety": "llama_guard",
|
|
},
|
|
id="together",
|
|
marks=pytest.mark.together,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "bedrock",
|
|
"safety": "bedrock",
|
|
},
|
|
id="bedrock",
|
|
marks=pytest.mark.bedrock,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"inference": "remote",
|
|
"safety": "remote",
|
|
},
|
|
id="remote",
|
|
marks=pytest.mark.remote,
|
|
),
|
|
]
|
|
|
|
|
|
def pytest_configure(config):
|
|
for mark in ["meta_reference", "ollama", "together", "remote", "bedrock"]:
|
|
config.addinivalue_line(
|
|
"markers",
|
|
f"{mark}: marks tests as {mark} specific",
|
|
)
|
|
|
|
|
|
SAFETY_SHIELD_PARAMS = [
|
|
pytest.param(
|
|
"meta-llama/Llama-Guard-3-1B", marks=pytest.mark.guard_1b, id="guard_1b"
|
|
),
|
|
]
|
|
|
|
|
|
def pytest_generate_tests(metafunc):
|
|
# We use this method to make sure we have built-in simple combos for safety tests
|
|
# But a user can also pass in a custom combination via the CLI by doing
|
|
# `--providers inference=together,safety=meta_reference`
|
|
|
|
if "safety_shield" in metafunc.fixturenames:
|
|
shield_id = metafunc.config.getoption("--safety-shield")
|
|
if shield_id:
|
|
assert shield_id.startswith("meta-llama/")
|
|
params = [pytest.param(shield_id, id="")]
|
|
else:
|
|
params = SAFETY_SHIELD_PARAMS
|
|
for fixture in ["inference_model", "safety_shield"]:
|
|
metafunc.parametrize(
|
|
fixture,
|
|
params,
|
|
indirect=True,
|
|
)
|
|
|
|
if "safety_stack" in metafunc.fixturenames:
|
|
available_fixtures = {
|
|
"inference": INFERENCE_FIXTURES,
|
|
"safety": SAFETY_FIXTURES,
|
|
}
|
|
combinations = (
|
|
get_provider_fixture_overrides(metafunc.config, available_fixtures)
|
|
or DEFAULT_PROVIDER_COMBINATIONS
|
|
)
|
|
metafunc.parametrize("safety_stack", combinations, indirect=True)
|