forked from phoenix-oss/llama-stack-mirror
6deef1ece0
# What does this PR do? - fix eval tests to include tool_runtime fixtures - rebase eval for extracting memory retrieval context ## Test Plan ``` pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio llama_stack/providers/tests/eval/test_eval.py pytest -v -s -m braintrust_scoring_together_inference llama_stack/providers/tests/scoring/test_scoring.py ``` - With notebook: https://gist.github.com/yanxi0830/1260a6cb7ec42498a195b88422462a34 ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] 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.
111 lines
3.5 KiB
Python
111 lines
3.5 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
|
|
|
|
from ..agents.fixtures import AGENTS_FIXTURES
|
|
|
|
from ..conftest import get_provider_fixture_overrides
|
|
|
|
from ..datasetio.fixtures import DATASETIO_FIXTURES
|
|
from ..inference.fixtures import INFERENCE_FIXTURES
|
|
from ..memory.fixtures import MEMORY_FIXTURES
|
|
from ..safety.fixtures import SAFETY_FIXTURES
|
|
from ..scoring.fixtures import SCORING_FIXTURES
|
|
from ..tools.fixtures import TOOL_RUNTIME_FIXTURES
|
|
from .fixtures import EVAL_FIXTURES
|
|
|
|
DEFAULT_PROVIDER_COMBINATIONS = [
|
|
pytest.param(
|
|
{
|
|
"eval": "meta_reference",
|
|
"scoring": "basic",
|
|
"datasetio": "localfs",
|
|
"inference": "fireworks",
|
|
"agents": "meta_reference",
|
|
"safety": "llama_guard",
|
|
"memory": "faiss",
|
|
"tool_runtime": "memory_and_search",
|
|
},
|
|
id="meta_reference_eval_fireworks_inference",
|
|
marks=pytest.mark.meta_reference_eval_fireworks_inference,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"eval": "meta_reference",
|
|
"scoring": "basic",
|
|
"datasetio": "localfs",
|
|
"inference": "together",
|
|
"agents": "meta_reference",
|
|
"safety": "llama_guard",
|
|
"memory": "faiss",
|
|
"tool_runtime": "memory_and_search",
|
|
},
|
|
id="meta_reference_eval_together_inference",
|
|
marks=pytest.mark.meta_reference_eval_together_inference,
|
|
),
|
|
pytest.param(
|
|
{
|
|
"eval": "meta_reference",
|
|
"scoring": "basic",
|
|
"datasetio": "huggingface",
|
|
"inference": "together",
|
|
"agents": "meta_reference",
|
|
"safety": "llama_guard",
|
|
"memory": "faiss",
|
|
"tool_runtime": "memory_and_search",
|
|
},
|
|
id="meta_reference_eval_together_inference_huggingface_datasetio",
|
|
marks=pytest.mark.meta_reference_eval_together_inference_huggingface_datasetio,
|
|
),
|
|
]
|
|
|
|
|
|
def pytest_configure(config):
|
|
for fixture_name in [
|
|
"meta_reference_eval_fireworks_inference",
|
|
"meta_reference_eval_together_inference",
|
|
"meta_reference_eval_together_inference_huggingface_datasetio",
|
|
]:
|
|
config.addinivalue_line(
|
|
"markers",
|
|
f"{fixture_name}: marks tests as {fixture_name} specific",
|
|
)
|
|
|
|
|
|
def pytest_addoption(parser):
|
|
parser.addoption(
|
|
"--inference-model",
|
|
action="store",
|
|
default="meta-llama/Llama-3.2-3B-Instruct",
|
|
help="Specify the inference model to use for testing",
|
|
)
|
|
|
|
parser.addoption(
|
|
"--judge-model",
|
|
action="store",
|
|
default="meta-llama/Llama-3.1-8B-Instruct",
|
|
help="Specify the judge model to use for testing",
|
|
)
|
|
|
|
|
|
def pytest_generate_tests(metafunc):
|
|
if "eval_stack" in metafunc.fixturenames:
|
|
available_fixtures = {
|
|
"eval": EVAL_FIXTURES,
|
|
"scoring": SCORING_FIXTURES,
|
|
"datasetio": DATASETIO_FIXTURES,
|
|
"inference": INFERENCE_FIXTURES,
|
|
"agents": AGENTS_FIXTURES,
|
|
"safety": SAFETY_FIXTURES,
|
|
"memory": MEMORY_FIXTURES,
|
|
"tool_runtime": TOOL_RUNTIME_FIXTURES,
|
|
}
|
|
combinations = (
|
|
get_provider_fixture_overrides(metafunc.config, available_fixtures)
|
|
or DEFAULT_PROVIDER_COMBINATIONS
|
|
)
|
|
metafunc.parametrize("eval_stack", combinations, indirect=True)
|