phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-31 16:01:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fixture return impl

Browse source
This commit is contained in:
Xi Yan 2024-11-07 21:22:18 -08:00
parent 9e8b41e605
commit 0dc2b9c6e4
2 changed files with 14 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_stack/providers/tests/eval/fixtures.py
View file

@ -52,11 +52,4 @@ async def eval_stack(request):
provider_data,
)
return (
impls[Api.eval],
impls[Api.eval_tasks],
impls[Api.scoring],
impls[Api.scoring_functions],
impls[Api.datasetio],
impls[Api.datasets],
)
return impls

16
llama_stack/providers/tests/eval/test_eval.py
View file

@ -14,6 +14,7 @@ from llama_stack.apis.eval.eval import (
EvalTaskDefWithProvider,
ModelCandidate,
)
from llama_stack.distribution.datatypes import Api
from llama_stack.providers.tests.datasetio.test_datasetio import register_dataset
@ -29,14 +30,19 @@ class Testeval:
async def test_eval_tasks_list(self, eval_stack):
# NOTE: this needs you to ensure that you are starting from a clean state
# but so far we don't have an unregister API unfortunately, so be careful
_, eval_tasks_impl, _, _, _, _ = eval_stack
eval_tasks_impl = eval_stack[Api.eval_tasks]
response = await eval_tasks_impl.list_eval_tasks()
assert isinstance(response, list)
assert len(response) == 0
@pytest.mark.asyncio
async def test_eval_evaluate_rows(self, eval_stack):
eval_impl, eval_tasks_impl, _, _, datasetio_impl, datasets_impl = eval_stack
eval_impl, eval_tasks_impl, datasetio_impl, datasets_impl = (
eval_stack[Api.eval],
eval_stack[Api.eval_tasks],
eval_stack[Api.datasetio],
eval_stack[Api.datasets],
)
await register_dataset(
datasets_impl, for_generation=True, dataset_id="test_dataset_for_eval"
)
@ -78,7 +84,11 @@ class Testeval:
@pytest.mark.asyncio
async def test_eval_run_eval(self, eval_stack):
eval_impl, eval_tasks_impl, _, _, datasetio_impl, datasets_impl = eval_stack
eval_impl, eval_tasks_impl, datasets_impl = (
eval_stack[Api.eval],
eval_stack[Api.eval_tasks],
eval_stack[Api.datasets],
)
await register_dataset(
datasets_impl, for_generation=True, dataset_id="test_dataset_for_eval"
)