phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-18 02:49:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix eval test

Browse source
This commit is contained in:
Xi Yan 2024-11-26 13:04:33 -08:00
parent e01d6d793c
commit 5e635d2e64
3 changed files with 35 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/distribution/request_headers.py
View file

@ -35,7 +35,7 @@ class NeedsRequestProviderData:
provider_data = validator(**val) provider_data = validator(**val)
return provider_data return provider_data
except Exception as e: except Exception as e:
log.error("Error parsing provider data", e) log.error(f"Error parsing provider data: {e}")
def set_request_provider_data(headers: Dict[str, str]): def set_request_provider_data(headers: Dict[str, str]):

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

@ -6,10 +6,14 @@
import pytest import pytest
from ..agents.fixtures import AGENTS_FIXTURES
from ..conftest import get_provider_fixture_overrides from ..conftest import get_provider_fixture_overrides
from ..datasetio.fixtures import DATASETIO_FIXTURES from ..datasetio.fixtures import DATASETIO_FIXTURES
from ..inference.fixtures import INFERENCE_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 ..scoring.fixtures import SCORING_FIXTURES
from .fixtures import EVAL_FIXTURES from .fixtures import EVAL_FIXTURES
@ -20,6 +24,9 @@ DEFAULT_PROVIDER_COMBINATIONS = [
"scoring": "basic", "scoring": "basic",
"datasetio": "localfs", "datasetio": "localfs",
"inference": "fireworks", "inference": "fireworks",
"agents": "meta_reference",
"safety": "llama_guard",
"memory": "faiss",
}, },
id="meta_reference_eval_fireworks_inference", id="meta_reference_eval_fireworks_inference",
marks=pytest.mark.meta_reference_eval_fireworks_inference, marks=pytest.mark.meta_reference_eval_fireworks_inference,
@ -30,6 +37,9 @@ DEFAULT_PROVIDER_COMBINATIONS = [
"scoring": "basic", "scoring": "basic",
"datasetio": "localfs", "datasetio": "localfs",
"inference": "together", "inference": "together",
"agents": "meta_reference",
"safety": "llama_guard",
"memory": "faiss",
}, },
id="meta_reference_eval_together_inference", id="meta_reference_eval_together_inference",
marks=pytest.mark.meta_reference_eval_together_inference, marks=pytest.mark.meta_reference_eval_together_inference,
@ -40,6 +50,9 @@ DEFAULT_PROVIDER_COMBINATIONS = [
"scoring": "basic", "scoring": "basic",
"datasetio": "huggingface", "datasetio": "huggingface",
"inference": "together", "inference": "together",
"agents": "meta_reference",
"safety": "llama_guard",
"memory": "faiss",
}, },
id="meta_reference_eval_together_inference_huggingface_datasetio", id="meta_reference_eval_together_inference_huggingface_datasetio",
marks=pytest.mark.meta_reference_eval_together_inference_huggingface_datasetio, marks=pytest.mark.meta_reference_eval_together_inference_huggingface_datasetio,
@ -75,6 +88,9 @@ def pytest_generate_tests(metafunc):
"scoring": SCORING_FIXTURES, "scoring": SCORING_FIXTURES,
"datasetio": DATASETIO_FIXTURES, "datasetio": DATASETIO_FIXTURES,
"inference": INFERENCE_FIXTURES, "inference": INFERENCE_FIXTURES,
"agents": AGENTS_FIXTURES,
"safety": SAFETY_FIXTURES,
"memory": MEMORY_FIXTURES,
} }
combinations = ( combinations = (
get_provider_fixture_overrides(metafunc.config, available_fixtures) get_provider_fixture_overrides(metafunc.config, available_fixtures)

20
llama_stack/providers/tests/eval/fixtures.py
View file

@ -40,14 +40,30 @@ async def eval_stack(request):
providers = {} providers = {}
provider_data = {} provider_data = {}
for key in ["datasetio", "eval", "scoring", "inference"]: for key in [
"datasetio",
"eval",
"scoring",
"inference",
"agents",
"safety",
"memory",
]:
fixture = request.getfixturevalue(f"{key}_{fixture_dict[key]}") fixture = request.getfixturevalue(f"{key}_{fixture_dict[key]}")
providers[key] = fixture.providers providers[key] = fixture.providers
if fixture.provider_data: if fixture.provider_data:
provider_data.update(fixture.provider_data) provider_data.update(fixture.provider_data)
test_stack = await construct_stack_for_test( test_stack = await construct_stack_for_test(
[Api.eval, Api.datasetio, Api.inference, Api.scoring], [
Api.eval,
Api.datasetio,
Api.inference,
Api.scoring,
Api.agents,
Api.safety,
Api.memory,
],
providers, providers,
provider_data, provider_data,
) )