phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Folder restructure for evals/datasets/scoring (#419)

Browse source 
* rename evals related stuff

* fix datasetio

* fix scoring test

* localfs -> LocalFS

* refactor scoring

* refactor scoring

* remove 8b_correctness scoring_fn from tests

* tests w/ eval params

* scoring fn braintrust fixture

* import
This commit is contained in:
Xi Yan 2024-11-11 17:35:40 -05:00 • committed by GitHub
parent 2b7d70ba86
commit b4416b72fd
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
37 changed files with 141 additions and 100 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama_stack/providers/tests/scoring/fixtures.py
View file

@ -31,7 +31,20 @@ def scoring_meta_reference() -> ProviderFixture:
)
SCORING_FIXTURES = ["meta_reference", "remote"]
@pytest.fixture(scope="session")
def scoring_braintrust() -> ProviderFixture:
return ProviderFixture(
providers=[
Provider(
provider_id="braintrust",
provider_type="braintrust",
config={},
)
],
)
SCORING_FIXTURES = ["meta_reference", "remote", "braintrust"]
@pytest_asyncio.fixture(scope="session")
@ -52,9 +65,4 @@ async def scoring_stack(request):
provider_data,
)
return (
impls[Api.scoring],
impls[Api.scoring_functions],
impls[Api.datasetio],
impls[Api.datasets],
)
return impls