phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 13:42:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

implement embedding generation in supported inference providers

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-12-09 12:48:56 -08:00
parent b896be2311
commit e167e9eb93
16 changed files with 383 additions and 29 deletions
Download patch file Download diff file Expand all files Collapse all files

27
llama_stack/providers/tests/inference/conftest.py
View file

@ -18,6 +18,12 @@ def pytest_addoption(parser):
default=None,
help="Specify the inference model to use for testing",
)
parser.addoption(
"--embedding-model",
action="store",
default=None,
help="Specify the embedding model to use for testing",
)
def pytest_configure(config):
@ -78,3 +84,24 @@ def pytest_generate_tests(metafunc):
):
fixtures = [stack.values[0]["inference"] for stack in filtered_stacks]
metafunc.parametrize("inference_stack", fixtures, indirect=True)
if "embedding_model" in metafunc.fixturenames:
model = metafunc.config.getoption("--embedding-model")
if not model:
raise ValueError(
"No embedding model specified. Please provide a valid embedding model."
)
params = [pytest.param(model, id="")]
metafunc.parametrize("embedding_model", params, indirect=True)
if "embedding_stack" in metafunc.fixturenames:
fixtures = INFERENCE_FIXTURES
if filtered_stacks := get_provider_fixture_overrides(
metafunc.config,
{
"inference": INFERENCE_FIXTURES,
},
):
fixtures = [stack.values[0]["inference"] for stack in filtered_stacks]
metafunc.parametrize("embedding_stack", fixtures, indirect=True)