phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-06 02:32:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

precommit

Browse source
This commit is contained in:
Xi Yan 2025-03-21 13:09:35 -07:00
parent 72f0550fb9
commit d0882afa61
1 changed files with 3 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

12
tests/integration/eval/test_eval.py
View file

@ -21,9 +21,7 @@ def test_evaluate_rows(llama_stack_client, text_model_id, scoring_fn_id):
purpose="eval/messages-answer", purpose="eval/messages-answer",
source={ source={
"type": "uri", "type": "uri",
"uri": data_url_from_file( "uri": data_url_from_file(Path(__file__).parent.parent / "datasets" / "test_dataset.csv"),
Path(__file__).parent.parent / "datasets" / "test_dataset.csv"
),
}, },
) )
response = llama_stack_client.datasets.list() response = llama_stack_client.datasets.list()
@ -72,9 +70,7 @@ def test_evaluate_benchmark(llama_stack_client, text_model_id, scoring_fn_id):
purpose="eval/messages-answer", purpose="eval/messages-answer",
source={ source={
"type": "uri", "type": "uri",
"uri": data_url_from_file( "uri": data_url_from_file(Path(__file__).parent.parent / "datasets" / "test_dataset.csv"),
Path(__file__).parent.parent / "datasets" / "test_dataset.csv"
),
}, },
) )
benchmark_id = str(uuid.uuid4()) benchmark_id = str(uuid.uuid4())
@ -103,9 +99,7 @@ def test_evaluate_benchmark(llama_stack_client, text_model_id, scoring_fn_id):
# ) # )
# assert job_status and job_status == "completed" # assert job_status and job_status == "completed"
eval_response = llama_stack_client.eval.jobs.retrieve( eval_response = llama_stack_client.eval.jobs.retrieve(job_id=response.job_id, benchmark_id=benchmark_id)
job_id=response.job_id, benchmark_id=benchmark_id
)
assert eval_response is not None assert eval_response is not None
assert len(eval_response.generations) == 5 assert len(eval_response.generations) == 5
assert scoring_fn_id in eval_response.scores assert scoring_fn_id in eval_response.scores