From d0882afa6104e1cd7590cff041697157a85c6ab0 Mon Sep 17 00:00:00 2001 From: Xi Yan Date: Fri, 21 Mar 2025 13:09:35 -0700 Subject: [PATCH] precommit --- tests/integration/eval/test_eval.py | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/tests/integration/eval/test_eval.py b/tests/integration/eval/test_eval.py index fbb44a4fa..6f454880a 100644 --- a/tests/integration/eval/test_eval.py +++ b/tests/integration/eval/test_eval.py @@ -21,9 +21,7 @@ def test_evaluate_rows(llama_stack_client, text_model_id, scoring_fn_id): purpose="eval/messages-answer", source={ "type": "uri", - "uri": data_url_from_file( - Path(__file__).parent.parent / "datasets" / "test_dataset.csv" - ), + "uri": data_url_from_file(Path(__file__).parent.parent / "datasets" / "test_dataset.csv"), }, ) 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", source={ "type": "uri", - "uri": data_url_from_file( - Path(__file__).parent.parent / "datasets" / "test_dataset.csv" - ), + "uri": data_url_from_file(Path(__file__).parent.parent / "datasets" / "test_dataset.csv"), }, ) 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" - eval_response = llama_stack_client.eval.jobs.retrieve( - job_id=response.job_id, benchmark_id=benchmark_id - ) + eval_response = llama_stack_client.eval.jobs.retrieve(job_id=response.job_id, benchmark_id=benchmark_id) assert eval_response is not None assert len(eval_response.generations) == 5 assert scoring_fn_id in eval_response.scores