phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-07 11:08:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix notebook

Browse source
This commit is contained in:
Xi Yan 2025-03-15 17:23:37 -07:00
parent 06f01f95c1
commit 1a07703d8b
2 changed files with 5 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/distribution/ui/page/evaluations/native_eval.py
View file

@ -229,9 +229,7 @@ def run_evaluation_3():
output_res[scoring_fn] = []
output_res[scoring_fn].append(eval_res.scores[scoring_fn].score_rows[0])
progress_text_container.write(
f"Expand to see current processed result ({i + 1} / {len(rows)})"
)
progress_text_container.write(f"Expand to see current processed result ({i + 1} / {len(rows)})")
results_container.json(eval_res, expanded=2)
progress_bar.progress(1.0, text="Evaluation complete!")

16
tests/integration/eval/test_eval.py
View file

@ -16,9 +16,7 @@ from ..datasetio.test_datasetio import register_dataset
@pytest.mark.parametrize("scoring_fn_id", ["basic::equality"])
def test_evaluate_rows(llama_stack_client, text_model_id, scoring_fn_id):
register_dataset(
llama_stack_client, for_generation=True, dataset_id="test_dataset_for_eval"
)
register_dataset(llama_stack_client, for_generation=True, dataset_id="test_dataset_for_eval")
response = llama_stack_client.datasets.list()
assert any(x.identifier == "test_dataset_for_eval" for x in response)
@ -61,9 +59,7 @@ def test_evaluate_rows(llama_stack_client, text_model_id, scoring_fn_id):
@pytest.mark.parametrize("scoring_fn_id", ["basic::subset_of"])
def test_evaluate_benchmark(llama_stack_client, text_model_id, scoring_fn_id):
register_dataset(
llama_stack_client, for_generation=True, dataset_id="test_dataset_for_eval_2"
)
register_dataset(llama_stack_client, for_generation=True, dataset_id="test_dataset_for_eval_2")
benchmark_id = str(uuid.uuid4())
llama_stack_client.benchmarks.register(
benchmark_id=benchmark_id,
@ -84,14 +80,10 @@ def test_evaluate_benchmark(llama_stack_client, text_model_id, scoring_fn_id):
},
)
assert response.job_id == "0"
job_status = llama_stack_client.eval.jobs.status(
job_id=response.job_id, benchmark_id=benchmark_id
)
job_status = llama_stack_client.eval.jobs.status(job_id=response.job_id, benchmark_id=benchmark_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