phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-07 09:49:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix eval

Browse source
This commit is contained in:
Xi Yan 2025-03-05 17:37:19 -08:00
parent 62a844c614
commit 9066b2ac12
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
tests/integration/eval/test_eval.py
View file

@ -83,7 +83,7 @@ def test_evaluate_benchmark(llama_stack_client, text_model_id, scoring_fn_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.result(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