phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-03 19:57:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(eval): use client.alpha for eval tests

Browse source
This commit is contained in:
Ashwin Bharambe 2025-09-30 13:02:33 -07:00
parent cc64093ae4
commit 73de235ef1
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
tests/integration/eval/test_eval.py
View file

@ -45,7 +45,7 @@ def test_evaluate_rows(llama_stack_client, text_model_id, scoring_fn_id):
list_benchmarks = llama_stack_client.benchmarks.list()
assert any(x.identifier == benchmark_id for x in list_benchmarks)
response = llama_stack_client.eval.evaluate_rows(
response = llama_stack_client.alpha.eval.evaluate_rows(
benchmark_id=benchmark_id,
input_rows=rows.data,
scoring_functions=scoring_functions,
@ -80,7 +80,7 @@ def test_evaluate_benchmark(llama_stack_client, text_model_id, scoring_fn_id):
scoring_functions=[scoring_fn_id],
)
response = llama_stack_client.eval.run_eval(
response = llama_stack_client.alpha.eval.run_eval(
benchmark_id=benchmark_id,
benchmark_config={
"eval_candidate": {
@ -93,10 +93,10 @@ 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.alpha.eval.jobs.status(job_id=response.job_id, benchmark_id=benchmark_id)
assert job_status and job_status.status == "completed"
eval_response = llama_stack_client.eval.jobs.retrieve(job_id=response.job_id, benchmark_id=benchmark_id)
eval_response = llama_stack_client.alpha.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