phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 05:49:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

regen

Browse source
This commit is contained in:
Xi Yan 2025-03-12 16:21:55 -07:00
parent 6bcf682a56
commit fa480149dd
4 changed files with 12564 additions and 1092 deletions
Download patch file Download diff file Expand all files Collapse all files

6
tests/integration/scoring/test_scoring.py
View file

@ -113,6 +113,8 @@ def test_scoring_score(llama_stack_client):
for x in scoring_functions:
assert x in response.results
assert len(response.results[x].score_rows) == 5
llama_stack_client.datasets.unregister("test_dataset")
def test_scoring_score_with_params_llm_as_judge(llama_stack_client, sample_judge_prompt_template, judge_model_id):
@ -156,6 +158,8 @@ def test_scoring_score_with_params_llm_as_judge(llama_stack_client, sample_judge
for x in scoring_functions:
assert x in response.results
assert len(response.results[x].score_rows) == 5
llama_stack_client.datasets.unregister("test_dataset")
@pytest.mark.parametrize(
@ -223,3 +227,5 @@ def test_scoring_score_with_aggregation_functions(
assert x in response.results
assert len(response.results[x].score_rows) == len(rows.rows)
assert len(response.results[x].aggregated_results) == len(aggr_fns)
llama_stack_client.datasets.unregister("test_dataset")