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 scoring

Browse source
This commit is contained in:
Xi Yan 2025-03-07 13:12:10 -08:00
parent e6355bfc3b
commit b4a22ed1b4
1 changed files with 0 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tests/integration/scoring/test_scoring.py
View file

@ -81,8 +81,6 @@ def test_scoring_functions_register(
def test_scoring_score(llama_stack_client): def test_scoring_score(llama_stack_client):
register_dataset(llama_stack_client, for_rag=True) register_dataset(llama_stack_client, for_rag=True)
response = llama_stack_client.datasets.list()
assert len(response) == 1
# scoring individual rows # scoring individual rows
rows = llama_stack_client.datasetio.get_rows_paginated( rows = llama_stack_client.datasetio.get_rows_paginated(
@ -119,8 +117,6 @@ def test_scoring_score(llama_stack_client):
def test_scoring_score_with_params_llm_as_judge(llama_stack_client, sample_judge_prompt_template, judge_model_id): def test_scoring_score_with_params_llm_as_judge(llama_stack_client, sample_judge_prompt_template, judge_model_id):
register_dataset(llama_stack_client, for_rag=True) register_dataset(llama_stack_client, for_rag=True)
response = llama_stack_client.datasets.list()
assert len(response) == 1
# scoring individual rows # scoring individual rows
rows = llama_stack_client.datasetio.get_rows_paginated( rows = llama_stack_client.datasetio.get_rows_paginated(