phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-11 12:38:02 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

datasetio

Browse source
This commit is contained in:
Xi Yan 2025-03-12 16:47:40 -07:00
parent 97d6b87e05
commit 9dcf617556
2 changed files with 7 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

3
tests/integration/datasetio/test_datasetio.py
View file

@ -15,11 +15,12 @@ import pytest
# #
# LLAMA_STACK_CONFIG="template-name" pytest -v tests/integration/datasetio # LLAMA_STACK_CONFIG="template-name" pytest -v tests/integration/datasetio
@pytest.fixture @pytest.fixture
def test_dataset(llama_stack_client): def test_dataset(llama_stack_client):
register_dataset(llama_stack_client) register_dataset(llama_stack_client)
yield # This is where the test function will run yield # This is where the test function will run
# Teardown - this always runs, even if the test fails # Teardown - this always runs, even if the test fails
try: try:
llama_stack_client.datasets.unregister("test_dataset") llama_stack_client.datasets.unregister("test_dataset")

7
tests/integration/scoring/test_scoring.py
View file

@ -9,11 +9,12 @@ import pytest
from ..datasetio.test_datasetio import register_dataset from ..datasetio.test_datasetio import register_dataset
@pytest.fixture @pytest.fixture
def test_dataset_rag(llama_stack_client): def test_dataset_rag(llama_stack_client):
register_dataset(llama_stack_client, for_rag=True) register_dataset(llama_stack_client, for_rag=True)
yield # This is where the test function will run yield # This is where the test function will run
# Teardown - this always runs, even if the test fails # Teardown - this always runs, even if the test fails
try: try:
llama_stack_client.datasets.unregister("test_dataset") llama_stack_client.datasets.unregister("test_dataset")
@ -124,7 +125,9 @@ def test_scoring_score(llama_stack_client, test_dataset_rag):
assert len(response.results[x].score_rows) == 5 assert len(response.results[x].score_rows) == 5
def test_scoring_score_with_params_llm_as_judge(llama_stack_client, sample_judge_prompt_template, judge_model_id, test_dataset_rag): def test_scoring_score_with_params_llm_as_judge(
llama_stack_client, sample_judge_prompt_template, judge_model_id, test_dataset_rag
):
# scoring individual rows # scoring individual rows
rows = llama_stack_client.datasetio.get_rows_paginated( rows = llama_stack_client.datasetio.get_rows_paginated(
dataset_id="test_dataset", dataset_id="test_dataset",