phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

precommit

Browse source
This commit is contained in:
Xi Yan 2025-03-16 16:27:29 -07:00
parent 5cf7779b8f
commit 63f1525165
2 changed files with 18 additions and 68 deletions
Download patch file Download diff file Expand all files Collapse all files

17
tests/integration/eval/test_eval.py
View file

@ -3,7 +3,6 @@
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
import os
import uuid
from pathlib import Path
@ -22,9 +21,7 @@ def test_evaluate_rows(llama_stack_client, text_model_id, scoring_fn_id):
purpose="eval/messages-answer",
source={
"type": "uri",
"uri": data_url_from_file(
Path(__file__).parent.parent / "datasets" / "test_dataset.csv"
),
"uri": data_url_from_file(Path(__file__).parent.parent / "datasets" / "test_dataset.csv"),
},
)
response = llama_stack_client.datasets.list()
@ -73,9 +70,7 @@ def test_evaluate_benchmark(llama_stack_client, text_model_id, scoring_fn_id):
purpose="eval/messages-answer",
source={
"type": "uri",
"uri": data_url_from_file(
Path(__file__).parent.parent / "datasets" / "test_dataset.csv"
),
"uri": data_url_from_file(Path(__file__).parent.parent / "datasets" / "test_dataset.csv"),
},
)
benchmark_id = str(uuid.uuid4())
@ -98,14 +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.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.retrieve(
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