phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix: fix scoring tests (#1487)

Browse source 
# What does this PR do?
- fix scoring test

[//]: # (If resolving an issue, uncomment and update the line below)
[//]: # (Closes #[issue-number])

## Test Plan
```
LLAMA_STACK_CONFIG=fireworks pytest -v tests/integration/scoring/test_scoring.py --text-model meta-llama/Llama-3.3-70B-Instruct --judge-model meta-llama/Llama-3.3-70B-Instruct
```

<img width="1061" alt="image"
src="https://github.com/user-attachments/assets/740f9e6e-a654-4265-9db1-61481515a852"
/>


[//]: # (## Documentation)
This commit is contained in:
Xi Yan 2025-03-07 13:13:41 -08:00 • committed by GitHub
parent e6355bfc3b
commit a55aab5958
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
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):
register_dataset(llama_stack_client, for_rag=True)
response = llama_stack_client.datasets.list()
assert len(response) == 1
# scoring individual rows
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):
register_dataset(llama_stack_client, for_rag=True)
response = llama_stack_client.datasets.list()
assert len(response) == 1
# scoring individual rows
rows = llama_stack_client.datasetio.get_rows_paginated(