From a55aab595872e69ff33f6defcbbfe969ed00ed98 Mon Sep 17 00:00:00 2001
From: Xi Yan <xiyan@meta.com>
Date: Fri, 7 Mar 2025 13:13:41 -0800
Subject: [PATCH] fix: fix scoring tests (#1487)

# 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)
---
 tests/integration/scoring/test_scoring.py | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/tests/integration/scoring/test_scoring.py b/tests/integration/scoring/test_scoring.py
index ecf3b9425..2fcdf54e2 100644
--- a/tests/integration/scoring/test_scoring.py
+++ b/tests/integration/scoring/test_scoring.py
@@ -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(