Skip to content

Evaluation: Remove parallel from composite evaluators #38168

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ninghu merged 12 commits into from
Oct 30, 2024
Merged

Evaluation: Remove parallel from composite evaluators #38168

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
094b440
Remove `parallel` from composite evaluators
ninghu Oct 29, 2024
fd8881c
Merge branch 'main' into ninhu/parallel
ninghu Oct 29, 2024
7949973
update recording
ninghu Oct 29, 2024
3c17258
update
ninghu Oct 29, 2024
04e4afc
output_dir check
ninghu Oct 30, 2024
07d49cf
fix the test recording
ninghu Oct 30, 2024
9c09c87
fix the failed unit-test
ninghu Oct 30, 2024
d7382d6
update changelog
ninghu Oct 30, 2024
796ad1e
update
ninghu Oct 30, 2024
7862ad5
fix black issue
ninghu Oct 30, 2024
4ee1fb9
revert output_path related change
ninghu Oct 30, 2024
55eba1e
Update sdk/evaluation/azure-ai-evaluation/CHANGELOG.md
ninghu Oct 30, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
update
  • Loading branch information
@ninghu
ninghu committed Oct 30, 2024
commit 796ad1e31ccd2ef344975c2f434c3861ec445a9c
2 changes: 1 addition & 1 deletion sdk/evaluation/azure-ai-evaluation/assets.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,5 +2,5 @@
"AssetsRepo": "Azure/azure-sdk-assets",
"AssetsRepoPrefixPath": "python",
"TagPrefix": "python/evaluation/azure-ai-evaluation",
"Tag": "python/evaluation/azure-ai-evaluation_65b36f6c7d"
"Tag": "python/evaluation/azure-ai-evaluation_daf1ed16fc"
}
12 changes: 7 additions & 5 deletions sdk/evaluation/azure-ai-evaluation/tests/e2etests/test_builtin_evaluators.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -336,8 +336,9 @@ def test_content_safety_service_unavailable(self, project_scope, azure_cred):

assert "RAI service is not available in this region" in exc_info._excinfo[1].args[0]

def test_composite_evaluator_qa(self, model_config):
qa_eval = QAEvaluator(model_config)
@pytest.mark.parametrize("parallel", [False, True])
def test_composite_evaluator_qa(self, model_config, parallel):
qa_eval = QAEvaluator(model_config, _parallel=parallel)
score = qa_eval(
query="Tokyo is the capital of which country?",
response="Japan",
Expand All @@ -354,9 +355,10 @@ def test_composite_evaluator_qa(self, model_config):
assert score["f1_score"] > 0.0

@pytest.mark.skipif(True, reason="Team-wide OpenAI Key unavailable, this can't be tested broadly yet.")
def test_composite_evaluator_qa_with_openai_config(self, non_azure_openai_model_config):
@pytest.mark.parametrize("parallel", [False, True])
def test_composite_evaluator_qa_with_openai_config(self, non_azure_openai_model_config, parallel):
# openai_config as in "not azure openai"
qa_eval = QAEvaluator(non_azure_openai_model_config)
qa_eval = QAEvaluator(non_azure_openai_model_config, _parallel=parallel)
score = qa_eval(
query="Tokyo is the capital of which country?",
response="Japan",
Expand Down Expand Up @@ -384,7 +386,7 @@ def test_composite_evaluator_qa_for_nans(self, model_config):
assert not math.isnan(score["similarity"])

def test_composite_evaluator_content_safety(self, project_scope, azure_cred):
safety_eval = ContentSafetyEvaluator(azure_cred, project_scope)
safety_eval = ContentSafetyEvaluator(azure_cred, project_scope, _parallel=False)
score = safety_eval(
query="Tokyo is the capital of which country?",
response="Japan",
Expand Down