Skip to content

chore: Deflake test_evaluation unit test #6887

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
copybara-service merged 1 commit into from
Jun 15, 2026
+16 −14
Merged

chore: Deflake test_evaluation unit test #6887

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
30 changes: 16 additions & 14 deletions tests/unit/vertexai/test_evaluation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -934,7 +934,7 @@ def test_compute_pointwise_metrics(self, api_transport):
scores = list(
test_result.metrics_table["test_pointwise_metric/score"].to_list()
)
assert scores == [5, 4] or scores == [4, 5]
assert sorted(scores) == [4, 5]
assert list(
test_result.metrics_table["test_pointwise_metric/explanation"].to_list()
) == [
Expand Down Expand Up @@ -994,9 +994,9 @@ def _pointwise_side_effect(**kwargs):
assert test_result.metrics_table["prompt"].equals(
_TEST_EVAL_DATASET_ALL_INCLUDED["prompt"]
)
assert list(
test_result.metrics_table["test_pointwise_metric_str/score"].to_list()
) == [5, 4]
assert sorted(
list(test_result.metrics_table["test_pointwise_metric_str/score"].to_list())
) == [4, 5]
assert list(
test_result.metrics_table["test_pointwise_metric_str/explanation"].to_list()
) == [
Expand Down Expand Up @@ -1049,9 +1049,9 @@ def test_compute_pointwise_metrics_metric_prompt_template_example(
"summarization_quality/explanation",
]
)
assert list(
test_result.metrics_table["summarization_quality/score"].to_list()
) == [5, 4]
assert sorted(
list(test_result.metrics_table["summarization_quality/score"].to_list())
) == [4, 5]
assert list(
test_result.metrics_table["summarization_quality/explanation"].to_list()
) == [
Expand Down Expand Up @@ -1166,9 +1166,9 @@ def _summarization_side_effect(**kwargs):
"source",
]
)
assert list(
test_result.metrics_table["summarization_quality/score"].to_list()
) == [5, 4]
assert sorted(
list(test_result.metrics_table["summarization_quality/score"].to_list())
) == [4, 5]
assert list(
test_result.metrics_table["summarization_quality/explanation"].to_list()
) == [
Expand Down Expand Up @@ -1595,9 +1595,9 @@ def test_compute_multiple_metrics(self, api_transport):
== 0.5
)

assert list(
test_result.metrics_table["summarization_quality/score"].to_list()
) == [5, 4]
assert sorted(
list(test_result.metrics_table["summarization_quality/score"].to_list())
) == [4, 5]
assert list(
test_result.metrics_table["summarization_quality/explanation"].to_list()
) == [
Expand Down Expand Up @@ -1884,7 +1884,9 @@ def test_runnable_response_eval_with_runnable_inference(self, api_transport):
"coherence/explanation",
]
)
assert list(test_result.metrics_table["coherence/score"].to_list()) == [5, 4]
assert sorted(
list(test_result.metrics_table["coherence/score"].to_list())
) == [4, 5]
assert list(test_result.metrics_table["coherence/explanation"].to_list()) == [
"explanation",
"explanation",
Expand Down
Loading