Skip to content

feat: GenAI SDK client(evals) - Support StepBasedLLMMetric in create_evaluation_metric. #7254

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
Nov 3, 2026
Merged

feat: GenAI SDK client(evals) - Support StepBasedLLMMetric in create_evaluation_metric. #7254

Show file tree
Hide file tree
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
6 changes: 6 additions & 0 deletions agentplatform/_genai/_transformers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -263,6 +263,12 @@ def t_metric_for_registry(
"evaluation_function": metric.custom_function
}

# Step-based LLM metric
elif getv(metric, ["steps"]):
metric_payload_item["step_based_llm_metric_spec"] = _step_based_llm_metric_spec(
metric
)

# LLM-based metric
elif (hasattr(metric, "prompt_template") and metric.prompt_template) or (
hasattr(metric, "rubric_group_name") and metric.rubric_group_name
Expand Down
11 changes: 11 additions & 0 deletions tests/unit/agentplatform/genai/test_evals.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12350,6 +12350,17 @@ def test_t_metrics_code_preprocessor(self):
assert spec["preprocessor"] == {"code_config": {"code": self._PREPROCESS_CODE}}
assert "autorater_config" not in spec["steps"][0]

def test_t_metric_for_registry_builds_step_based_spec(self):
metric = self._metric()

payload = _transformers.t_metric_for_registry(metric)

assert payload == {
"step_based_llm_metric_spec": _transformers.t_metrics([metric])[0][
"step_based_llm_metric_spec"
]
}

@pytest.mark.parametrize(
"steps,error",
[
Expand Down
Loading