fmt

python/docs/create_api_rst.py

@@ -105,9 +105,7 @@ def _load_module_members(module_path: str, namespace: str) -> ModuleMembers:
                 else (
                     "enum"
                     if issubclass(type_, Enum)
-                    else "Pydantic"
-                    if issubclass(type_, BaseModel)
-                    else "Regular"
+                    else "Pydantic" if issubclass(type_, BaseModel) else "Regular"
                 )
             )
             # if hasattr(type_, "__slots__"):

python/langsmith/evaluation/_runner.py

@@ -1665,14 +1665,14 @@ def _score(
                     yield result
 
     def _apply_summary_evaluators(
-        self,
-        summary_evaluators: Sequence[SUMMARY_EVALUATOR_T],
+        self, summary_evaluators: Sequence[SUMMARY_EVALUATOR_T]
     ) -> Generator[EvaluationResults, None, None]:
         runs, examples, evaluation_results = [], [], []
         for row in self.get_results():
             runs.append(row["run"])
             examples.append(row["example"])
             evaluation_results.append(row["evaluation_results"]["results"])
+
         aggregate_feedback = []
         with ls_utils.ContextThreadPoolExecutor() as executor:
             project_id = self._get_experiment().id if self._upload_results else None

python/tests/unit_tests/evaluation/test_runner.py

@@ -978,7 +978,7 @@ def summary_eval_outputs_reference(outputs, reference_outputs):
     return min([len(x["response"]) for x in outputs])
 
 
-def summary_eval_outputs_reference(evaluation_results):
+def summary_eval_evaluation_results(evaluation_results):
     return len(evaluation_results)
 
 
@@ -988,6 +988,7 @@ def summary_eval_outputs_reference(evaluation_results):
         summary_eval_runs_examples,
         summary_eval_inputs_outputs,
         summary_eval_outputs_reference,
+        summary_eval_evaluation_results,
     ],
 )
 def test__normalize_summary_evaluator(evaluator: Callable) -> None: