feat: Cherry-pick progress on parallelization of eval runs

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "uipath"
-version = "2.1.78"
+version = "2.1.80"
 description = "Python SDK and CLI for UiPath Platform, enabling programmatic interaction with automation services, process management, and deployment tools."
 readme = { file = "README.md", content-type = "text/markdown" }
 requires-python = ">=3.10"

samples/calculator/main.py

@@ -35,15 +35,15 @@ class Wrapper:
 
 @traced()
 @mockable(example_calls=GET_RANDOM_OPERATOR_EXAMPLES)
-def get_random_operator() -> Wrapper:
+async def get_random_operator() -> Wrapper:
     """Get a random operator."""
     return Wrapper(result=random.choice([Operator.ADD, Operator.SUBTRACT, Operator.MULTIPLY, Operator.DIVIDE]))
 
 
 @traced()
 async def main(input: CalculatorInput) -> CalculatorOutput:
     if input.operator == Operator.RANDOM:
-        operator = get_random_operator().result
+        operator = (await get_random_operator()).result
     else:
         operator = input.operator
     match operator:

src/uipath/_cli/_evals/_models/_output.py

@@ -64,46 +64,49 @@ class EvaluationRunResultDto(BaseModel):
     model_config = ConfigDict(alias_generator=to_camel, populate_by_name=True)
 
     evaluator_name: str
+    evaluator_id: str
     result: EvaluationResultDto
 
+    @model_serializer(mode="wrap")
+    def serialize_model(self, serializer, info):
+        data = serializer(self)
+        if isinstance(data, dict):
+            data.pop("evaluatorId", None)
+        return data
+
 
 class EvaluationRunResult(BaseModel):
     model_config = ConfigDict(alias_generator=to_camel, populate_by_name=True)
 
-    score: float = 0.0
     evaluation_name: str
     evaluation_run_results: List[EvaluationRunResultDto]
 
-    def compute_average_score(self) -> None:
+    @property
+    def score(self) -> float:
         """Compute average score for this single eval_item."""
         if not self.evaluation_run_results:
-            self.score = 0.0
-            return
+            return 0.0
 
         total_score = sum(dto.result.score for dto in self.evaluation_run_results)
-        self.score = total_score / len(self.evaluation_run_results)
+        return total_score / len(self.evaluation_run_results)
 
 
 class UiPathEvalOutput(BaseModel):
     model_config = ConfigDict(alias_generator=to_camel, populate_by_name=True)
 
     evaluation_set_name: str
-    score: float
     evaluation_set_results: List[EvaluationRunResult]
 
-    def compute_average_score(self) -> None:
-        """Compute overall average by calling eval_item.compute_average_score()."""
+    @property
+    def score(self) -> float:
+        """Compute overall average score from evaluation results."""
         if not self.evaluation_set_results:
-            self.score = 0.0
-            return
-
-        for eval_result in self.evaluation_set_results:
-            eval_result.compute_average_score()
+            return 0.0
 
         eval_item_scores = [
             eval_result.score for eval_result in self.evaluation_set_results
         ]
-        self.score = sum(eval_item_scores) / len(eval_item_scores)
+        return sum(eval_item_scores) / len(eval_item_scores)
 
     def calculate_final_score(
         self,
@@ -181,5 +184,4 @@ def calculate_final_score(
 
         final_score = total_weighted_score / total_weight if total_weight > 0 else 0.0
 
-        self.score = final_score
         return final_score, agg_metrics_per_evaluator