feat: add experimental folder for beta features

tests/evaluation/metrics/test_goal_metrics.py

@@ -1,8 +1,8 @@
 from unittest.mock import patch, MagicMock
 from tests.evaluation.metrics.base_evaluation_metrics_test import BaseEvaluationMetricsTest
 
-from crewai.evaluation.base_evaluator import EvaluationScore
-from crewai.evaluation.metrics.goal_metrics import GoalAlignmentEvaluator
+from crewai.experimental.evaluation.base_evaluator import EvaluationScore
+from crewai.experimental.evaluation.metrics.goal_metrics import GoalAlignmentEvaluator
 from crewai.utilities.llm_utils import LLM
 
 

tests/evaluation/metrics/test_reasoning_metrics.py

@@ -3,12 +3,12 @@ from unittest.mock import patch, MagicMock
 from typing import List, Dict, Any
 
 from crewai.tasks.task_output import TaskOutput
-from crewai.evaluation.metrics.reasoning_metrics import (
+from crewai.experimental.evaluation.metrics.reasoning_metrics import (
     ReasoningEfficiencyEvaluator,
 )
 from tests.evaluation.metrics.base_evaluation_metrics_test import BaseEvaluationMetricsTest
 from crewai.utilities.llm_utils import LLM
-from crewai.evaluation.base_evaluator import EvaluationScore
+from crewai.experimental.evaluation.base_evaluator import EvaluationScore
 
 class TestReasoningEfficiencyEvaluator(BaseEvaluationMetricsTest):
     @pytest.fixture

tests/evaluation/metrics/test_semantic_quality_metrics.py

@@ -1,7 +1,7 @@
 from unittest.mock import patch, MagicMock
 
-from crewai.evaluation.base_evaluator import EvaluationScore
-from crewai.evaluation.metrics.semantic_quality_metrics import SemanticQualityEvaluator
+from crewai.experimental.evaluation.base_evaluator import EvaluationScore
+from crewai.experimental.evaluation.metrics.semantic_quality_metrics import SemanticQualityEvaluator
 from tests.evaluation.metrics.base_evaluation_metrics_test import BaseEvaluationMetricsTest
 from crewai.utilities.llm_utils import LLM
 

tests/evaluation/metrics/test_tools_metrics.py

@@ -1,6 +1,6 @@
 from unittest.mock import patch, MagicMock
 
-from crewai.evaluation.metrics.tools_metrics import (
+from crewai.experimental.evaluation.metrics.tools_metrics import (
     ToolSelectionEvaluator,
     ParameterExtractionEvaluator,
     ToolInvocationEvaluator

tests/evaluation/test_agent_evaluator.py

@@ -3,9 +3,9 @@ import pytest
 from crewai.agent import Agent
 from crewai.task import Task
 from crewai.crew import Crew
-from crewai.evaluation.agent_evaluator import AgentEvaluator
-from crewai.evaluation.base_evaluator import AgentEvaluationResult
-from crewai.evaluation import (
+from crewai.experimental.evaluation.agent_evaluator import AgentEvaluator
+from crewai.experimental.evaluation.base_evaluator import AgentEvaluationResult
+from crewai.experimental.evaluation import (
     GoalAlignmentEvaluator,
     SemanticQualityEvaluator,
     ToolSelectionEvaluator,
@@ -14,7 +14,7 @@ from crewai.evaluation import (
     ReasoningEfficiencyEvaluator
 )
 
-from crewai.evaluation import create_default_evaluator
+from crewai.experimental.evaluation import create_default_evaluator
 class TestAgentEvaluator:
     @pytest.fixture
     def mock_crew(self):

tests/evaluation/test_experiment_result.py

@@ -1,7 +1,7 @@
 import pytest
 from unittest.mock import MagicMock, patch
 
-from crewai.evaluation.experiment.result import ExperimentResult, ExperimentResults
+from crewai.experimental.evaluation.experiment.result import ExperimentResult, ExperimentResults
 
 
 class TestExperimentResult:

tests/evaluation/test_experiment_runner.py

@@ -2,10 +2,10 @@ import pytest
 from unittest.mock import MagicMock, patch
 
 from crewai.crew import Crew
-from crewai.evaluation.experiment.runner import ExperimentRunner
-from crewai.evaluation.experiment.result import ExperimentResults
-from crewai.evaluation.evaluation_display import AgentAggregatedEvaluationResult
-from crewai.evaluation.base_evaluator import MetricCategory, EvaluationScore
+from crewai.experimental.evaluation.experiment.runner import ExperimentRunner
+from crewai.experimental.evaluation.experiment.result import ExperimentResults
+from crewai.experimental.evaluation.evaluation_display import AgentAggregatedEvaluationResult
+from crewai.experimental.evaluation.base_evaluator import MetricCategory, EvaluationScore
 
 
 class TestExperimentRunner:
@@ -44,7 +44,7 @@ class TestExperimentRunner:
 
         return {"Test Agent": agent_evaluation}
 
-    @patch('crewai.evaluation.experiment.runner.create_default_evaluator')
+    @patch('crewai.experimental.evaluation.experiment.runner.create_default_evaluator')
     def test_run_success(self, mock_create_evaluator, mock_crew, mock_evaluator_results):
         dataset = [
             {
@@ -102,7 +102,7 @@ class TestExperimentRunner:
         assert mock_evaluator.get_agent_evaluation.call_count == 3
 
 
-    @patch('crewai.evaluation.experiment.runner.create_default_evaluator')
+    @patch('crewai.experimental.evaluation.experiment.runner.create_default_evaluator')
     def test_run_success_with_unknown_metric(self, mock_create_evaluator, mock_crew, mock_evaluator_results):
         dataset = [
             {
@@ -130,7 +130,7 @@ class TestExperimentRunner:
         assert "unknown_metric" in result.expected_score.keys()
         assert result.passed is True
 
-    @patch('crewai.evaluation.experiment.runner.create_default_evaluator')
+    @patch('crewai.experimental.evaluation.experiment.runner.create_default_evaluator')
     def test_run_success_with_single_metric_evaluator_and_expected_specific_metric(self, mock_create_evaluator, mock_crew, mock_evaluator_results):
         dataset = [
             {
@@ -163,7 +163,7 @@ class TestExperimentRunner:
         assert "goal_alignment" in result.expected_score.keys()
         assert result.passed is True
 
-    @patch('crewai.evaluation.experiment.runner.create_default_evaluator')
+    @patch('crewai.experimental.evaluation.experiment.runner.create_default_evaluator')
     def test_run_success_when_expected_metric_is_not_available(self, mock_create_evaluator, mock_crew, mock_evaluator_results):
         dataset = [
             {