Added functionality to have any llm run test functionality (#2071)

* Added functionality to have any llm run test functionality

* Fixed lint issues

* Fixed Linting issues

* Fixed unit test case

* Fixed unit test

* Fixed test case

* Fixed unit test case

---------

Co-authored-by: Brandon Hancock (bhancock_ai) <109994880+bhancockio@users.noreply.github.com>

src/crewai/crew.py

@@ -1169,19 +1169,24 @@ class Crew(BaseModel):
     def test(
         self,
         n_iterations: int,
-        openai_model_name: Optional[str] = None,
+        eval_llm: Union[str, InstanceOf[LLM]],
         inputs: Optional[Dict[str, Any]] = None,
     ) -> None:
         """Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
         test_crew = self.copy()
 
+        eval_llm = create_llm(eval_llm)
+
+        if not eval_llm:
+            raise ValueError("Failed to create LLM instance.")
+
         self._test_execution_span = test_crew._telemetry.test_execution_span(
             test_crew,
             n_iterations,
             inputs,
-            openai_model_name,  # type: ignore[arg-type]
+            eval_llm.model,  # type: ignore[arg-type]
         )  # type: ignore[arg-type]
-        evaluator = CrewEvaluator(test_crew, openai_model_name)  # type: ignore[arg-type]
+        evaluator = CrewEvaluator(test_crew, eval_llm)  # type: ignore[arg-type]
 
         for i in range(1, n_iterations + 1):
             evaluator.set_iteration(i)

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -1,11 +1,12 @@
 from collections import defaultdict
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, Field, InstanceOf
 from rich.box import HEAVY_EDGE
 from rich.console import Console
 from rich.table import Table
 
 from crewai.agent import Agent
+from crewai.llm import LLM
 from crewai.task import Task
 from crewai.tasks.task_output import TaskOutput
 from crewai.telemetry import Telemetry
@@ -23,7 +24,7 @@ class CrewEvaluator:
 
     Attributes:
         crew (Crew): The crew of agents to evaluate.
-        openai_model_name (str): The model to use for evaluating the performance of the agents (for now ONLY OpenAI accepted).
+        eval_llm (LLM): Language model instance to use for evaluations
         tasks_scores (defaultdict): A dictionary to store the scores of the agents for each task.
         iteration (int): The current iteration of the evaluation.
     """
@@ -32,9 +33,9 @@ class CrewEvaluator:
     run_execution_times: defaultdict = defaultdict(list)
     iteration: int = 0
 
-    def __init__(self, crew, openai_model_name: str):
+    def __init__(self, crew, eval_llm: InstanceOf[LLM]):
         self.crew = crew
-        self.openai_model_name = openai_model_name
+        self.llm = eval_llm
         self._telemetry = Telemetry()
         self._setup_for_evaluating()
 
@@ -51,7 +52,7 @@ class CrewEvaluator:
             ),
             backstory="Evaluator agent for crew evaluation with precise capabilities to evaluate the performance of the agents in the crew based on the tasks they have performed",
             verbose=False,
-            llm=self.openai_model_name,
+            llm=self.llm,
         )
 
     def _evaluation_task(
@@ -181,7 +182,7 @@ class CrewEvaluator:
                 self.crew,
                 evaluation_result.pydantic.quality,
                 current_task.execution_duration,
-                self.openai_model_name,
+                self.llm.model,
             )
             self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
             self.run_execution_times[self.iteration].append(

tests/crew_test.py

@@ -14,6 +14,7 @@ from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
 from crewai.crews.crew_output import CrewOutput
 from crewai.knowledge.source.string_knowledge_source import StringKnowledgeSource
+from crewai.llm import LLM
 from crewai.memory.contextual.contextual_memory import ContextualMemory
 from crewai.process import Process
 from crewai.project import crew
@@ -3341,7 +3342,8 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
     copy_mock.return_value = crew
 
     n_iterations = 2
-    crew.test(n_iterations, openai_model_name="gpt-4o-mini", inputs={"topic": "AI"})
+    llm_instance = LLM('gpt-4o-mini')
+    crew.test(n_iterations, llm_instance, inputs={"topic": "AI"})
 
     # Ensure kickoff is called on the copied crew
     kickoff_mock.assert_has_calls(
@@ -3350,7 +3352,7 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
 
     crew_evaluator.assert_has_calls(
         [
-            mock.call(crew, "gpt-4o-mini"),
+            mock.call(crew,llm_instance),
             mock.call().set_iteration(1),
             mock.call().set_iteration(2),
             mock.call().print_crew_evaluation_result(),