fix: enable any llm to run test functionality

Co-Authored-By: Joe Moura <joao@crewai.com>

src/crewai/crew.py

@@ -4,6 +4,7 @@ import uuid
 import warnings
 from concurrent.futures import Future
 from hashlib import md5
+from crewai.llm import LLM
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 
 from pydantic import (
@@ -1075,7 +1076,7 @@ class Crew(BaseModel):
     def test(
         self,
         n_iterations: int,
-        openai_model_name: Optional[str] = None,
+        llm: Union[str, LLM],
         inputs: Optional[Dict[str, Any]] = None,
     ) -> None:
         """Test and evaluate the Crew with the given inputs for n iterations concurrently using concurrent.futures."""
@@ -1085,9 +1086,9 @@ class Crew(BaseModel):
             test_crew,
             n_iterations,
             inputs,
-            openai_model_name,  # type: ignore[arg-type]
+            str(llm) if isinstance(llm, LLM) else llm,
-        )  # type: ignore[arg-type]
+        )
-        evaluator = CrewEvaluator(test_crew, openai_model_name)  # type: ignore[arg-type]
+        evaluator = CrewEvaluator(test_crew, llm)
 
         for i in range(1, n_iterations + 1):
             evaluator.set_iteration(i)

src/crewai/utilities/evaluators/crew_evaluator_handler.py

@@ -1,3 +1,6 @@
+from typing import Union
+
+from crewai.llm import LLM
 from collections import defaultdict
 
 from pydantic import BaseModel, Field
@@ -32,9 +35,9 @@ class CrewEvaluator:
     run_execution_times: defaultdict = defaultdict(list)
     iteration: int = 0
 
-    def __init__(self, crew, openai_model_name: str):
+    def __init__(self, crew, llm: Union[str, LLM]):
         self.crew = crew
-        self.openai_model_name = openai_model_name
+        self.llm = LLM(model=llm) if isinstance(llm, str) else llm
         self._telemetry = Telemetry()
         self._setup_for_evaluating()
 
@@ -51,7 +54,7 @@ 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 +184,7 @@ class CrewEvaluator:
                 self.crew,
                 evaluation_result.pydantic.quality,
                 current_task._execution_time,
-                self.openai_model_name,
+                str(self.llm) if isinstance(self.llm, LLM) else self.llm,
             )
             self.tasks_scores[self.iteration].append(evaluation_result.pydantic.quality)
             self.run_execution_times[self.iteration].append(

tests/crew_test.py

@@ -10,6 +10,7 @@ import instructor
 import pydantic_core
 import pytest
 
+from crewai.llm import LLM
 from crewai.agent import Agent
 from crewai.agents.cache import CacheHandler
 from crewai.crew import Crew
@@ -1123,7 +1124,7 @@ def test_kickoff_for_each_empty_input():
     assert results == []
 
 
-@pytest.mark.vcr(filter_headers=["authorization"])
+@pytest.mark.vcr(filter_headeruvs=["authorization"])
 def test_kickoff_for_each_invalid_input():
     """Tests if kickoff_for_each raises TypeError for invalid input types."""
 
@@ -2828,7 +2829,7 @@ 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"})
+    crew.test(n_iterations, llm="gpt-4o-mini", inputs={"topic": "AI"})
 
     # Ensure kickoff is called on the copied crew
     kickoff_mock.assert_has_calls(
@@ -2844,6 +2845,32 @@ def test_crew_testing_function(kickoff_mock, copy_mock, crew_evaluator):
         ]
     )
 
+@mock.patch("crewai.crew.CrewEvaluator")
+@mock.patch("crewai.crew.Crew.copy")
+@mock.patch("crewai.crew.Crew.kickoff")
+def test_crew_testing_with_custom_llm(kickoff_mock, copy_mock, crew_evaluator):
+    task = Task(
+        description="Test task",
+        expected_output="Test output",
+        agent=researcher,
+    )
+    crew = Crew(agents=[researcher], tasks=[task])
+    copy_mock.return_value = crew
+    custom_llm = LLM(model="gpt-4")
+    
+    crew.test(2, llm=custom_llm, inputs={"topic": "AI"})
+    
+    kickoff_mock.assert_has_calls([
+        mock.call(inputs={"topic": "AI"}),
+        mock.call(inputs={"topic": "AI"})
+    ])
+    crew_evaluator.assert_has_calls([
+        mock.call(crew, custom_llm),
+        mock.call().set_iteration(1),
+        mock.call().set_iteration(2),
+        mock.call().print_crew_evaluation_result(),
+    ])
+
 
 @pytest.mark.vcr(filter_headers=["authorization"])
 def test_hierarchical_verbose_manager_agent():

tests/utilities/evaluators/test_crew_evaluator_handler.py

@@ -2,6 +2,7 @@ from unittest import mock
 
 import pytest
 
+from crewai.llm import LLM
 from crewai.agent import Agent
 from crewai.crew import Crew
 from crewai.task import Task
@@ -23,7 +24,7 @@ class TestCrewEvaluator:
         )
         crew = Crew(agents=[agent], tasks=[task])
 
-        return CrewEvaluator(crew, openai_model_name="gpt-4o-mini")
+        return CrewEvaluator(crew, llm="gpt-4o-mini")
 
     def test_setup_for_evaluating(self, crew_planner):
         crew_planner._setup_for_evaluating()
@@ -47,6 +48,18 @@ class TestCrewEvaluator:
         assert agent.verbose is False
         assert agent.llm.model == "gpt-4o-mini"
 
+    def test_evaluator_with_custom_llm(self, crew_planner):
+        custom_llm = LLM(model="gpt-4")
+        evaluator = CrewEvaluator(crew_planner.crew, custom_llm)
+        agent = evaluator._evaluator_agent()
+        assert agent.llm == custom_llm
+
+    def test_evaluator_with_string_llm(self, crew_planner):
+        evaluator = CrewEvaluator(crew_planner.crew, "gpt-4")
+        agent = evaluator._evaluator_agent()
+        assert isinstance(agent.llm, LLM)
+        assert agent.llm.model == "gpt-4"
+
     def test_evaluation_task(self, crew_planner):
         evaluator_agent = Agent(
             role="Evaluator Agent",