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>
This commit is contained in:
Vidit Ostwal
2025-02-18 22:15:26 +05:30
committed by GitHub
parent b6d668fc66
commit ac819bcb6e
3 changed files with 19 additions and 11 deletions

View File

@@ -1148,19 +1148,24 @@ 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)