import evoagentx.workflow.operators as operator import examples.aflow.scicode.optimized.round_2.prompt as prompt_custom from evoagentx.models.model_configs import LLMConfig from evoagentx.benchmark.benchmark import Benchmark from evoagentx.models.model_utils import create_llm_instance class Workflow: def __init__( self, name: str, llm_config: LLMConfig, benchmark: Benchmark ): self.name = name self.llm = create_llm_instance(llm_config) self.benchmark = benchmark self.custom = operator.Custom(self.llm) self.custom_code_generate = operator.CustomCodeGenerate(self.llm) self.test = operator.Test(self.llm) self.ensemble = operator.ScEnsemble(self.llm) # Added ensemble operator async def __call__(self, problem: str, entry_point: str): """ Implementation of the workflow Custom operator to generate anything you want. But when you want to get standard code, you should use custom_code_generate operator. """ # Generate multiple initial solutions solutions = [] for _ in range(3): # Generating three solutions response = await self.custom(input=problem + " Generate a solution, ensure it is functional.", instruction=prompt_custom.GENERATE_PYTHON_CODE_PROMPT) solutions.append(response['response']) # Test the solutions for errors test_results = [] for solution in solutions: test_result = await self.test(problem=problem, solution=solution, entry_point=entry_point, benchmark=self.benchmark) test_results.append(test_result) # Select best solution using ensemble if errors detected successful_solutions = [result['solution'] for result in test_results if result['result']] if successful_solutions: return await self.ensemble(solutions=successful_solutions, problem=problem) # Applying ensemble on successful solutions return "No valid solutions found." # Handling case where no tests pass