examples/aflow/humanevalplus_update/optimized/round_7/graph.py

import evoagentx.workflow.operators as operator
import examples.aflow.humanevalplus_update.optimized.round_7.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)  # Initialize the Test operator
        self.sc_ensemble = operator.ScEnsemble(self.llm)  # Initialize the ScEnsemble 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 solutions
        solutions = []
        for _ in range(3):  # Generate three solutions for ensemble
            solution = await self.custom_code_generate(problem=problem, entry_point=entry_point, instruction=prompt_custom.GENERATE_PYTHON_CODE_PROMPT)
            solutions.append(solution['response'])
        
        # Review the solutions before selection
        review_results = []
        for solution in solutions:
            review = await self.custom(input=solution, instruction=prompt_custom.REVIEW_SOLUTION_PROMPT)
            review_results.append(review['response'])
        
        # Use ScEnsemble to select the best solution based on reviews
        best_solution = await self.sc_ensemble(solutions=review_results, problem=problem)
        
        test_result = await self.test(problem=problem, solution=best_solution['response'], entry_point=entry_point, benchmark=self.benchmark)  # Validate the solution
        if test_result['result']:
            return best_solution['response']
        else:
            return "Solution failed the tests."  # Provide feedback if the solution fails