examples/aflow/humaneval/optimized/round_14/graph.py

import evoagentx.workflow.operators as operator
import examples.aflow.humaneval.optimized.round_14.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)  # Added Test operator for validation
        self.ensemble = operator.ScEnsemble(self.llm)  # Added ScEnsemble operator for improved solution selection

    async def __call__(self, problem: str, entry_point: str):
        """
        Implementation of the workflow
        Custom operator to generate code and validate it with tests.
        """
        solution = await self.custom_code_generate(problem=problem, entry_point=entry_point, instruction=prompt_custom.GENERATE_PYTHON_CODE_PROMPT)
        validation = await self.test(problem=problem, solution=solution['response'], entry_point=entry_point, benchmark=self.benchmark)  # Testing the solution
        
        if validation['result']:
            return solution['response']
        else:
            # Gather insights on common failure patterns
            insight = await self.custom(input=problem + f" with errors: {validation['solution']}", instruction=prompt_custom.GATHER_INSIGHTS_PROMPT)
            # If tests fail, modify solution based on insights from validation errors
            modified_solution = await self.custom(input=problem + f" with problems: {insight['response']}", instruction=prompt_custom.GENERATE_PYTHON_CODE_PROMPT)
            # Collect potential solutions for ensemble decision
            solutions_list = [solution['response'], modified_solution['response']]
            # Use ScEnsemble to determine the best solution from collected options
            ensemble_result = await self.ensemble(solutions=solutions_list, problem=problem)
            return ensemble_result['response']  # Return the ensemble-selected solution if tests fail