import evoagentx.workflow.operators as operator
import examples.aflow.hotpotqa.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.answer_generate = operator.AnswerGenerate(self.llm) 
        self.qas_ensemble = operator.QAScEnsemble(self.llm)  
        self.additional_step = operator.AnswerGenerate(self.llm)  # Added another AnswerGenerate operator for additional processing
        self.review_step = operator.AnswerGenerate(self.llm)  # Added a review step for better solution structuring
    
    async def __call__(self, problem: str):
        """
        Implementation of the workflow
        """
        solution = await self.answer_generate(input=problem)
        additional_solution = await self.additional_step(input=problem)  # Generate an additional solution
        review_response = await self.review_step(input=f"Review these solutions: {solution['answer']}, {additional_solution['answer']}")  # Review the generated solutions
        ensemble_response = await self.qas_ensemble(solutions=[review_response['answer']])  # Use QAScEnsemble to select the best solution
        return ensemble_response['response']  # Return the selected response