examples/aflow/pertqa/optimized_adamson_update/round_9/graph.py

import evoagentx.workflow.operators as operator
import examples.aflow.pertqa.optimized_adamson_update.round_9.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)  # Using QAScEnsemble operator
        self.diversity_check = operator.Custom(self.llm)  # Added diversity check operator
    
    async def __call__(self, problem: str):
        """
        Implementation of the workflow
        """
        solution = await self.answer_generate(input=problem)
        solutions_list = [solution['answer']]  # Collecting solutions for ensemble
        diversity_response = await self.diversity_check(input=problem, instruction=prompt_custom.DIVERSITY_PROMPT)  # Using diversity check
        solutions_list.append(diversity_response['response'])  # Adding diverse solution
        ensemble_response = await self.qas_ensemble(solutions=solutions_list)  # Using QAScEnsemble
        return ensemble_response['response']  # Returning the ensemble response