examples/aflow/molqa/optimized_molqa/round_4/graph.py

import evoagentx.workflow.operators as operator
import examples.aflow.molqa.optimized_molqa.round_4.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.ensemble = operator.QAScEnsemble(self.llm)  # Added QAScEnsemble operator
    
    async def __call__(self, problem: str):
        """
        Implementation of the workflow
        """
        solution = await self.answer_generate(input=problem)
        ensemble_response = await self.ensemble.sc_ensemble([solution['answer']])  # Use ensemble to select the best answer
        return ensemble_response['response']  # Return the selected answer from ensemble