|
|
import evoagentx.workflow.operators as operator |
|
|
import examples.aflow.humaneval.optimized.round_13.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) |
|
|
self.ensemble = operator.ScEnsemble(self.llm) |
|
|
self.review = operator.Custom(self.llm) |
|
|
|
|
|
async def __call__(self, problem: str, entry_point: str): |
|
|
""" |
|
|
Implementation of the workflow |
|
|
Custom operator to generate code, review it, and validate it with tests. |
|
|
""" |
|
|
solution = await self.custom_code_generate(problem=problem, entry_point=entry_point, instruction=prompt_custom.GENERATE_PYTHON_CODE_PROMPT) |
|
|
reviewed_solution = await self.review(input=solution['response'], instruction=prompt_custom.REVIEW_CODE_PROMPT) |
|
|
validation = await self.test(problem=problem, solution=reviewed_solution['response'], entry_point=entry_point, benchmark=self.benchmark) |
|
|
|
|
|
if validation['result']: |
|
|
return reviewed_solution['response'] |
|
|
else: |
|
|
modified_solution = await self.custom(input=problem + f" with problems: {validation['solution']}", instruction=prompt_custom.GENERATE_PYTHON_CODE_PROMPT) |
|
|
solutions_list = [reviewed_solution['response'], modified_solution['response']] |
|
|
ensemble_result = await self.ensemble(solutions=solutions_list, problem=problem) |
|
|
return ensemble_result['response'] |
|
|
|