handler.py

from typing import Dict, List, Any
from transformers import pipeline

class EndpointHandler:
    def __init__(self, path=""):
        self.pipeline = pipeline("text-generation", model=path)

    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
        """
         data args:
              inputs (:obj: `str`)
              date (:obj: `str`)
        Return:
              A :obj:`list` | `dict`: will be serialized and returned
        """
        # get inputs
        template = """
        INSTRUCTION
        {}
        RESPONSE
        {}
        """
        instruction = data.pop("instruction", data)
        inputs = template.format(instruction, "")
        # run normal prediction
        prediction = self.pipeline(inputs)
        return prediction