from typing import Dict, List, Any

class EndpointHandler():
    def __init__(self ,  path=""):
        # Preload all the elements you are going to need at inference.
        # pseudo:
        # self.model= load_model(path)
        bnb_config = BitsAndBytesConfig(
          load_in_4bit=True,
          bnb_4bit_use_double_quant=True,
          bnb_4bit_quant_type="nf4",
          bnb_4bit_compute_dtype=torch.bfloat16
           )
        path = "shredder-31/GA_model_Gemma_2b"
        model = AutoModelForCausalLM.from_pretrained(path, quantization_config=bnb_config, device_map={"":0})
        tokenizer = AutoTokenizer.from_pretrained(path, add_eos_token=True)
        self.model = model
        self.tokenizer = tokenizer
        

    def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
        """
       data args:
            inputs (:obj: `str` | `PIL.Image` | `np.array`)
            kwargs
      Return:
            A :obj:`list` | `dict`: will be serialized and returned
        """

      
        encodeds = self.tokenizer(data['inputs'], return_tensors="pt", add_special_tokens=True)
        generated_ids = self.model.generate(**encodeds, max_length=100 ,max_new_tokens=100, do_sample=False)
        decoded = self.tokenizer.decode(generated_ids[0], skip_special_tokens=True)

        return {'output':decoded[len(data['inputs']):]}