from typing import Dict, List, Any
from transformers import AutoTokenizer, AutoModelForCausalLM

class EndpointHandler():
    def __init__(self, path=""):
        # init
        self.tokenizer = AutoTokenizer.from_pretrained("verseAI/vai-GPT-NeoXT-Chat-Base-20B")
        self.model = AutoModelForCausalLM.from_pretrained("verseAI/vai-GPT-NeoXT-Chat-Base-20B", device_map="auto", load_in_8bit=True)        

    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

            from transformers import AutoTokenizer, AutoModelForCausalLM
        """
        # infer
        inputs = self.tokenizer("<human>: Hello!\n<bot>:", return_tensors='pt').to(self.model.device)
        outputs = self.model.generate(**inputs, max_new_tokens=10, do_sample=True, temperature=0.8)
        output_str = self.tokenizer.decode(outputs[0])
        print(output_str)
        return output_str