from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
import torch

class EndpointHandler:
    def __init__(self, path=""):
        self.tokenizer = AutoTokenizer.from_pretrained(path)
        self.model = AutoModelForSeq2SeqLM.from_pretrained(
            path, 
            torch_dtype=torch.bfloat16
        )
        
    def __call__(self, data):
        inputs = data.pop("inputs", data)
        messages = [{"role": "user", "content": inputs}]
        
        input_ids = self.tokenizer.apply_chat_template(
            messages,
            add_generation_prompt=True,
            return_tensors="pt"
        )
        
        outputs = self.model.generate(
            input_ids,
            max_new_tokens=1024,
            temperature=0.1,
            do_sample=True
        )
        
        return {
            "generated_text": self.tokenizer.decode(outputs[0], skip_special_tokens=True)
        }