handler.py

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)
        self.model.eval()

    def __call__(self, data):
        inputs = data.get("inputs", "")
        parameters = data.get("parameters", {})
        
        if not inputs:
            return [{"error": "Missing 'inputs' in payload"}]

        input_ids = self.tokenizer.encode(inputs, return_tensors="pt")
        outputs = self.model.generate(
            input_ids,
            max_new_tokens=parameters.get("max_new_tokens", 128),
            do_sample=True,
            temperature=parameters.get("temperature", 0.7),
            top_p=parameters.get("top_p", 0.9),
        )

        result = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
        return [{"generated_text": result}]  # ✅ Must return a list