from typing import Dict from transformers import AutoTokenizer, AutoModelForSequenceClassification import torch class EndpointHandler: def __init__(self, path=""): self.tokenizer = AutoTokenizer.from_pretrained(path) self.model = AutoModelForSequenceClassification.from_pretrained(path) self.model.eval() self.id2label = {0: "create", 1: "edit", 2: "query"} def __call__(self, data: Dict[str, str]) -> Dict[str, str]: text = data.get("inputs", "") inputs = self.tokenizer(text, return_tensors="pt") with torch.no_grad(): outputs = self.model(**inputs) probs = torch.nn.functional.softmax(outputs.logits, dim=1) pred = torch.argmax(probs, dim=1).item() label = self.id2label[pred] confidence = probs[0][pred].item() return {"label": label, "confidence": round(confidence, 3)}