import gradio as gr
from transformers import AutoTokenizer, AutoModel
import torch

tokenizer = AutoTokenizer.from_pretrained("law-ai/InLegalBERT")
model = AutoModel.from_pretrained("law-ai/InLegalBERT")

def encode(text):
    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True)
    outputs = model(**inputs)
    cls_embedding = outputs.last_hidden_state[:, 0, :].squeeze().detach().numpy()
    return str(cls_embedding[:10])  # แสดงเฉพาะ 10 ค่าแรก

demo = gr.Interface(fn=encode, inputs="text", outputs="text")
demo.launch()