import gradio as gr
import tempfile
from PIL import Image

from transformers import AutoModel, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
model = AutoModel.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True, low_cpu_mem_usage=True, device_map='cuda', use_safetensors=True, pad_token_id=tokenizer.eos_token_id)
model = model.eval().cuda()

def OCR(image):
    pil_image = Image.fromarray(image)
    with tempfile.TemporaryDirectory() as temp_dir:
        temp_image_path = f"{temp_dir}/processed_image.png"
        pil_image.save(temp_image_path)
        res = model.chat(tokenizer, temp_image_path, ocr_type='ocr')
        return res        

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