app.py

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()


# input your test image
image_file = 'car.jpg'

# plain texts OCR
res = model.chat(tokenizer, image_file, ocr_type='ocr')

# format texts OCR:
# res = model.chat(tokenizer, image_file, ocr_type='format')

# fine-grained OCR:
# res = model.chat(tokenizer, image_file, ocr_type='ocr', ocr_box='')
# res = model.chat(tokenizer, image_file, ocr_type='format', ocr_box='')
# res = model.chat(tokenizer, image_file, ocr_type='ocr', ocr_color='')
# res = model.chat(tokenizer, image_file, ocr_type='format', ocr_color='')

# multi-crop OCR:
# res = model.chat_crop(tokenizer, image_file, ocr_type='ocr')
# res = model.chat_crop(tokenizer, image_file, ocr_type='format')

# render the formatted OCR results:
# res = model.chat(tokenizer, image_file, ocr_type='format', render=True, save_render_file = './demo.html')

print(res)

#import google.generativeai as genai
#import os

#genai.configure(api_key=os.environ["AIzaSyB5WiEJf_yLMD1dMQf305EAbaPTzF_QD-I"])

#model = genai.GenerativeModel('gemini-1.5-flash')
#response = model.generate_content(
#    text_input="the color of the car is ?", 
#    image_input="car.jpg"
#)
#print(response.text)