import re
import torch
import requests
from PIL import Image, ImageDraw
from transformers import AutoProcessor, Kosmos2_5ForConditionalGeneration

repo = "microsoft/kosmos-2.5"
device = "cuda:0"
dtype = torch.bfloat16
model = Kosmos2_5ForConditionalGeneration.from_pretrained(repo, device_map=device, torch_dtype=dtype)
processor = AutoProcessor.from_pretrained(repo)

# sample image
url = "https://huggingface.co/microsoft/kosmos-2.5/blob/main/receipt_00008.png"
image = Image.open(requests.get(url, stream=True).raw)

prompt = "<md>"
inputs = processor(text=prompt, images=image, return_tensors="pt")

height, width = inputs.pop("height"), inputs.pop("width")
raw_width, raw_height = image.size
scale_height = raw_height / height
scale_width = raw_width / width

inputs = {k: v.to(device) if v is not None else None for k, v in inputs.items()}
inputs["flattened_patches"] = inputs["flattened_patches"].to(dtype)
generated_ids = model.generate(
    **inputs,
    max_new_tokens=1024,
)

generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)
print(generated_text[0])