handler.py

from typing import Dict, List, Any
from transformers import LayoutLMForTokenClassification, LayoutLMv2Processor
import torch
from subprocess import run
import pytesseract
from pytesseract import Output

# install tesseract-ocr and pytesseract
run("apt install -y tesseract-ocr", shell=True, check=True)

# set device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")


class EndpointHandler:
	
	def __init__(self, path=""):
		self.pytesseract_installed = False
		try:
			import pytesseract 
			self.pytesseract_installed = True
		except ImportError:
			print("Pytesseract not installed, will not use OCR")
			
	def __call__(self, data: Dict[str, bytes]) -> Dict[str, List[Any]]:
		"""
		Args:
			data (:obj:):
				includes the deserialized image file as PIL.Image
		"""
		# process input
		image = data.pop("inputs", data)

		result = pytesseract.image_to_string(image, config='--psm 3', output_type=Output.STRING)
		return {"predictions": result}