handler

handler.py

@@ -0,0 +1,25 @@
+from typing import Dict, List, Any
+from transformers import LayoutLMForTokenClassification, LayoutLMv2Processor
+import torch
+from subprocess import run
+import pytesseract
+
+# 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 __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)
+ return {"predictions": result}

requirements.txt

@@ -0,0 +1 @@
+pytesseract