Update app.py

app.py

@@ -2,6 +2,7 @@ import torch
 from transformers import AutoModel, AutoTokenizer
 from PIL import Image
 import gradio as gr
+import os
 
 # Load the OCR model and tokenizer with low memory usage in mind
 tokenizer = AutoTokenizer.from_pretrained('ucaslcl/GOT-OCR2_0', trust_remote_code=True)
@@ -15,13 +16,17 @@ model = model.to(device)
 
 # Function to perform OCR on the image
 def perform_ocr(image):
-    # Open the image using PIL
-    pil_image = Image.open(image)
+    # Save the uploaded image temporarily
+    temp_image_path = "temp_image.png"
+    image.save(temp_image_path)
 
     # Use torch.no_grad() to avoid unnecessary memory usage
     with torch.no_grad():
-        # Perform OCR using the model (image passed as PIL image)
-        result = model.chat(tokenizer, pil_image, ocr_type='ocr')
+        # Perform OCR using the model (pass the file path of the saved image)
+        result = model.chat(tokenizer, temp_image_path, ocr_type='ocr')
+    
+    # Clean up the temporary image file
+    os.remove(temp_image_path)
     
     # Return the extracted text
     return result