Update app.py

app.py

@@ -1,33 +1,38 @@
 import torch
 from transformers import AutoModel, AutoTokenizer
 from PIL import Image
+import gradio as gr
+import tempfile
 
-# Load the OCR model and tokenizer with low memory usage in mind
+# Load the OCR model and tokenizer
 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, 
                                   pad_token_id=tokenizer.eos_token_id).eval()
 
-# Ensure we are using CPU
-device = torch.device('cpu')
+# Check if GPU is available and use it, else use CPU
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
 model = model.to(device)
 
 # Function to perform OCR on the image
-def perform_ocr(image_path):
-    # Open the image file
-    image = Image.open(image_path)
+def perform_ocr(image):
+    # Save the image to a temporary file
+    with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as temp_file:
+        image.save(temp_file.name)  # Save the image
+        temp_image_path = temp_file.name  # Get the file path for the saved image
 
-    # Use torch.no_grad() to avoid unnecessary memory usage
-    with torch.no_grad():
-        # Perform OCR using the model
-        result = model.chat(tokenizer, image_path, ocr_type='ocr')
-    
-    # Return the extracted text
+    # Perform OCR using the model
+    result = model.chat(tokenizer, temp_image_path, ocr_type='ocr')
     return result
 
-# Example usage with an image file path
-image_path = "/content/id.jpg"
-extracted_text = perform_ocr(image_path)
+# Create the Gradio interface using the new syntax
+interface = gr.Interface(
+    fn=perform_ocr, 
+    inputs=gr.Image(type="pil"),  # Updated to gr.Image
+    outputs=gr.Textbox(),         # Updated to gr.Textbox
+    title="OCR Web App",
+    description="Upload an image to extract text using the GOT-OCR2.0 model."
+)
 
-# Output the extracted text
-print("Extracted Text:", extracted_text)
+# Launch the app
+interface.launch()