Update app.py

app.py

@@ -2,37 +2,33 @@ import torch
 from transformers import AutoModel, AutoTokenizer
 from PIL import Image
 import gradio as gr
-import tempfile
 
-# Load the OCR model and tokenizer
+# Load the OCR model and tokenizer with low memory usage in mind
 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()
 
-# Check if GPU is available and use it, else use CPU
-device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+# Ensure we are using CPU
+device = torch.device('cpu')
 model = model.to(device)
 
 # Function to perform OCR on the image
 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
+    # Open the image using PIL
+    pil_image = Image.open(image)
 
-    # Perform OCR using the model
-    result = model.chat(tokenizer, temp_image_path, ocr_type='ocr')
+    # 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')
+    
+    # Return the extracted text
     return result
 
-# 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."
-)
+# Create the Gradio interface for file upload and OCR
+iface = gr.Interface(fn=perform_ocr, inputs="file", outputs="text", 
+                     title="OCR Application", description="Upload an image to extract text.")
 
-# Launch the app
-interface.launch()
+# Launch the Gradio app
+iface.launch()