Update app.py

app.py

@@ -15,17 +15,21 @@ def extract_data_from_pdf(pdf_file):
     doc = fitz.open(pdf_file.name)
     text_data = []
 
-    for page_num in range(doc.page_count):
+    # Limit processing to the first 5 pages for faster results
+    max_pages = min(doc.page_count, 5)
+
+    for page_num in range(max_pages):
         page = doc[page_num]
         pix = page.get_pixmap()  # Render page to a Pixmap image
         
-        # Convert Pixmap to PIL Image
+        # Convert Pixmap to PIL Image and resize for faster processing
         image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
+        image = image.resize((image.width // 2, image.height // 2))  # Resize to 50% for faster processing
         
         # Preprocess image for the Donut model
         processed_image = processor(image, return_tensors="pt").pixel_values
         # Generate text with controlled length using `max_new_tokens`
-        outputs = model.generate(processed_image, max_new_tokens=100)
+        outputs = model.generate(processed_image, max_new_tokens=50)  # Reduced length for faster output
         
         # Decode generated text
         text = processor.batch_decode(outputs, skip_special_tokens=True)[0]
@@ -93,8 +97,6 @@ iface = gr.Interface(
     title="Advanced Document Data Extractor",
     description=(
         "Upload a PDF file to extract structured purchase order data and download it as an Excel file. "
-        "The model will identify and parse rows with fields like Position, Item Code, Description, Quantity, Price, etc. "
-        "Calculated fields (like Central GST, State GST, and Sub Total) are automatically included."
     ),
 )