Update app.py

app.py

@@ -11,7 +11,7 @@ from PIL import Image
 vl_model = Qwen2VLForConditionalGeneration.from_pretrained(
     "Qwen/Qwen2-VL-2B-Instruct", torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32, device_map="auto"
 )
-vl_processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct")
+vl_processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-2B-Instruct", max_pixels=480*480)
 
 # Load Text Model
 model_name = "Qwen/Qwen2.5-Math-1.5B-Instruct"
@@ -21,20 +21,27 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 
 math_messages = []
 
+def resize_image(image):
+    max_size = 480
+    if isinstance(image, str):  # Handle file paths
+        image = Image.open(image)
+    image.thumbnail((max_size, max_size))
+    return image
+    
 def process_image(image, shouldConvert=False):
     global math_messages
     math_messages = []  # Reset when uploading an image
 
     if image is None:
         return "No image provided."
-    
+        
     if shouldConvert:
         new_img = Image.new('RGB', size=(image.width, image.height), color=(255, 255, 255))
         new_img.paste(image, (0, 0), mask=image)
         image = new_img
 
     try:
-        inputs = vl_processor(images=image, return_tensors="pt").to(device)
+        inputs = vl_processor(images=resize_image(image), return_tensors="pt").to(device)
         if inputs is None:
             return "Error processing image."