one more

app.py

@@ -1,10 +1,12 @@
 import os
+import tempfile
 import gradio as gr
 import numpy as np
 from transformers import Qwen2VLForConditionalGeneration, AutoProcessor
 from qwen_vl_utils import process_vision_info
 import torch
 from ast import literal_eval
+from PIL import Image
 
 # Load the model on the available device(s)
 model = Qwen2VLForConditionalGeneration.from_pretrained(
@@ -37,7 +39,7 @@ tax_deductions = '''Extract the following information in the given format:
                         'ee medicare tax:': {'Amount':'', 'Year-To_Date':""}},
                     'california:': {
                         'withholding tax:': {'Amount':'', 'Year-To_Date':""},
-                        'ee disability tax:': {'Amount':'', 'Year-To_Date':""}}},
+                        'ee disability tax:': {'Amount':'', 'Year-To-Date':""}}},
                 }
 '''
 
@@ -87,8 +89,11 @@ def demo(image_path, prompt):
     return json
 
 def process_document(image):
-    # Save the uploaded image temporarily and get its path
-    image_path = image.name  # Gradio provides an interface to access the file name
+    # Save the uploaded image to a temporary file
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as tmp_file:
+        image = Image.fromarray(image)  # Convert NumPy array to PIL Image
+        image.save(tmp_file.name)  # Save the image to the temporary file
+        image_path = tmp_file.name  # Get the path of the saved file
 
     # Process the image with your model
     one = demo(image_path, other_benifits)
@@ -97,6 +102,10 @@ def process_document(image):
         "tax_deductions": one,
         "other_benifits": two
     }
+
+    # Optionally, you can delete the temporary file after use
+    os.remove(image_path)
+
     return json_op
 
 # Create Gradio interface