Update app.py

app.py

@@ -1,13 +1,20 @@
 import gradio
 from transformers import ViltProcessor, ViltForQuestionAnswering
 from PIL import Image
+import requests
 
 processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
 model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
 
 
 def predict_answer(image, question):
-    image = Image.fromarray(image.astype('uint8'), 'RGB')
+    if isinstance(image, str):
+        # Download image from URL
+        response = requests.get(image)
+        image = Image.open(BytesIO(response.content))
+    else:
+        # Convert numpy array to PIL Image
+        image = Image.fromarray(image.astype('uint8'), 'RGB')
     encoding = processor(image, question, return_tensors="pt")
     outputs = model(**encoding)
     logits = outputs.logits
@@ -24,7 +31,8 @@ def predict_answer(image, question):
 
 
 inputs = [
-    gradio.components.Image(label="Image"),
+    gradio.inputs.Image(type="file", label="Upload Image"),
+    gradio.inputs.Image(type="url", label="Image URL"),
     gradio.components.Textbox(label="Question", placeholder="Enter your question here.")
 ]