update 4

app.py

@@ -74,23 +74,22 @@ model.load_state_dict(new_state_dict)
 # Load the tokenizer from Jina
 tokenizer = AutoTokenizer.from_pretrained("jinaai/jina-embeddings-v2-base-en")
 
-def load_image(image):
-    """
-    Preprocess the uploaded image.
-    """
+def load_image(image_path_or_url):
+    if isinstance(image_path_or_url, str) and image_path_or_url.startswith("http"):
+        with urllib.request.urlopen(image_path_or_url) as url:
+            image = Image.open(url).convert('RGB')
+    else:
+        image = Image.open(image_path_or_url).convert('RGB')
+    
     image = transform(image)
     image = image.unsqueeze(0)  # Add batch dimension
     return image
 
-def predict(image, title, threshold=0.7):
-    """
-    Predict the top 3 categories for the given image and title.
-    Includes "Others" if the confidence of the top prediction is below the threshold.
-    """
+def predict(image_path_or_file, title, threshold=0.7):
     # Preprocess the image
-    image = load_image(image)
+    image = load_image(image_path_or_file)
     
-    # Tokenize the title
+    # Tokenize title
     title_encoding = tokenizer(title, padding='max_length', max_length=200, truncation=True, return_tensors='pt')
     input_ids = title_encoding['input_ids']
     attention_mask = title_encoding['attention_mask']
@@ -118,9 +117,9 @@ def predict(image, title, threshold=0.7):
     return results
 
 # Define the Gradio interface
-title_input = gr.inputs.Textbox(label="Product Title", placeholder="Enter the product title here...")
-image_input = gr.inputs.Image(type="pil", label="Upload Image")
-output = gr.outputs.JSON(label="Top 3 Predictions with Probabilities")
+title_input = gr.Textbox(label="Product Title", placeholder="Enter the product title here...")
+image_input = gr.Image(type="filepath", label="Upload Image or Provide URL")
+output = gr.JSON(label="Top 3 Predictions with Probabilities")
 
 gr.Interface(
     fn=predict,