Update app.py

app.py

@@ -1,35 +1,39 @@
-import gradio as gr
-import requests
-from PIL import Image
+import os
 from transformers import BlipProcessor, BlipForConditionalGeneration
+import gradio as gr
 
-# Load your model and processor
-processor = BlipProcessor.from_pretrained("quadranttechnologies/Imageclassification")
-model = BlipForConditionalGeneration.from_pretrained("quadranttechnologies/Imageclassification")
+# Load the token from the environment
+HUGGINGFACE_TOKEN = os.getenv("HUGGINGFACE_TOKEN")
 
-# Define a function to generate captions for the uploaded image
+# Load the model and processor with the token
+processor = BlipProcessor.from_pretrained(
+    "quadranttechnologies/Imageclassification",
+    use_auth_token=HUGGINGFACE_TOKEN
+)
+model = BlipForConditionalGeneration.from_pretrained(
+    "quadranttechnologies/Imageclassification",
+    use_auth_token=HUGGINGFACE_TOKEN
+)
+
+# Define your Gradio interface and logic as before
 def generate_caption(image):
     try:
-        # Convert the image into the required format for the model
         inputs = processor(image, return_tensors="pt")
-
-        # Generate caption
         outputs = model.generate(**inputs)
         caption = processor.decode(outputs[0], skip_special_tokens=True)
         return caption
     except Exception as e:
         return f"Error generating caption: {e}"
 
-# Set up Gradio interface for image upload and caption generation
 interface = gr.Interface(
     fn=generate_caption,
-    inputs=gr.Image(type="pil"),  # Accepts uploaded images
-    outputs="text",               # Displays the caption as text
+    inputs=gr.Image(type="pil"),
+    outputs="text",
     title="Image Captioning Model",
     description="Upload an image to receive a caption generated by the model."
 )
 
-# Launch the Gradio app
 if __name__ == "__main__":
-    interface.launch(share=True)  # Set share=True to enable public link if needed
+    interface.launch(share=True)
+