Update app.py

app.py

@@ -13,25 +13,26 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 model.to(device)
 
 # Define function for image captioning
-def analyze_scene(image):
+def analyze_scene_api(image):
     try:
         # Preprocess the image
         processed_image = processor(images=image, return_tensors="pt").pixel_values.to(device)
         with torch.no_grad():
             output = model.generate(processed_image)
         caption = processor.decode(output[0], skip_special_tokens=True)
-        return caption
+        return {"caption": caption}
     except Exception as e:
-        return f"Error: {str(e)}"
+        return {"error": str(e)}
 
-# Create Gradio Interface
+# Create Gradio Interface with API mode
 interface = gr.Interface(
-    fn=analyze_scene,
+    fn=analyze_scene_api,
     inputs=gr.Image(type="pil"),
-    outputs="text",
-    title="BLIP Image Captioning",
-    description="Upload an image to get a caption generated by BLIP."
+    outputs="json",
+    title="BLIP API for Image Captioning",
+    description="Send an image to get a caption response in JSON format."
 )
 
 if __name__ == "__main__":
-    interface.launch()
+    # Launch Gradio interface in API mode
+    interface.launch(server_name="0.0.0.0", server_port=7860, enable_queue=True)