Update app.py

app.py

@@ -37,13 +37,14 @@ def fetch_image(image_url):
     except Exception as e:
         raise ValueError(f"Failed to fetch image from URL: {str(e)}")
 
-def predict(image_url, prompt):
+def predict(image_url):
     """
     Process the image URL and prompt, return annotated image data.
     """
     try:
         # Validate and fetch the image
         image = fetch_image(image_url)
+        prompt = "Detect all objects in the provided image and output their bounding box coordinates in the format <box>(x1,y1,x2,y2)</box>. Do not include any other text or descriptions. If multiple objects are detected, list each bounding box in a new <box> tag."
 
         # Call the Hugging Face Inference API
         stream = client.chat.completions.create(
@@ -87,16 +88,11 @@ def predict(image_url, prompt):
 def create_gradio_interface():
     with gr.Blocks(title="Object Detection Demo") as demo:
         gr.Markdown("# Object Detection with Bounding Boxes")
-        gr.Markdown("Provide an image URL and a prompt to detect objects and display bounding boxes.")
+        gr.Markdown("Provide an image URL detect objects and display bounding boxes.")
 
         with gr.Row():
             with gr.Column():
                 image_url = gr.Textbox(label="Image URL", placeholder="Enter a publicly accessible image URL")
-                prompt = gr.Textbox(
-                    label="Prompt",
-                    placeholder="e.g., 'Detect and label all objects in the image with bounding boxes.'",
-                    lines=3
-                )
                 submit_btn = gr.Button("Run Detection")
             with gr.Column():
                 output_image = gr.AnnotatedImage(label="Detected Objects")
@@ -104,7 +100,7 @@ def create_gradio_interface():
 
         submit_btn.click(
             fn=predict,
-            inputs=[image_url, prompt],
+            inputs=[image_url],
             outputs=[output_image, status]
         )