"""
This module provides an interface for image captioning using the BLIP model.
The interface allows users to upload an image and receive a caption.
"""

import gradio as gr
import spaces
from transformers import BlipProcessor, BlipForConditionalGeneration
from PIL import Image

# Initialize the processor and model
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = (
    BlipForConditionalGeneration
    .from_pretrained("Salesforce/blip-image-captioning-base")
    .to("cuda")
)

def generate_caption(image: Image) -> str:
    """
    Generates a caption for a given image using the BLIP model.

    Args:
        image (Image): The input image as a PIL Image object.

    Returns:
        str: The generated caption.
    """
    inputs = processor(images=image, return_tensors="pt").to("cuda")
    outputs = model.generate(**inputs)
    caption = processor.decode(outputs[0], skip_special_tokens=True)
    return caption

@spaces.GPU
def caption_image(image: Image) -> str:
    """
    Takes a PIL Image input and returns a caption.

    Args:
        image (Image): The input image as a PIL Image object.

    Returns:
        str: The generated caption or an error message.
    """
    try:
        return generate_caption(image)
    except Exception as e:
        return f"An error occurred: {str(e)}"

# Define the Gradio interface
demo = gr.Interface(
    fn=caption_image,
    inputs=gr.Image(type="pil"),
    outputs="text",
    title="Image Captioning with BLIP",
    description="Upload an image to generate a caption."
)

# Launch the interface
demo.launch()