import os
import io
import IPython.display
from PIL import Image
import base64
from transformers import pipeline, AutoTokenizer
import requests
import gradio as gr


get_completion = pipeline("image-to-text", model="Salesforce/blip-image-captioning-base")

def generate_caption(base64_image):
    # Decode base64 string to PIL image
    image_data = base64.b64decode(base64_image)
    image = Image.open(io.BytesIO(image_data))

    # Get caption using the BLIP model
    caption_result = get_completion(image)

    # Ensure a consistent format by always returning a dictionary
    if isinstance(caption_result, str):
        return {'generated_text': caption_result}
    elif caption_result and isinstance(caption_result, list):
        return caption_result[0]
    else:
        return {'generated_text': None}
    
def image_to_base64_str(pil_image):
    byte_arr = io.BytesIO()
    pil_image.save(byte_arr, format='PNG')
    byte_arr = byte_arr.getvalue()
    return str(base64.b64encode(byte_arr).decode('utf-8'))

def captioner(image):
    base64_image = image_to_base64_str(image)
    result = generate_caption(base64_image)
    print(result)  # Debugging print statement to see the structure of the result

    # Access the 'generated_text' field from the result dictionary
    caption_text = result['generated_text']
    print(caption_text)
    return caption_text

demo = gr.Interface(fn=captioner,
                    inputs=[gr.Image(label="Upload image", type="pil")],
                    outputs=[gr.Textbox(label="Caption")],
                    title="Image Captioning with BLIP",
                    description="Caption any image using the BLIP model",
                    allow_flagging="never",
                    examples=["christmas_dog.jpeg", "bird_flight.jpeg", "cow.jpeg"])

demo.launch() # Remove share=True and server_port for Hugging Face Spaces