import gradio as gr
import numpy as np
from PIL import Image
from transformers import AutoProcessor, BlipForConditionalGeneration

# HuggingFace
# Load model directly
from transformers import AutoProcessor, AutoModelForSeq2SeqLM

processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = AutoModelForSeq2SeqLM.from_pretrained("Salesforce/blip-image-captioning-base")
#processor = # write your code here
#model = # write your code here

def caption_image(input_image: np.ndarray):
    # Convert numpy array to PIL Image and convert to RGB
    raw_image = Image.fromarray(input_image).convert('RGB')
    
    # Process the image
    # You do not need a question for image captioning
    text = "the image of"
    inputs = processor(images=image, text=text, return_tensors="pt")
    

    # Generate a caption for the image
    # Generate a caption for the image
    outputs = model.generate(**inputs, max_length=50)

    # Decode the generated tokens to text and store it into `caption`
    # Decode the generated tokens to text
    caption = processor.decode(outputs[0], skip_special_tokens=True)
    # Print the caption
    #print(caption)
    

    return caption

iface = gr.Interface(
    fn=caption_image, 
    inputs=gr.Image(), 
    outputs="text",
    title="Image Captioning",
    description="This is a simple web app for generating captions for images using a trained model."
)

iface = gr.Interface(
    fn=caption_image, 
    inputs=gr.Image(), 
    outputs="text",
    title="Image Captioning",
    description="This is a simple web app for generating captions for images using a trained model."
)