import streamlit as st
from transformers import pipeline
from PIL import Image
import base64

pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")

# Set the title and text color to dark green
st.title('R3SELL', color='darkgreen')

# Create a file input option for uploading an image
file_name = st.file_uploader("Upload an image file (JPEG, PNG, etc.)")

# Create an option to access the camera/webcam
if st.button("Take an image from camera"):
    cap = cv2.VideoCapture(0)
    ret, frame = cap.read()
    if ret:
        # Encode the webcam image as a Base64 string
        img_encoded = base64.b64encode(cv2.imencode('.jpg', frame)[1]).decode('utf-8')

        # Pass the Base64 encoded image to the pipeline function
        predictions = pipeline(Image.open('data:image/jpeg;base64,' + img_encoded))

        # Replace file_name with the encoded image
        file_name = 'webcam_image.jpg'

# Add a text bar to add a title
image_title = st.text_input("Image Title", value="Specificity is nice!")

# Add a text bar to add a description
image_description = st.text_input("Image Description", value="(Optional)")

if file_name is not None:
    col1, col2 = st.columns(2)

    # Check if the file is a webcam image
    if file_name == 'webcam_image.jpg':
        # Use the Base64 encoded image
        image = Image.open('data:image/jpeg;base64,' + img_encoded)
    else:
        # Open the uploaded image
        image = Image.open(file_name)

    col1.image(image, use_column_width=True)
    predictions = pipeline(image)

    col2.header("Probabilities")
    for p in predictions:
        col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")