import streamlit as st
import transformers
from transformers import pipeline
import PIL
from PIL import Image
import requests
from transformers import AutoProcessor, AutoModelForZeroShotImageClassification

pipe = pipeline("summarization", model="google/pegasus-xsum")
agepipe = pipeline("image-classification", model="dima806/facial_age_image_detection")
imgpipe = pipeline("zero-shot-image-classification", model="openai/clip-vit-base-patch32")


st.title("NLP APP")
option = st.sidebar.selectbox(
    "Choose a task",
    ("Summarization", "Age Detection", "Emotion Detection", "Image Classification")
)
if option == "Summarization":
    st.title("Text Summarization")
    text = st.text_area("Enter text to summarize")
    if st.button("Summarize"):
        if text:
            st.write("Summary:", pipe(text)[0]["summary_text"])
        else:
            st.write("Please enter text to summarize.")
elif option == "Age Detection":
    st.title("Welcome to age detection")

    uploaded_files = st.file_uploader("Choose a image file",type="jpg")

    if uploaded_files is not None:
        Image=Image.open(uploaded_files)

        st.write(agepipe(Image)[0]["label"])
elif option == "Image Classification":
    st.title("Welcome to object detection")

    uploaded_file = st.file_uploader("Choose an image file", type=["jpg", "jpeg", "png"])
    text = st.text_area("Enter possible class names (comma-separated)")
    if uploaded_file is not None and text:
        candidate_labels = [t.strip() for t in text.split(',')]
        image = Image.open(uploaded_file)
        st.image(image, caption="Uploaded Image", use_column_width=True)
        classification_result = imgpipe(image, candidate_labels)
        for result in classification_result:
            st.write(f"Label: {result['label']}, Score: {result['score']}")
    else:
        st.write("Please upload an image file and enter class names.")
        

else:
    st.title("None")