app.py

from itertools import product
import streamlit as st
import numpy as np
import pandas as pd
from PIL import Image, ImageOps
import time
from paddleocr import PaddleOCR
import os
from dotenv import load_dotenv
from huggingface_hub import login

load_dotenv()  # Load .env file
huggingface_token = os.getenv("HF_TOKEN")
login(huggingface_token)

##########################LLAMA3BI################################
from huggingface_hub import InferenceClient
client = InferenceClient(api_key=huggingface_token)
messages = [
    {"role": "system", "content": """Your task is to get the product details out of the text given. 
                                    The text given will be raw text from OCR of product images,
                                    and the goal is to get product details and description so that it can be used for e-commerce product listing. 
                                    TRY TO KEEP THE LISTING IN FOLLOWING FORMAT. 
                                    \ud83d\udce6 [Product Name]
                                    \ud83d\udcb0 Price: $XX.XX
                                    ✨ Key Features:
                                    • [Main Feature 1]
                                    • [Main Feature 2]
                                    • [Main Feature 3]
                                    \ud83d\udcf8 [Product Image]
                                    \ud83c\udff7 Available Now on E-commerce Platform
                                    ✈️ Fast Shipping Available
                                    \ud83d\udecd️ Shop Now: [Link]
                                    🔍 Search: [Main Keywords]
                                    [#RelevantHashtags] """},
]

# Initialize PaddleOCR model
ocr = PaddleOCR(use_angle_cls=True, lang='en')

# Team details
team_members = [
    {"name": "Aman Deep", "image": "aman.jpg"},
    {"name": "Gaurav Lodhi", "image": "anandimg.jpg"}
]

# Function to display team members in circular format
def display_team_members(members, max_members_per_row=4):
    num_members = len(members)
    num_rows = (num_members + max_members_per_row - 1) // max_members_per_row

    for i in range(num_rows):
        cols = st.columns(min(max_members_per_row, num_members - i * max_members_per_row))
        for j, member in enumerate(members[i * max_members_per_row:(i + 1) * max_members_per_row]):
            with cols[j]:
                img = Image.open(member["image"])  
                st.image(img, use_column_width=True)  
                st.write(member["name"])  

# Function to simulate loading process with a progress bar
def simulate_progress():
    progress_bar = st.progress(0)
    for percent_complete in range(100):
        time.sleep(0.02)
        progress_bar.progress(percent_complete + 1)

# Title and description
st.title("Hacknovate 6.0")
# Team Details with links
st.sidebar.title("Hacknovate 6.0")
st.sidebar.write("DELHI TECHNOLOGICAL UNIVERSITY")

# Navbar with task tabs
st.sidebar.title("Navigation")
st.sidebar.write("Team Name: sadhya")
app_mode = st.sidebar.selectbox("Choose the task", ["Welcome", "Project Details", "Task 1", "Team Details"])

if app_mode == "Welcome":
    st.write("# Welcome to Hacknovate 6.0! 🎉")
    video_file = open('Finalist.mp4', 'rb')
    video_bytes = video_file.read()
    st.video(video_bytes) 
    welcome_image = Image.open("grid_banner.jpg")
    st.image(welcome_image, use_column_width=True)

elif app_mode == "Project Details":
    st.write("## Project Overview: Automating Product Listings with AI")
    st.write("Our system extracts product details using OCR and LLMs to create structured e-commerce listings.")

elif app_mode == "Team Details":
    st.write("## Meet Our Team:")
    display_team_members(team_members)
    st.write("Delhi Technological University")

elif app_mode == "Task 1":
    st.write("## Task 1: 🖼️ OCR to Extract Details 📄")
    st.write("Using OCR to extract details from product packaging material.")
    
    uploaded_files = st.file_uploader("Upload images of products", type=["jpeg", "png", "jpg"], accept_multiple_files=True)

    if uploaded_files:
        st.write("### Uploaded Images:")
        for uploaded_file in uploaded_files:
            img = Image.open(uploaded_file)
            st.image(img, use_column_width=True)

        if st.button("Start Analysis"):
            simulate_progress()
            for uploaded_image in uploaded_files:
                image = Image.open(uploaded_image)
                img_array = np.array(image)
                st.write(f"Extracting details from {uploaded_image.name}...")
                result = ocr.ocr(img_array, cls=True)
                text = " ".join([box[1][0] for line in result for box in line])
                st.write(f"OCR Result: {text}")
                simulate_progress()
                messages.append({"role": "user", "content": text})
                completion = client.chat.completions.create(
                    model="meta-llama/Llama-3.2-3B-Instruct", 
                    messages=messages, 
                    max_tokens=500
                )
                productListingContent = completion.choices[0].message
                st.markdown(productListingContent.content)
                st.markdown("---")
    else:
        st.write("Please upload images to extract product details.")

st.markdown(""" 
    <style>
        @keyframes fade-in {
            from { opacity: 0; }
            to { opacity: 1;}
        }
        .footer {
            text-align: center;
            font-size: 1.1em;
            animation: fade-in 2s;
            padding-top: 2rem;
        }
    </style>
    <div class="footer">
        <p>© 2024 Hacknovate 6.0. All rights reserved.</p>
    </div>
""", unsafe_allow_html=True)