Upload 14 files

data/.streamlit/config.toml

@@ -0,0 +1,6 @@
+[theme]
+base="dark"
+primaryColor="#6643b5"
+backgroundColor="#0E1117"
+textColor="#FAFAFA"
+secondaryBackgroundColor="#262730"

data/__init__.py

@@ -0,0 +1,3 @@
+from functions import *
+import lxml
+import lxml_html_clean

data/about_app.py

@@ -0,0 +1,21 @@
+import streamlit as st
+
+st.set_page_config(
+    layout="wide",
+    initial_sidebar_state="collapsed"
+)
+
+### insert external css
+def insert_css(css_file:str):
+    with open(css_file) as f:
+        st.markdown(f"<style>{f.read()}</style>",unsafe_allow_html=True)
+
+# app settings css
+insert_css("css_files/app.css")
+
+### insert external html file
+def insert_html(html_file):
+    with open(html_file) as f:
+        return f.read()
+
+st.markdown(insert_html("html_files/about.html"),unsafe_allow_html=True)

data/animation/particles.html

@@ -0,0 +1,88 @@
+
+<script src="https://cdn.jsdelivr.net/npm/particles.js@2.0.0/particles.min.js"></script>
+<script>
+    document.addEventListener("DOMContentLoaded", function() {
+        particlesJS('particles-js', {
+            "particles": {
+                "number": {
+                    "value": 80,
+                    "density": {
+                        "enable": true,
+                        "value_area": 800
+                    }
+                },
+                "color": {
+                    "value": "#ffffff"
+                },
+                "shape": {
+                    "type": "circle",
+                    "stroke": {
+                        "width": 0,
+                        "color": "#000000"
+                    }
+                },
+                "opacity": {
+                    "value": 0.5,
+                    "random": false,
+                    "anim": {
+                        "enable": false,
+                        "speed": 1,
+                        "opacity_min": 0.1,
+                        "sync": false
+                    }
+                },
+                "size": {
+                    "value": 3,
+                    "random": true,
+                    "anim": {
+                        "enable": false,
+                        "speed": 40,
+                        "size_min": 0.1,
+                        "sync": false
+                    }
+                },
+                "line_linked": {
+                    "enable": true,
+                    "distance": 150,
+                    "color": "#ffffff",
+                    "opacity": 0.4,
+                    "width": 1
+                },
+                "move": {
+                    "enable": true,
+                    "speed": 6,
+                    "direction": "none",
+                    "random": false,
+                    "straight": false,
+                    "out_mode": "out",
+                    "bounce": false,
+                    "attract": {
+                        "enable": false,
+                        "rotateX": 600,
+                        "rotateY": 1200
+                    }
+                }
+            },
+            "interactivity": {
+                "detect_on": "canvas",
+                "events": {
+                    "onhover": {
+                        "enable": true,
+                        "mode": "repulse"
+                    },
+                    "onclick": {
+                        "enable": true,
+                        "mode": "push"
+                    },
+                    "resize": true
+                }
+            },
+            "retina_detect": true
+        });
+    });
+</script>
+<div id="particles-js" style="position: absolute; width: 100%; height: 100%;"></div>
+
+
+
+

data/app.py

@@ -0,0 +1,56 @@
+import streamlit as st
+
+### page setup
+
+web_qna = st.Page(
+    page="webscraper.py",
+    title="web Scraper",
+    icon=":material/globe:",
+    default=True
+)
+
+text_qna = st.Page(
+    page="text.py",
+    title="Text Q&A , Summarizer",
+    icon=":material/description:",
+)
+
+document_qna = st.Page(
+    page="document.py",
+    title="Document Q&A , Summarizer",
+    icon=":material/picture_as_pdf:",
+)
+
+
+
+about_app = st.Page(
+    page="about_app.py",
+    title="About App",
+    icon=":material/person:"
+)
+
+pg = st.navigation(
+    pages=[web_qna,text_qna,document_qna,about_app],
+    expanded=False,position="sidebar"
+)
+pg.run()
+
+app_sidebar = st.sidebar
+
+with app_sidebar:
+    
+    # project Link
+    st.link_button(
+        label="Project Link",
+        url="https://github.com/Nishant43S/Gen-Ai-Summarizer-Question-Answering-App.git",
+        icon=":material/code_off:",
+        use_container_width=True
+    )
+
+### insert external css
+def insert_css(css_file:str):
+    with open(css_file) as f:
+        st.markdown(f"<style>{f.read()}</style>",unsafe_allow_html=True)
+
+# app settings css
+insert_css("css_files/app.css")

data/css_files/app.css

@@ -0,0 +1,22 @@
+*{
+    scrollbar-width: none;
+}
+
+/* main app css */
+[class="stAppViewMain main st-emotion-cache-bm2z3a ea3mdgi8"]{
+    background: #0f1116;
+}
+
+[class="st-emotion-cache-luriig ezrtsby2"]{
+    background: #0f1116;   
+}
+
+[data-testid="stBaseButton-header"]{
+    visibility: hidden;
+}
+
+::selection{
+    background: #421b9b;
+    color: whitesmoke;
+}
+

data/document.py

@@ -0,0 +1,320 @@
+import streamlit as st
+from functions import *
+from transformers import pipeline
+from pdfminer.high_level import extract_text
+import os
+import PyPDF2
+import base64
+
+
+
+#### chatbot function
+
+def Chat_Bot(text_input,Best_size,max_answer_length):
+    st.markdown(
+        """
+        <style>
+            /* Fix the chat input box at the bottom */
+            div[data-testid="stChatInput"] {
+                position: fixed;
+                bottom: 0;
+                margin-bottom: 36px;
+                
+            }
+        </style>
+        """,
+        unsafe_allow_html=True
+    )
+    # Load the Question Answering model
+    qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
+
+    # Initialize session state for chat history
+    if "messages" not in st.session_state:
+        st.session_state.messages = []
+
+
+    # User inputs context
+    context = text_input
+
+    # Display chat history
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+
+    if context:
+        user_input = st.chat_input("💬 Ask a question based on the context:")
+        if user_input:
+            with st.chat_message("user"):
+                st.markdown(user_input)
+            
+            st.session_state.messages.append({"role": "user", "content": user_input})
+            
+            with st.spinner("🤔 Thinking..."):
+                response = qa_pipeline(
+                    {"question": user_input, "context": context},
+                    max_answer_len=max_answer_length, n_best_size=Best_size
+                )
+                answer = response["answer"]
+            
+            with st.chat_message("assistant"):
+                st.markdown(f"{answer}")
+            
+            st.session_state.messages.append({"role": "assistant", "content": f"{answer}"})
+
+    # Clear chat history button
+    if st.button("🗑️ Clear Chat"):
+        st.session_state.messages = []
+        st.rerun()
+
+
+# page settings
+st.set_page_config(
+    layout="wide",
+    initial_sidebar_state="collapsed"
+)
+
+### insert external css
+def insert_css(css_file:str):
+    with open(css_file) as f:
+        st.markdown(f"<style>{f.read()}</style>",unsafe_allow_html=True)
+
+# app settings css
+insert_css("css_files/app.css")
+
+def extract_pdf_text(pdf_file):
+    """Extracts text from a PDF file."""
+    return extract_text(pdf_file)
+
+
+
+#### displaying uploaded pdf file
+def display_pdf_file(uploaded_file):
+    """
+    it is used to display the
+    file on screen
+    """
+    #### saving the uploaded file
+    def save_uploadfile(save_file):
+        with open(os.path.join("data",save_file.name),"wb") as f:
+            f.write(save_file.getbuffer())
+            return st.toast("file uploaded: {}".format(save_file.name))
+        
+    try:
+        ### display pdf on screen
+        def displayPDF(pdf_file):
+            with open(pdf_file,"rb") as f:
+                base64_pdf = base64.b64encode(f.read()).decode("utf-8")
+
+            pdf_display = f"""
+                <iframe
+                    src="data:application/pdf;base64,{base64_pdf}"
+                    width="950" height="1000"
+                    type="application/pdf"
+                >
+                </iframe>
+            """
+
+            st.markdown(pdf_display,unsafe_allow_html=True)
+
+        ### save and display file
+        save_uploadfile(uploaded_file)
+        pdf_file = "data/"+uploaded_file.name
+        displayPDF(pdf_file)
+    except Exception as e:
+        st.warning("Something Went wrong...\n\n",e,icon="⚠️")
+
+
+# --- PDF Page Text Extractor Function ---
+def extract_text_from_pdf(pdf_file, page_num):
+    try:
+        reader = PyPDF2.PdfReader(pdf_file)
+        total_pages = len(reader.pages)
+        if 1 <= page_num <= total_pages:
+            page = reader.pages[page_num - 1]  # Adjusting for 0-based index
+            text = page.extract_text()
+            return text, total_pages
+        else:
+            return None, total_pages
+    except Exception as e:
+        st.error(f"Error extracting text: {e}")
+        return None, 0
+
+def pdf_Summarizer(file):
+    Display_col, Summarizer_col = st.tabs(["Pdf Display","PDF Summarizer"])
+    with Display_col:
+        display_pdf_file(file)
+    with Summarizer_col:
+        temp_reader = PyPDF2.PdfReader(file)
+        total_pages = len(temp_reader.pages)
+        st.write(f"### Total Pages: {total_pages}")
+
+        ## columns
+        Input_col = st.columns([4,10])
+        with Input_col[0]:
+            page_number = st.number_input(
+                "Select page number", 
+                min_value=1, max_value=total_pages,
+                value=1, step=1)
+            st.write("Page Number {}".format(page_number))
+        text, _ = extract_text_from_pdf(file, page_number)
+        return text
+
+
+app_sidebar = st.sidebar
+
+with app_sidebar:
+    select_mode = st.selectbox(
+        label="Select Mode",
+        options=["Summarizer","Que/Ans"],
+        key="mode selector",
+        index=0
+    )
+
+    if select_mode == "Que/Ans":
+        st.write("### Que/Ans Settings")
+
+        max_answer_length = st.slider(
+            label="Max answer",
+            min_value=1,
+            max_value=10,
+            key="max answer",
+            value=4
+        )
+
+        max_answer_length = max_answer_length*10
+
+        Best_size_ = st.slider(
+            label="n best size",
+            min_value=1,
+            max_value=10,
+            key="best size",
+            value=5
+        )
+
+def Summarizer_Model(context,Max_Length):
+    try:
+        summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+        Summary = summarizer(
+            context,
+            max_length=Max_Length+20, 
+            min_length=Max_Length, 
+            do_sample=False
+        )
+        return Summary[0]['summary_text']
+
+    except Exception as e:
+        st.warning(f"Error...\n{e}",icon="⚠️")
+
+app_col = st.columns([2,8,2])
+
+with app_col[1]:
+
+    if select_mode == "Summarizer":
+        st.write("## 📑 Document Summarizer")
+    elif select_mode == "Que/Ans":
+        st.write("## 📑 Document Question Answering")
+
+### question answering 
+que_col = st.columns([2,8,2])
+
+with que_col[1]:
+    if select_mode == "Que/Ans":
+        ## input file
+        File_input = st.file_uploader(
+            label="Drop Your File hear",
+            type=["txt", "pdf"],
+            key="file uploader"
+        )
+
+        if File_input is not None:
+            if File_input.type == "text/plain":
+                text = File_input.read().decode("utf-8")
+                Chat_Bot(
+                    text_input=Text_Cleaning(text),
+                    Best_size=Best_size_,
+                    max_answer_length=max_answer_length
+                )
+            else:
+                text = extract_pdf_text(File_input)
+                Chat_Bot(
+                    text_input=Text_Cleaning(text),
+                    Best_size=Best_size_,
+                    max_answer_length=max_answer_length
+                )
+
+# session state
+if 'input_text' not in st.session_state:
+    st.session_state.input_text = []
+
+if 'pdf_text' not in st.session_state:
+    st.session_state.pdf_text = []
+
+if 'summary_text' not in st.session_state:
+    st.session_state.summary_text = []
+
+summ_col = st.columns([2,8,2])
+
+with summ_col[1]:
+    if select_mode == "Summarizer":
+        ## input file
+        File_input = st.file_uploader(
+            label="Drop Your File hear",
+            type=["txt", "pdf"],
+            key="file uploader"
+        )
+        if File_input is not None:
+            if File_input.type == "text/plain":
+                text = File_input.read().decode("utf-8")
+                st.session_state.input_text = []
+                st.session_state.input_text = st.text_area(label="Uploaded document Text",value=Text_Cleaning(text),height=200)
+                Text_input = Text_Cleaning(st.session_state.input_text)
+                value_func = lambda x: x * 0.3 
+                max_length = st.slider(
+                    label="Max Length",min_value=1,
+                    max_value=len(st.session_state.input_text.split()),
+                    value=int(value_func(len(st.session_state.input_text.split())))
+                )
+
+                if st.button(label="📄 Generate Summary"):
+                    with st.spinner("Generating Summary"):
+
+                        Generated_Summary = Summarizer_Model(context=Text_input,Max_Length=max_length)
+                        st.write(Generated_Summary)
+                        Copy_Text(Generated_Summary)
+            
+            else:
+                st.session_state.pdf_text = []
+                st.session_state.summary_text = []
+                st.session_state.pdf_text = pdf_Summarizer(File_input)
+
+                ## text area
+                Text_Area_Input = st.text_area(
+                    "Pdf Text",value=Text_Cleaning(st.session_state.pdf_text),
+                    key="text area",height=450
+                )
+
+                value_func = lambda x: x * 0.3 
+                Max_Pdf_Summary_len = st.slider(
+                    label="MAx Length",
+                    min_value=1,
+                    max_value=len(Text_Area_Input.split()),
+                    value=int(value_func(len(Text_Area_Input.split()))),
+                    key="pdf summarizer Slider"
+                )
+
+                if st.button("📑 Generate Summary",key="pdf Summary"):
+                    # generating summary
+                    with st.spinner("Generating Summary"):
+                        ## initilizing model
+                        st.session_state.summary_text = Summarizer_Model(
+                            context=Text_Area_Input,Max_Length=Max_Pdf_Summary_len
+                        )
+
+                        st.write(st.session_state.summary_text)
+                        Copy_Text(st.session_state.summary_text)
+
+
+
+
+
+                

data/functions.py

@@ -0,0 +1,129 @@
+# creating function file
+import streamlit as st
+import requests
+from bs4 import BeautifulSoup
+import re
+from cleantext import clean
+import streamlit.components.v1 as component
+
+def Copy_Text(text):
+    """
+    copy button to copy text
+    """
+    Html_Code = f"""
+    <!DOCTYPE html>
+    <html lang="en">
+    <head>
+        <meta charset="UTF-8">
+        <meta name="viewport" content="width=device-width, initial-scale=1.0">
+        <title>Copy Button</title>
+        <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.2/css/all.min.css">
+        <style>            
+            p {{
+                font-size: 18px;
+                margin-bottom: 10px;
+            }}
+            .copy-link {{
+                color: #6643b5;
+                text-decoration: none;
+                margin-top: 32px;
+                margin-left: 13px;
+                font-size: 20px;
+                display: inline-flex;
+                align-items: center;
+                gap: 5px;
+                position: relative;
+                transition: background 0.3s;
+                cursor: pointer;
+            }}
+            .copy-link:hover {{
+                color: #8594e4;
+            }}
+            .tooltip {{
+                position: absolute;
+                top: -30px;
+                left: 50%;
+                transform: translateX(-50%);
+                background: black;
+                color: white;
+                padding: 5px 10px;
+                font-size: 12px;
+                border-radius: 5px;
+                opacity: 0;
+                transition: opacity 0.3s, transform 0.3s;
+            }}
+            .show-tooltip {{
+                opacity: 1;
+                transform: translate(-50%, -10px);
+            }}
+        </style>
+    </head>
+    <body>
+        <div class="container">
+            <a href="#" class="copy-link" onclick="copyText(event)">
+                <i class="fa-regular fa-copy"></i>
+                <span class="tooltip" id="tooltip">Copied!</span>
+            </a>
+            <br>
+            <br>
+            <p id="text">{text}</p>
+        </div>
+        <script>
+            function copyText(event) {{
+                event.preventDefault();
+                const text = document.getElementById("text").innerText;
+                const textarea = document.createElement("textarea");
+                textarea.value = text;
+                document.body.appendChild(textarea);
+                textarea.select();
+                document.execCommand("copy");
+                document.body.removeChild(textarea);
+                
+                const tooltip = document.getElementById("tooltip");
+                tooltip.classList.add("show-tooltip");
+                setTimeout(() => {{
+                    tooltip.classList.remove("show-tooltip");
+                }}, 1000);
+            }}
+        </script>
+    </body>
+    </html>
+    """
+    component.html(Html_Code,height=60,width=60)
+
+
+
+
+def scrape_paragraphs(url, num_paragraphs):
+    try:
+        response = requests.get(url)
+        if response.status_code != 200:
+            return []
+        soup = BeautifulSoup(response.text, 'lxml')
+        paragraphs = [p.get_text() for p in soup.find_all('p')[:num_paragraphs]]
+        return paragraphs
+    except Exception as e:
+        st.warning(f"Error...\n{e}",icon="⚠️")
+        return []
+
+
+### text cleaning 
+def Text_Cleaning(text:str)->str:
+    """
+    this function gives clean 
+    text of the paragraphs , etc
+    which makes easy to understand of the text
+    """
+    pattern = r'[`^]'
+    cleaned_paragraph = re.sub(pattern, '', text)
+
+    clean_text = clean(
+        text=cleaned_paragraph,fix_unicode=True,
+        to_ascii=True,
+        no_line_breaks=False,
+        keep_two_line_breaks=True
+    )
+
+    pattern = r'\[\d+\]'
+    cleaned_text_output = re.sub(pattern, '', clean_text)
+    return cleaned_text_output

data/html_files/about.html

@@ -0,0 +1,526 @@
+<!DOCTYPE html>
+<html lang="en">
+
+<head>
+    <meta charset="UTF-8">
+    <meta name="viewport" content="width=device-width, initial-scale=1.0">
+    <title>About Project</title>
+    <!-- <link rel="stylesheet" href="style.css"> -->
+    <!-- link for poppins font -->
+    <link rel="preconnect" href="https://fonts.googleapis.com">
+    <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
+    <link
+        href="https://fonts.googleapis.com/css2?family=Poppins:ital,wght@0,100;0,200;0,300;0,400;0,500;0,600;0,700;0,800;0,900;1,100;1,200;1,300;1,400;1,500;1,600;1,700;1,800;1,900&display=swap"
+        rel="stylesheet">
+    <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.7.2/css/all.min.css"
+        integrity="sha512-Evv84Mr4kqVGRNSgIGL/F/aIDqQb7xQ2vcrdIwxfjThSH8CSR7PBEakCr51Ck+w+/U6swU2Im1vVX0SVk9ABhg=="
+        crossorigin="anonymous" referrerpolicy="no-referrer" />
+    <!-- Internal CSS -->
+    <style>
+        * {
+            margin: 0;
+            padding: 0;
+            box-sizing: border-box;
+            /* cursor: pointer; */
+        }
+        body {
+            font-family: 'Poppins', sans-serif;
+            background-color: rgb(14, 17, 23);
+            color: rgb(250, 250, 250);
+            line-height: 1.6;
+        }
+        .main-container {
+            max-width: 900px;
+            margin: 0 auto;
+            padding: 20px;
+        }
+        /* ------ Header Section -------*/
+        header {
+            /* text-align: center; */
+            margin-bottom: 30px;
+        }
+        .hover {
+            text-shadow: 0 0 20px rgba(98, 162, 250, 0.4);
+        }
+        header h1 {
+            font-size: 3em;
+            color: rgb(98, 162, 250);
+            cursor: pointer;
+        }
+        header h2 {
+            font-size: 2.5em;
+            color: white;
+            cursor: pointer;
+        }
+        header h2:hover {
+            text-shadow: 0 0 20px rgba(255, 255, 255, 0.4);
+        }
+        /* ------ About Section ------ */
+        .about {
+            position: relative;
+            background-color: rgb(24, 28, 38);
+            padding: 20px;
+            border-radius: 15px;
+            margin-bottom: 40px;
+            box-shadow: 0 8px 15px rgba(0, 0, 0, 0.4);
+            cursor: pointer;
+            /* width: 500px; */
+        }
+        .about:hover {
+            transform: scale(1.02);
+            border: 2px solid rgb(98, 162, 250);
+        }
+        .about h3 {
+            font-size: 1.8em;
+            margin-bottom: 15px;
+            color: rgb(98, 162, 250);
+        }
+        .about p,
+        .about ul {
+            font-size: 1.1em;
+            margin-bottom: 15px;
+        }
+        .about ul {
+            padding-left: 20px;
+            list-style-type: disc;
+        }
+        /* ------ Technologies Section ------ */
+        .technologies {
+            margin-top: 30px;
+        }
+        .technologies h2 {
+            font-size: 2em;
+            margin-bottom: 20px;
+            color: rgb(98, 162, 250);
+            cursor: pointer;
+        }
+        .technologies h2:hover {
+            /* text-decoration: underline; */
+            text-shadow: 0 0 20px rgba(98, 162, 250, 0.4);
+        }
+        .row {
+            display: flex;
+            justify-content: space-around;
+            align-items: center;
+        }
+        .tech-card {
+            align-items: center;
+            /* width: 30%;
+            height: 300px; */
+            width: 43%;
+            height: 255px;
+            /* background-color: rgb(46, 84, 182); */
+            background-color: rgb(24, 28, 38);
+            padding: 15px;
+            border-radius: 15px;
+            box-shadow: 0 8px 15px rgba(0, 0, 0, 0.4);
+            margin-bottom: 20px;
+            position: relative;
+            overflow: hidden;
+            transition: transform 0.3s ease;
+            cursor: pointer;
+        }
+        .tech-card h4 {
+            color: rgb(98, 162, 250);
+            font-size: 1.3rem;
+            text-align: center;
+            margin-bottom: 5px;
+        }
+        /*
+        .tech-card > p {
+            text-align: justify;
+        } 
+        */
+        .tech-card:hover {
+            transform: scale(1.02);
+        }
+        .tech-card::before {
+            content: '';
+            position: absolute;
+            top: 0;
+            left: 0;
+            width: 100%;
+            height: 100%;
+            background: rgba(24, 28, 38, 0.4);
+            /* blur color */
+            filter: blur(20px);
+            z-index: -1;
+            opacity: 0;
+            transition: opacity 0.3s ease;
+        }
+        .tech-card:hover::before {
+            opacity: 1;
+        }
+        @keyframes glow {
+            0% {
+                box-shadow: 0 0 20px rgba(24, 28, 38, 0.4), 0 0 40px rgba(24, 28, 38, 0.3), 0 0 60px rgba(24, 28, 38, 0.2);
+            }
+
+            100% {
+                box-shadow: 0 0 20px rgba(24, 28, 38, 0.4), 0 0 40px rgba(24, 28, 38, 0.3), 0 0 60px rgba(24, 28, 38, 0.2);
+            }
+        }
+        .tech-card:hover {
+            animation: glow 1.5s infinite ease-in-out;
+        }
+        /* ------ Developers Section ------ */
+        .developers {
+            margin-top: 30px;
+        }
+        .developers h2 {
+            font-size: 2em;
+            margin-bottom: 20px;
+            color: rgb(98, 162, 250);
+            cursor: pointer;
+        }
+        .developers h2:hover {
+            text-shadow: 0 0 20px rgba(98, 162, 250, 0.4);
+        }
+        .developer-card {
+            display: flex;
+            align-items: center;
+            background-color: rgb(24, 28, 38);
+            padding: 15px;
+            border-radius: 15px;
+            box-shadow: 0 8px 15px rgba(0, 0, 0, 0.4);
+            margin-bottom: 20px;
+        }
+        .profile img {
+            width: 100px;
+            height: 100px;
+            border-radius: 50%;
+            border: 2px solid rgb(98, 162, 250);
+        }
+        .details {
+            margin-left: 20px;
+            display: flex;
+            width: 80%;
+            margin: auto;
+            justify-content: space-between;
+        }
+        .details p {
+            font-size: 1.2em;
+            margin-bottom: 10px;
+        }
+        .developer {
+            display: inline-block;
+            width: 200px;
+        }
+        .developer-name {
+            cursor: pointer;
+            width: 200px;
+        }
+        .developer-name:hover {
+            text-shadow: 0 0 20px rgba(255, 255, 255, 0.4);
+        }
+        .social-icons {
+            display: flex;
+
+        }
+        .social-icons a {
+            text-decoration: none;
+            margin: 0px 15px;
+        }
+        .fa-brands.fa-linkedin.fa-2xl {
+            color: gray
+        }
+        .fa-brands.fa-linkedin.fa-2xl:hover {
+            color: rgb(98, 162, 250);
+            text-shadow: 0 0 20px rgba(98, 162, 250, 0.9);
+        }
+        .fa-brands.fa-github.fa-2xl {
+            color: gray;
+        }
+        .fa-brands.fa-github.fa-2xl:hover {
+            /* color: rgb(98, 162, 250); */
+            color: rgb(255, 255, 255);
+            text-shadow: 0 0 20px rgba(98, 162, 250, 0.9);
+        }
+        /* ----------- Media Query Section ------------ */
+        @media screen and (max-width: 768px) {
+            .main-container {
+                max-width: 600px;
+                margin: 0 auto;
+                padding: 20px;
+            }
+            .row {
+                display: block;
+            }
+            .tech-card {
+                margin: auto;
+                width: 100%;
+                bottom: 10px;
+                margin-bottom: 20px;
+                height: 215px;
+            }
+        }
+        @media screen and (max-width: 600px) {
+            .about p,
+            .about ul {
+                font-size: 16px;
+                margin-bottom: 10px;
+            }
+        }
+        @media screen and (max-width: 500px) {
+            /* .main-container {
+              max-width: 600px;
+              margin: 0 auto;
+              padding: 20px;
+            } */
+            header h1 {
+                font-size: 35px;
+            }
+            header h2 {
+                font-size: 28px;
+            }
+            .about h3 {
+                font-size: 1.5em;
+            }
+            .technologies h2 {
+                font-size: 1.5em;
+            }
+            .developers h2 {
+                font-size: 1.5em;
+            }
+            .details p {
+                font-size: 17px;
+                margin-bottom: 10px;
+                display: block;
+            }
+            .developer {
+                width: 50%;
+                margin: auto;
+                display: block;
+                margin-top: 10px;
+            }
+        }
+        @media screen and (max-width: 420px) {
+            .about p,
+            .about ul {
+                font-size: 15px;
+            }
+            p {
+                font-size: 15px;
+            }
+            header h1 {
+                font-size: 28px;
+            }
+            header h2 {
+                font-size: 24px;
+            }
+            .about h3 {
+                font-size: 1.2em;
+            }
+            .technologies h2 {
+                font-size: 1.2em;
+            }
+            .developers h2 {
+                font-size: 1.2em;
+            }
+            .details {
+                display: block;
+            }
+        }
+        @media screen and (max-width: 375px) {
+            header h1 {
+                font-size: 24px;
+            }
+            header h2 {
+                font-size: 20px;
+            }
+            .about h3 {
+                font-size: 1.1em;
+            }
+            .technologies h2 {
+                font-size: 1.1em;
+            }
+            .developers h2 {
+                font-size: 1.1em;
+            }
+            .details {
+                display: block;
+            }
+        }
+    </style>
+</head>
+<body>
+    <!-- Main Container -->
+    <div class="main-container">
+        <!-- Header Section -->
+        <header>
+            <h1 class="hover">About Project</h1>
+        </header>
+        <!-- About Project Section -->
+        <section class="about">  
+            <p>
+                In the digital era, information overload is a major challenge. Our <strong>AI for Smart Document
+                    Summarization
+                    and Automated Question Generation </strong> aims to simplify content processing by leveraging
+                advanced natural
+                language processing (NLP) techniques.
+                This project is designed for students, researchers, content creators, and professionals who need quick
+                insights from large volumes of data. By automating summarization and question generation, our AI
+                solution enhances productivity and knowledge retention effortlessly.
+            </p>
+            <p><strong>How It Works:</strong></p>
+            <ul>
+                <li>
+                    Input – Paste text, enter a URL, or upload a document.
+                </li>
+                <li>
+                    Processing – The AI extracts essential insights, removes redundancies, and formulates a structured
+                    summary.
+                </li>
+                <li>
+                    Output – Receive a well-structured summary and a set of AI-generated questions for further analysis.
+                </li>
+            </ul>
+            <p>
+            <p><strong>Key features include:</strong></p>
+            <ul>
+                <li>
+                    Smart Summarization – Input any text, URL, or document, and our AI-powered system generates a
+                    concise and meaningful summary.
+                </li>
+                <li>
+                    Automated Question Generation – Transform lengthy articles into relevant questions, making it ideal
+                    for study materials, research, and knowledge assessment.
+                </li>
+            </ul>
+            <p>
+                Developed using <strong>Streamlit</strong>, this project demonstrates cutting-edge technology with an
+                interactive and user-friendly interface.
+            </p>
+        </section>
+        <!-- Teechnologies Used Section -->
+        <section class="technologies">
+            <h2>Technologies Used</h2>
+            <div class="technology-card">
+                <!-- Row 1 -->
+                <div class="row">
+                    <div class="tech-card">
+                        <h4>Python</h4>
+                        <p>
+                            Used as the core programming language for implementing document summarization and automated question generation, leveraging NLP models and AI algorithms for efficient text processing.
+                        </p>
+                    </div>
+                    <div class="tech-card">
+                        <h4>HTML</h4>
+                        <p>
+                            Used to structure the web pages, including sections like "About Project," "Technologies Used," and user interaction areas, ensuring a clean and semantic layout.
+                        </p>
+                    </div>
+                </div>
+                <!-- Row 2 -->
+                <div class="row">
+                    <div class="tech-card">
+                        <h4>CSS</h4>
+                        <p>
+                            Utilized for styling the web interface, improving visual aesthetics, adding animations, and ensuring a responsive design across different devices.
+                        </p>
+                    </div>
+                    <div class="tech-card">
+                        <h4>JavaScript</h4>
+                        <p>
+                            Implemented interactive elements like real-time updates, animations, and user-friendly components to enhance the overall experience.
+                        </p>
+                    </div>
+                </div>
+                <!-- Row 3 -->
+                <div class="row">
+                    <div class="tech-card">
+                        <h4>Streamlit</h4>
+                        <p>
+                            Used to develop the web-based interface, allowing users to input text, URLs, or documents for summarization and question generation seamlessly.
+                        </p>
+                    </div>
+                    <div class="tech-card">
+                        <h4>Facebook-BART</h4>
+                        <p>
+                            A powerful transformer-based model used for text summarization and natural language understanding, ensuring high-quality summaries with contextual relevance.
+                        </p>
+                    </div>
+                </div>
+                <!-- Row 4 -->
+                <div class="row">
+                    <div class="tech-card">
+                        <h4>Transformers (Hugging Face)</h4>
+                        <p>
+                            Leverages pre-trained transformer models for advanced natural language processing tasks, optimizing summarization and question generation.
+                        </p>
+                    </div>
+                    <div class="tech-card">
+                        <h4>PDFMiner</h4>
+                        <p>
+                            Used for extracting text from PDF files, enabling document-based summarization and automated question generation without losing content integrity.
+                        </p>
+                    </div>
+                </div><!-- Row 5 -->
+                <div class="row">
+                    <div class="tech-card">
+                        <h4>Web Summarizer & Q&A Module</h4>
+                        <p>
+                            An AI-powered system designed to extract key insights from online content, generating concise summaries and relevant questions for better comprehension.
+                        </p>
+                    </div>
+                    <div class="tech-card">
+                        <h4>Text Processing</h4>
+                        <p>
+                            Handles raw text input efficiently, ensuring proper parsing, cleaning, and analysis before summarization and question generation.
+                        </p>
+                    </div>
+                </div>
+                <!-- Row 6 -->
+                <div class="row">
+                    <div class="tech-card">
+                        <h4>PDF Support</h4>
+                        <p>
+                            Enables users to upload and process PDF documents, extracting text to generate summaries and structured questions automatically.
+                        </p>
+                    </div>
+                    <!-- <div class="tech-card">
+                        <h4>Text Processing</h4>
+                        <p>
+                            Handles raw text input efficiently, ensuring proper parsing, cleaning, and analysis before summarization and question generation.
+                        </p>
+                    </div> -->
+                </div>
+            </div>
+        </section>
+        <!-- Developers Section -->
+        <section class="developers">
+            <h2>Developers</h2>
+            <div class="developer-card">
+                <div class="details">
+                    <!-- Nishant -->
+                    <div class="developer">
+                        <p class="developer-name"><strong>Nishant Maity</strong></p>
+                        <div class="social-icons">
+                            <a href="https://www.linkedin.com/in/nishant-maity/" target="_blank">
+                                <i class="fa-brands fa-linkedin fa-2xl"></i>
+                            </a>
+                            <a href="https://github.com/Nishant43S" target="_blank">
+                                <i class="fa-brands fa-github fa-2xl"></i>
+                            </a>
+                        </div>
+                    </div>
+                    <!-- Yash -->
+                    <div class="developer">
+                        <p class="developer-name"><strong>Yash Sahu</strong></p>
+                        <div class="social-icons">
+                            <a href="https://www.linkedin.com/in/yashsahu02" target="_blank">
+                                <i class="fa-brands fa-linkedin fa-2xl"></i>
+                            </a>
+                            <a href="https://github.com/yashsahu02" target="_blank">
+                                <i class="fa-brands fa-github fa-2xl"></i>
+                            </a>
+                        </div>
+                    </div>
+                </div>
+            </div>
+        </section>
+    </div>
+    <!-- FontAwesome for icons -->
+    <script src="https://kit.fontawesome.com/a076d05399.js" crossorigin="anonymous"></script>
+</body>
+</html>

data/text.py

@@ -0,0 +1,174 @@
+import streamlit as st
+import re
+from cleantext import clean
+import streamlit.components.v1 as component
+from transformers import pipeline
+from functions import Copy_Text
+from functions import *
+
+# page settings 
+st.set_page_config(
+    layout="wide",
+    initial_sidebar_state="collapsed"
+)
+
+### insert external css
+def insert_css(css_file:str):
+    with open(css_file) as f:
+        st.markdown(f"<style>{f.read()}</style>",unsafe_allow_html=True)
+
+# app settings css
+insert_css("css_files/app.css")
+
+# sidebar
+app_sidebar = st.sidebar
+with app_sidebar:
+    select_mode = st.selectbox(
+        label="Select Mode",
+        options=["Summarizer","Que/Ans"],
+        key="mode selector",
+        index=0
+    )
+
+    if select_mode == "Que/Ans":
+        st.write("### Que/Ans Settings")
+
+        max_answer_length = st.slider(
+            label="Max answer",
+            min_value=1,
+            max_value=10,
+            key="max answer",
+            value=4
+        )
+
+        max_answer_length = max_answer_length*10
+
+        Best_size = st.slider(
+            label="n best size",
+            min_value=1,
+            max_value=10,
+            key="best size",
+            value=5
+        )
+
+# initilize session state
+if 'summary' not in st.session_state:
+    st.session_state.summary = []    
+
+app_col = st.columns([2,8,2])
+
+with app_col[1]:
+
+    if select_mode == "Summarizer":
+        st.write("## Text Summarizer")
+    elif select_mode == "Que/Ans":
+        st.write("## 📚 Text Question Answering")
+
+#################### question answering ####################
+
+if select_mode == "Que/Ans":
+    app_c = st.columns([2,8,2])
+    with app_c[0]:
+        pass
+    with app_c[1]:
+        # Inject custom CSS to place the chat input at the bottom
+        st.markdown(
+            """
+            <style>
+                /* Fix the chat input box at the bottom */
+                div[data-testid="stChatInput"] {
+                    position: fixed;
+                    bottom: 0;
+                    margin-bottom: 36px;
+                    
+                }
+            </style>
+            """,
+            unsafe_allow_html=True
+        )
+        # Load model
+        qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
+
+        # Initialize session state 
+        if "messages" not in st.session_state:
+            st.session_state.messages = []
+
+        # User inputs context
+        context = st.text_area("📜 Enter Text Hear", "", height=200)
+        context = Text_Cleaning(context)
+
+        # Display chat history
+        for message in st.session_state.messages:
+            with st.chat_message(message["role"]):
+                st.markdown(message["content"])
+
+        if context:
+            user_input = st.chat_input("💬 Ask a question ",)
+            if user_input:
+                with st.chat_message("user"):
+                    st.markdown(user_input)
+                        
+                st.session_state.messages.append({"role": "user", "content": user_input})
+                        
+                with st.spinner("🤔 Thinking..."):
+                    response = qa_pipeline({"question": user_input, "context": context}, 
+                                           max_answer_len=max_answer_length, n_best_size=Best_size)
+                    answer = response["answer"]
+                        
+                    with st.chat_message("assistant"):
+                        st.markdown(f"{answer}")
+                        
+                    st.session_state.messages.append({"role": "assistant", "content": f"{answer}"})
+
+            # Clear chat history button
+            if st.button("🗑️ Clear Chat"):
+                st.session_state.messages = []
+                st.rerun()
+
+
+############ summarizer ###########
+
+app_sum_col = st.columns([2,8,2])
+
+
+# add session state
+if 'summary' not in st.session_state:
+    st.session_state.summary = []
+
+with app_sum_col[1]:
+    if select_mode == "Summarizer":
+        Text_input = st.text_area(label="📜 Enter Text Hear",key="Summarizer input",height=220)
+        Text_input = Text_Cleaning(Text_input)
+
+        if Text_input.strip() != "":
+            st.session_state.summary = []
+
+            value_func = lambda x: x * 0.3 
+            # max length
+            max_tokens = st.slider(
+                label="Max Length",
+                key="max length",
+                min_value=1,
+                max_value=len(Text_input.split()),
+                value=int(value_func(len(Text_input.split())))
+            )
+
+            if st.button(label="📄 Generate Summary "):
+                try:
+                    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+                    st.session_state.summary = summarizer(
+                        Text_input,
+                        max_length=max_tokens+20, 
+                        min_length=max_tokens, 
+                        do_sample=False
+                    )
+
+                except Exception as e:
+                    st.warning(f"Error...\n{e}",icon="⚠️")
+                
+                if st.session_state.summary:
+                    with st.spinner("Generating Summary..."):
+                        st.write("### Summary")
+                        generated_summary = st.session_state.summary[0]['summary_text']
+                        st.write(generated_summary)
+                        Copy_Text(generated_summary)

data/webscraper.py

@@ -0,0 +1,200 @@
+import streamlit as st
+import requests
+from bs4 import BeautifulSoup
+import re
+from cleantext import clean
+import streamlit.components.v1 as component
+from transformers import pipeline
+from functions import Copy_Text
+from functions import *
+
+### import animation
+def particle(Js_file):
+    with open(Js_file) as f:
+        component.html(f"{f.read()}", height=400)
+
+### insert external css
+def insert_css(css_file:str):
+    with open(css_file) as f:
+        st.markdown(f"<style>{f.read()}</style>",unsafe_allow_html=True)
+
+
+# page settings
+st.set_page_config(
+    layout="wide",
+    initial_sidebar_state="collapsed"
+)
+
+# sidebar
+app_sidebar = st.sidebar
+with app_sidebar:
+    select_mode = st.selectbox(
+        label="Select Mode",
+        options=["Summarizer","Que/Ans"],
+        key="mode selector",
+        index=0
+    )
+
+    if select_mode == "Que/Ans":
+        st.write("### Que/Ans Settings")
+
+        max_answer_length = st.slider(
+            label="Max answer",
+            min_value=1,
+            max_value=10,
+            key="max answer",
+            value=4
+        )
+
+        max_answer_length = max_answer_length*10
+
+        Best_size = st.slider(
+            label="n best size",
+            min_value=1,
+            max_value=10,
+            key="best size",
+            value=5
+        )
+
+# Initialize session state
+if 'scraped_paragraphs' not in st.session_state:
+    st.session_state.scraped_paragraphs = []
+if 'summarizer_mode' not in st.session_state:
+    st.session_state.summarizer_mode = False
+if 'summary' not in st.session_state:
+    st.session_state.summary = []
+
+app_col = st.columns([2,8,2],gap="small")
+
+with app_col[0]:
+    pass
+
+with app_col[2]:
+    pass
+
+with app_col[1]:
+    # Title
+    st.write("## GenAi Scraper")
+
+    # Input URL
+    url_input = st.text_input(label="Enter Website URL",key="url input",placeholder="https://www.example.com")
+
+    # number of paragraphs
+    num_paragraphs = st.slider("Select number of paragraphs to scrape", 1, 30, 5)
+
+    scrap_btn = st.button("Scrape Paragraphs",key="scrap button")
+
+    if url_input.strip() == "" and not scrap_btn:
+        # animation
+        particle("animation/particles.html")
+
+    else:
+        if scrap_btn:
+            st.session_state.scraped_paragraphs = scrape_paragraphs(url_input, num_paragraphs)
+            st.session_state.summary = []  # Reset summary
+
+        # Display scraped paragraphs
+        if st.session_state.scraped_paragraphs:
+            
+            st.write("### Scraped Paragraphs")
+            
+            paragraph_scrap = "\n\n".join(st.session_state.scraped_paragraphs)
+            st.write(Text_Cleaning(paragraph_scrap))
+
+            Copy_Text(Text_Cleaning(paragraph_scrap)) ## copy text
+        
+        #################### summarizer  #############
+
+        if select_mode == "Summarizer":    
+            if st.session_state.scraped_paragraphs:
+                # Toggle for summarization mode
+                st.session_state.summarizer_mode = st.toggle("Enable Summarizer Mode", st.session_state.summarizer_mode)
+                    
+                if st.session_state.summarizer_mode:
+                    value_func = lambda x: x * 0.3 
+                    max_tokens = st.slider(label="Select Max Token Length", min_value=10, 
+                                    max_value=sum(len(p.split()) for p in st.session_state.scraped_paragraphs), 
+                                    value=int(value_func(
+                                        sum(len(p.split()) for p in st.session_state.scraped_paragraphs)
+                                    ))
+                                )
+                    if st.button("📄 Generate Summary"):
+                        with st.spinner("Generating Summary..."):
+                            try:
+                                summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+                                st.session_state.summary = summarizer(
+                                    Text_Cleaning(" ".join(st.session_state.scraped_paragraphs)),
+                                    max_length=max_tokens+20, 
+                                    min_length=max_tokens, 
+                                    do_sample=False
+                                )
+
+                            except Exception as e:
+                                st.warning(f"Error...\n{e}",icon="⚠️")
+                    
+                # Display summary 
+                if st.session_state.summary:
+                    st.write("### Summary")
+                    generated_summary = st.session_state.summary[0]['summary_text']
+                    st.write(generated_summary)
+                    Copy_Text(generated_summary)
+        
+        ################# question answering #####################
+
+        elif select_mode == "Que/Ans":
+            if st.session_state.scraped_paragraphs:
+                if st.toggle(label="Question Answering",key="Q/A"):
+                    # Inject custom CSS to place the chat input at the bottom
+                    st.markdown(
+                        """
+                        <style>
+                            /* Fix the chat input box at the bottom */
+                            div[data-testid="stChatInput"] {
+                                position: fixed;
+                                bottom: 0;
+                                margin-bottom: 36px;
+                                
+                            }
+                        </style>
+                        """,
+                        unsafe_allow_html=True
+                    )
+                    qa_pipeline = pipeline("question-answering", model="deepset/roberta-base-squad2")
+
+                    # Initialize session state 
+                    if "messages" not in st.session_state:
+                        st.session_state.messages = []
+
+                    # User inputs context
+                    context = Text_Cleaning(paragraph_scrap)
+
+                    # Display chat history
+                    for message in st.session_state.messages:
+                        with st.chat_message(message["role"]):
+                            st.markdown(message["content"])
+
+                    if context:
+                        user_input = st.chat_input("💬 Ask a question ",)
+                        if user_input:
+                            with st.chat_message("user"):
+                                st.markdown(user_input)
+                                    
+                            st.session_state.messages.append({"role": "user", "content": user_input})
+                                    
+                            with st.spinner("🤔 Thinking..."):
+                                response = qa_pipeline({"question": user_input, "context": context},
+                                                       max_answer_len=max_answer_length, n_best_size=Best_size)
+                                answer = response["answer"]
+                                    
+                                with st.chat_message("assistant"):
+                                    st.markdown(f"{answer}")
+                                    
+                                st.session_state.messages.append({"role": "assistant", "content": f"{answer}"})
+
+                        # Clear chat history button
+                        if st.button("🗑️ Clear Chat"):
+                            st.session_state.messages = []
+                            st.rerun()
+
+# app settings css
+insert_css("css_files/app.css")