markup.py

def app_intro():
    return """
    <div style='text-align: left;'>
    <h2 style='text-align: center;'>CIMA Textbooks Chatbot</h2>
    <h3 style='text-align: center;'>Introduction</h3>
            
    <p>Welcome to the CIMA Textbooks Chatbot! Our chatbot is designed to assist you with questions and information related to CIMA (Chartered Institute of Management Accountants) studies. Whether you need answers to standalone questions or want to evaluate sources, our chatbot is here to help.</p>

    <h4>Chat Options:</h4>
    <ul>
        <li><b>QA Option:</b> Get answers to standalone questions and evaluate sources.</li>
        <li><b>QA with Memory Option:</b> Has short-term memory to answer follow-up questions to a main question.</li>
        <li><b>Chat Option:</b> Fully dynamic and conversational AI chatbot that can be easily customized with additional options.</li>
    </ul>

    <h4>Indexed PDFs for Context:</h4>
    <ul>
        <li>E1 Study Text 2019-20 NPE.pdf - Managing Finance in a digital World</li>
        <li>E2 Study Text 2019-20 NPA.pdf - Managing Performance</li>
        <li>E3 Study Text 2019-20.pdf - Strategic Management</li>
        <li>F1 Study Text 2019-20 NPE_unlocked.pdf - Financial Reporting</li>
        <li>F2 Study Text 2019-20 NPA.pdf - Advanced Financial Reporting</li>
        <li>F3 Study Text 2019-20.pdf - Financial Strategy</li>
        <li>P1 Study Text 2019-20 NPA-unlocked.pdf - Management Accounting</li>
        <li>P2 Study Text 2019-20 NPE.pdf - Advanced Management Accounting</li>
        <li>P3 Study Text 2019-20 NPE.pdf - Risk Management</li>
    </ul>
    
    <p>This application utilizes a hybrid search method, which retrieves relevant text from the documents, regardless of the large number of pages in each textbook. This method combines a state-of-the-art sparse retrieval algorithm, ideal for finding keywords, with a dense retrieval method, proficient at locating documents through semantic similarity.</p>
    
    </div>          
    """