app.py

import streamlit as st
import os
import pickle
from streamlit_extras.add_vertical_space import add_vertical_space
from huggingface_hub import Repository
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import OpenAI
from langchain.chains.question_answering import load_qa_chain
from langchain.callbacks import get_openai_callback

# Step 1: Clone the Dataset Repository
repo = Repository(
    local_dir="Private_Book",  # Local directory to clone the repository
    repo_type="dataset",  # Specify that this is a dataset repository
    clone_from="Anne31415/Private_Book",  # Replace with your repository URL
    token=os.getenv("HUB_TOKEN")  # Use the secret token to authenticate
)
repo.git_pull()  # Pull the latest changes (if any)

# Step 2: Load the PDF File
pdf_file_path = "Private_Book/KOMBI_all2.pdf"  # Replace with your PDF file path

def cloud_button(label, key=None, color=None, overlap=30):
    button_id = f"cloud-button-{key or label}"
    color_class = f"color-{color}" if color else ""
    num_circles = max(3, min(20, len(label) // 4))
    circle_size = 60

    # Create circles with text enclosed
    circles_html = ''.join([
        f'<div class="circle {color_class}" style="margin-right: -{overlap}px;"></div>'
        for _ in range(num_circles)
    ])
    circles_html += f'<div class="circle-text">{label}</div>'  # Add the text after the circles

    cloud_button_html = f"""
    <div class="cloud" id="{button_id}" style="margin-bottom: 20px;">
        <div class="wrapper {color_class}">
            {circles_html}
        </div>
    </div>
    <style>
        .cloud {{
            position: relative;
            display: inline-flex;
            align-items: center;
            justify-content: center;
        }}
        .wrapper {{
            display: flex;
            align-items: center;
            justify-content: center;
            position: relative;
            padding: 10px 20px;
        }}
        .circle {{
            background-color: #FF6347;
            border-radius: 50%;
            width: {circle_size}px;
            height: {circle_size}px;
            position: relative;
            margin-right: {overlap}px; /* Adjust the margin for overlapping effect */
        }}
        .circle-text {{
            position: absolute;
            top: 50%;
            left: 50%;
            transform: translate(-50%, -50%);
            font-weight: bold;
            z-index: 2;
            white-space: nowrap;  /* Prevent line breaks */
            text-align: center; /* Center the text horizontally and vertically */
        }}
        /* Add this CSS for the hover effect and shadow */
        .cloud:hover .circle {{
            transform: scale(1.1); /* Scale up the circles on hover */
            box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1); /* Add a shadow on hover */
        }}
        
        .color-1 .circle {{ background-color: #FFA07A; }}
        .color-2 .circle {{ background-color: #FF7F50; }}
        .color-3 .circle {{ background-color: #FF6347; }}
    </style>
    <script>
        document.getElementById("{button_id}").onclick = function() {{
            // Your existing JavaScript code for handling button click
        }};
    </script>
    """
    st.markdown(cloud_button_html, unsafe_allow_html=True)



# Example usage with a specified overlap value
cloud_button("Short Text", color="1", overlap=30)
cloud_button("This is a longer piece of text", color="2", overlap=30)
cloud_button("This is an even longer piece of text to test the cloud button", color="3", overlap=30)



def load_pdf(file_path):
    pdf_reader = PdfReader(file_path)
    text = ""
    for page in pdf_reader.pages:
        text += page.extract_text()

    text_splitter = RecursiveCharacterTextSplitter(
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )
    chunks = text_splitter.split_text(text=text)

    store_name, _ = os.path.splitext(os.path.basename(file_path))

    if os.path.exists(f"{store_name}.pkl"):
        with open(f"{store_name}.pkl", "rb") as f:
            VectorStore = pickle.load(f)
    else:
        embeddings = OpenAIEmbeddings()
        VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
        with open(f"{store_name}.pkl", "wb") as f:
            pickle.dump(VectorStore, f)

    return VectorStore

def load_chatbot():
    return load_qa_chain(llm=OpenAI(), chain_type="stuff")

def display_chat_history(chat_history):
    for chat in chat_history:
        background_color = "#FFA07A" if chat[2] == "new" else "#acf" if chat[0] == "User" else "#caf"
        st.markdown(f"<div style='background-color: {background_color}; padding: 10px; border-radius: 10px; margin: 10px;'>{chat[0]}: {chat[1]}</div>", unsafe_allow_html=True)

def main():
    with st.sidebar:
        st.title('BinDoc GmbH')
        st.markdown("Experience revolutionary interaction with BinDocs Chat App, leveraging state-of-the-art AI technology.")
        
        add_vertical_space(1)  # Adjust as per the desired spacing
        
        st.markdown("""
        Hello! I’m here to assist you with:<br><br>
        📘 **Glossary Inquiries:**<br>
        I can clarify terms like "DiGA", "AOP", or "BfArM", providing clear and concise explanations to help you understand our content better.<br><br>
        
        🆘 **Help Page Navigation:**<br>
        Ask me if you forgot your password or want to know more about topics related to the platform.<br><br>
        
        📰 **Latest Whitepapers Insights:**<br>
        Curious about our recent publications? Feel free to ask about our latest whitepapers!<br><br>
        """, unsafe_allow_html=True)
        
        add_vertical_space(1)  # Adjust as per the desired spacing
        st.write('Made with ❤️ by BinDoc GmbH')
        api_key = os.getenv("OPENAI_API_KEY")

    hide_streamlit_style = """
        <style>
        #MainMenu {visibility: hidden;}
        footer {visibility: hidden;}
        </style>
    """
    st.markdown(hide_streamlit_style, unsafe_allow_html=True)

    # Main content
    st.title("Welcome to BinDocs ChatBot! 🤖")




    pdf_path = "path_to_your_pdf_file.pdf"  # Update this to the path of your PDF file
    if not os.path.exists(pdf_path):
        st.error("File not found. Please check the file path.")
        return

    if "chat_history" not in st.session_state:
        st.session_state['chat_history'] = []

    display_chat_history(st.session_state['chat_history'])

    st.write("<!-- Start Spacer -->", unsafe_allow_html=True)
    st.write("<div style='flex: 1;'></div>", unsafe_allow_html=True)
    st.write("<!-- End Spacer -->", unsafe_allow_html=True)

    new_messages_placeholder = st.empty()

    if pdf_path is not None:
        query = st.text_input("Ask questions about your PDF file (in any preferred language):")
        
        if st.button("Ask") or (not st.session_state['chat_history'] and query) or (st.session_state['chat_history'] and query != st.session_state['chat_history'][-1][1]):
            st.session_state['chat_history'].append(("User", query, "new"))
            loading_message = st.empty()
            loading_message.text('Bot is thinking...')
            VectorStore = load_pdf(pdf_path)
            chain = load_chatbot()
            docs = VectorStore.similarity_search(query=query, k=3)
            response = chain.run(input_documents=docs, question=query)
            st.session_state['chat_history'].append(("Bot", response, "new"))
            new_messages = st.session_state['chat_history'][-2:]
            for chat in new_messages:
                background_color = "#FFA07A" if chat[2] == "new" else "#acf" if chat[0] == "User" else "#caf"
                new_messages_placeholder.markdown(f"<div style='background-color: {background_color}; padding: 10px; border-radius: 10px; margin: 10px;'>{chat[0]}: {chat[1]}</div>", unsafe_allow_html=True)
            st.write("<script>document.getElementById('response').scrollIntoView();</script>", unsafe_allow_html=True)
            loading_message.empty()
            query = ""
        st.session_state['chat_history'] = [(sender, msg, "old") for sender, msg, _ in st.session_state['chat_history']]

if __name__ == "__main__":
    main()