app.py

import streamlit as st
from dotenv import load_dotenv
import pickle
from huggingface_hub import Repository
from PyPDF2 import PdfReader
from streamlit_extras.add_vertical_space import add_vertical_space
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
import os

st.markdown("""
<style>
.cloud-button {
    position: relative;
    background: #E0E0E0;
    border: none;
    padding: 20px 40px;
    cursor: pointer;
    overflow: hidden;
    outline: none;
    box-shadow: 2px 2px 12px rgba(0,0,0,0.1);
}

/* Main cloud shape */
.cloud-button::before {
    content: '';
    position: absolute;
    background: #E0E0E0;
    border-radius: 50%;
    width: 150px;
    height: 150px;
    top: -50px;
    left: 50%;
    transform: translateX(-50%);
}

/* Additional cloud bubbles */
.cloud-button::after {
    content: '';
    position: absolute;
    background: #E0E0E0;
    border-radius: 50%;
    width: 120px;
    height: 120px;
    top: 20px;
    left: 15%;
}

.cloud-button span {
    position: relative;
    z-index: 1;
}

/* Hover effect */
.cloud-button:hover {
    box-shadow: 2px 2px 18px rgba(0,0,0,0.2);
}

/* Override some default styles for the button to ensure cloud shape */
.cloud-button, .cloud-button::before, .cloud-button::after {
    border: none;
    outline: none;
    text-decoration: none;
}

</style>

""", unsafe_allow_html=True)

if hasattr(st.session_state, "cloud_button_pressed"):
    query = st.session_state.cloud_button_pressed
    del st.session_state.cloud_button_pressed  # remove the attribute after using it



# 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.environ["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



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")
    # Retrieve the API key from st.secrets


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

# Load the PDF file when the app starts
if "pdf_data" not in st.session_state:
    st.session_state.pdf_data = load_pdf(pdf_file_path)



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

# Load the chatbot when the app starts
if "chatbot_instance" not in st.session_state:
    st.session_state.chatbot_instance = load_chatbot()

def main():

    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! 🤖")

    # Directly specifying the path to the PDF file
    pdf_path = pdf_file_path
    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):")

    st.markdown("""
    <button class="cloud-button" onclick="document.dispatchEvent(new CustomEvent('cloud_button_event', {detail: 'Was genau ist ein Belegarzt?'}));">
        <span>Was genau ist ein Belegarzt?</span>
    </button>
    <script>
    document.addEventListener('cloud_button_event', function(e) {
        window.streamlitSetComponentValue(e.detail);
});
</script>
""", unsafe_allow_html=True)


    if st.button("Wofür wird die Alpha-ID verwendet?"):
        query = "Wofür wird die Alpha-ID verwendet?"

    if st.button("Ask") or is_cloud_button_pressed or (not st.session_state['chat_history'] and query) or (st.session_state['chat_history'] and query != st.session_state['chat_history'][-1][1]):
        if is_cloud_button_pressed:
            query = is_cloud_button_pressed

        loading_message = st.empty()
        loading_message.text('Bot is thinking...')
        docs = st.session_state.pdf_data.similarity_search(query=query, k=3)
        with get_openai_callback() as cb:
            response = st.session_state.chatbot_instance.run(input_documents=docs, question=query)

        st.session_state['chat_history'].append(("Bot", response, "new"))

        # Display new messages at the bottom
        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)

        # Scroll to the latest response using JavaScript
        st.write("<script>document.getElementById('response').scrollIntoView();</script>", unsafe_allow_html=True)

        loading_message.empty()

        # Clear the input field by setting the query variable to an empty string
        query = ""

    # Mark all messages as old after displaying
    st.session_state['chat_history'] = [(sender, msg, "old") for sender, msg, _ in st.session_state['chat_history']]




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)

if __name__ == "__main__":
    main()