app.py

import streamlit as st
import os
import pickle
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):
    button_id = f"cloud-button-{key or label}"
    cloud_button_html = f"""
    <div class="cloud" id="{button_id}">
        <div class="circle small"></div>
        <div class="circle medium"></div>
        <div class="circle large"></div>
        <div class="rectangle">{label}</div>
        <div class="circle medium"></div>
        <div class="circle small"></div>
    </div>
    <style>
        .cloud {{
            position: relative;
            display: inline-block;
            cursor: pointer;
            user-select: none;
        }}
        .rectangle {{
            width: 120px;
            height: 60px;
            background-color: white;
            border-radius: 30px;
            position: absolute;
            top: 20px;
            left: 10px;
            display: flex;
            align-items: center;
            justify-content: center;
            font-size: 16px;
            font-weight: bold;
            transition: background-color 0.4s;
        }}
        .circle {{
            position: absolute;
            background-color: white;
        }}
        .circle.small {{
            width: 40px;
            height: 40px;
            border-radius: 20px;
            top: 10px;
            left: 50px;
        }}
        .circle.medium {{
            width: 60px;
            height: 60px;
            border-radius: 30px;
        }}
        .circle.large {{
            width: 80px;
            height: 80px;
            border-radius: 40px;
            top: -10px;
            left: 40px;
        }}
        .cloud:hover .rectangle {{
            background-color: #008CBA;
            color: white;
        }}
    </style>
    <script>
        document.getElementById("{button_id}").onclick = function() {{
            google.script.run.withSuccessHandler(function(e) {{
                document.getElementById("{button_id}").innerText = e;
            }}).getCloudButtonValue("{label}");
        }};
    </script>
    """
    st.markdown(cloud_button_html, unsafe_allow_html=True)

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 = 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):")

        if cloud_button("Was genau ist ein Belegarzt?"):
            query = "Was genau ist ein Belegarzt?"
        if cloud_button("Wofür wird die Alpha-ID verwendet?"):
            query = "Wofür wird die Alpha-ID verwendet?"
        if cloud_button("Was sind die Vorteile des ambulanten operierens?"):
            query = "Was sind die Vorteile des ambulanten operierens?"
        if cloud_button("Was kann ich mit dem Prognose-Analyse Toll machen?"):
            query = "Was kann ich mit dem Prognose-Analyse Toll machen?"
        if cloud_button("Was sagt mir die Farbe der Balken der Bevölkerungsentwicklung?"):
            query = "Was sagt mir die Farbe der Balken der Bevölkerungsentwicklung?"
        if cloud_button("Ich habe mein Meta Password vergessen, wie kann ich es zurücksetzen?"):
            query = "Ich habe mein Meta Password vergessen, wie kann ich es zurücksetzen?"

        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()