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

# 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/Glossar_HELP_DESK_combi.pdf"  # Replace with your PDF file path



# Sidebar contents
with st.sidebar:
    st.title(':orange[BinDoc GmbH]')
    st.markdown(
        "Experience the future of document interaction with the revolutionary"
    )

    st.markdown("**BinDocs Chat App**.")

        
    st.markdown("Harnessing the power of a Large Language Model and AI technology,")
       


    st.markdown("this innovative platform redefines PDF engagement,")

    st.markdown("enabling dynamic conversations that bridge the gap between")
    st.markdown("human and machine intelligence.")

    
    
    add_vertical_space(3)  # Add more vertical space between text blocks
    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



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

def main():
    st.title("BinDocs Chat App")
    st.markdown(
        """🤖 Welcome to BinDocs ChatBot! 🤖
        
Hello! I’m your friendly assistant, designed to help you navigate through our platform with ease. Here's a snapshot of what I can assist you with:

📘 **Glossary Inquiries:**
Having trouble understanding specific terms? Ask me! For instance, if you are unsure about what "Belegarzt" means, just type in “What is a Belegarzt?” and I will provide you with a detailed explanation based on our glossary.

🆘 **Help Page Navigation:**
I can guide you through our help page and answer your queries regarding any problems or inquiries you might have, such as “Forgot your Password?” or other platform-related concerns.

#### How to Interact:
Simply type in your question or concern, and I will do my best to assist you. Examples are shown at the bottom of this page. Try some out!"""
    )
    
    # 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):")

        if st.button("Was genau ist ein Belegarzt?"):
            query = "Was genau ist ein Belegarzt?"
        if st.button("Wofür wird die Alpha-ID verwendet?"):
            query = "Wofür wird die Alpha-ID verwendet?"
        if st.button("Was sind die Vorteile des ambulanten operierens?"):
            query = "Was sind die Vorteile des ambulanten operierens?"
        if st.button("Was kann ich mit dem Prognose-Analyse Toll machen?"):
            query = "Was kann ich mit dem Prognose-Analyse Toll machen?"
        if st.button("Was sagt mir die Farbe der Balken der Bevölkerungsentwicklung?"):
            query = "Was sagt mir die Farbe der Balken der Bevölkerungsentwicklung?"

            
        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)
            with get_openai_callback() as cb:
                response = chain.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()