app.py

import streamlit as st
from PIL import Image
import time
import streamlit_analytics
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

import pandas as pd
import pydeck as pdk
from urllib.error import URLError

# Initialize session state variables
if 'chat_history_page1' not in st.session_state:
    st.session_state['chat_history_page1'] = []

if 'chat_history_page2' not in st.session_state:
    st.session_state['chat_history_page2'] = []



# 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_path = "Private_Book/141123_Kombi_compressed.pdf"  # Replace with your PDF file path

# Step 2: Load the PDF File
pdf_path2 = "Private_Book/Deutsche_Kodierrichtlinien_23.pdf"  # Replace with your PDF file path


api_key = os.getenv("OPENAI_API_KEY")
# Retrieve the API key from st.secrets



# Updated caching mechanism using st.cache_data
@st.cache_data(persist="disk")  # Using persist="disk" to save cache across sessions
def load_vector_store(file_path, store_name, force_reload=False):

        # Check if we need to force reload the vector store (e.g., when the PDF changes)
        if force_reload or not os.path.exists(f"{store_name}.pkl"):
            text_splitter = RecursiveCharacterTextSplitter(
                chunk_size=1000,
                chunk_overlap=200,
                length_function=len
            )
            
            text = load_pdf_text(file_path)
            chunks = text_splitter.split_text(text=text)
            
            embeddings = OpenAIEmbeddings()
            VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
            with open(f"{store_name}.pkl", "wb") as f:
                pickle.dump(VectorStore, f)
        else:
            with open(f"{store_name}.pkl", "rb") as f:
                VectorStore = pickle.load(f)
    
        return VectorStore

# Utility function to load text from a PDF
def load_pdf_text(file_path):
    pdf_reader = PdfReader(file_path)
    text = ""
    for page in pdf_reader.pages:
        text += page.extract_text() or ""  # Add fallback for pages where text extraction fails
    return text

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 = "#ffeecf" if chat[2] == "new" else "#ffeecf" if chat[0] == "User" else "#ffeecf"
        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 page1():
    try:
        hide_streamlit_style = """
                <style>
                #MainMenu {visibility: hidden;}
                footer {visibility: hidden;}
                </style>
                """
        st.markdown(hide_streamlit_style, unsafe_allow_html=True)
    
         # Create columns for layout
        col1, col2 = st.columns([3, 1])  # Adjust the ratio to your liking

        with col1:
            st.title("Welcome to BinDocs ChatBot!")

        with col2:
            # Load and display the image in the right column, which will be the top-right corner of the page
            image = Image.open('BinDoc Logo (Quadratisch).png')
            st.image(image, use_column_width='always')

 
        # Start tracking user interactions
        with streamlit_analytics.track():
            if not os.path.exists(pdf_path):
                st.error("File not found. Please check the file path.")
                return
    
            VectorStore = load_vector_store(pdf_path, "vector_store_page1", force_reload=False)

            display_chat_history(st.session_state['chat_history_page1'])
    
            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()
    
            query = st.text_input("Ask questions about your PDF file (in any preferred language):")

            add_vertical_space(2)  # Adjust as per the desired spacing
            
            # Create two columns for the buttons
            col1, col2 = st.columns(2)
            
            with col1:
                if st.button("Was kann ich mit dem Prognose-Analyse-Tool machen?"):
                    query = "Was kann ich mit dem Prognose-Analyse-Tool 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("Ich habe mein Meta-Password vergessen, wie kann ich es zurücksetzen?"):
                    query = "Ich habe mein Meta-Password vergessen, wie kann ich es zurücksetzen?"

            
            with col2:
                if st.button("Dies ist eine reine Test Frage, welche aber eine ausreichende Länge hat."):
                    query = "Dies ist eine reine Test Frage, welche aber eine ausreichende Länge hat."
                if st.button("Was sagt mir denn generell die wundervolle Bevölkerungsentwicklung?"):
                    query = "Was sagt mir denn generell die wundervolle Bevölkerungsentwicklung?"
                if st.button("Ob ich hier wohl viel schreibe, dass die Fragen vom Layout her passen?"):
                    query = "Ob ich hier wohl viel schreibe, dass die Fragen vom Layout her passen?"

        
            if query:
                st.session_state['chat_history_page1'].append(("User", query, "new"))

                # Start timing
                start_time = time.time()
                
                with st.spinner('Bot is thinking...'):
                    # Use the VectorStore loaded at the start from the session state
                    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)

                        
                # Stop timing
                end_time = time.time()
                
                # Calculate duration
                duration = end_time - start_time

                # You can use Streamlit's text function to display the timing
                st.text(f"Response time: {duration:.2f} seconds")
    
                st.session_state['chat_history_page1'].append(("Bot", response, "new"))
    
    
                # Display new messages at the bottom
                new_messages = st.session_state['chat_history_page1'][-2:]
                for chat in new_messages:
                    background_color = "#ffeecf" if chat[2] == "new" else "#ffeecf" if chat[0] == "User" else "#ffeecf"
                    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)
    
    
                # Clear the input field after the query is made
                query = ""
    
            # Mark all messages as old after displaying
            st.session_state['chat_history_page1'] = [(sender, msg, "old") for sender, msg, _ in st.session_state['chat_history_page1']]

    except Exception as e:
        st.error(f"Upsi, an unexpected error occurred: {e}")
        # Optionally log the exception details to a file or error tracking service




def page2():
    try:
        hide_streamlit_style = """
                <style>
                #MainMenu {visibility: hidden;}
                footer {visibility: hidden;}
                </style>
                """
        st.markdown(hide_streamlit_style, unsafe_allow_html=True)
    
         # Create columns for layout
        col1, col2 = st.columns([3, 1])  # Adjust the ratio to your liking

        with col1:
            st.title("Kodieren statt Frustrieren!")

        with col2:
            # Load and display the image in the right column, which will be the top-right corner of the page
            image = Image.open('BinDoc Logo (Quadratisch).png')
            st.image(image, use_column_width='always')

 
        # Start tracking user interactions
        with streamlit_analytics.track():
            
            if not os.path.exists(pdf_path2):
                st.error("File not found. Please check the file path.")
                return
    
            VectorStore = load_vector_store(pdf_path2, "vector_store_page2", force_reload=False)
    

    
            display_chat_history(st.session_state['chat_history_page2'])
    
            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()
    
            query = st.text_input("Ask questions about your PDF file (in any preferred language):")

            add_vertical_space(2)  # Adjust as per the desired spacing
            
            # Create two columns for the buttons
            col1, col2 = st.columns(2)
            
            with col1:
                if st.button("Wann kodiere ich etwas als Hauptdiagnose und wann als Nebendiagnose?"):
                    query = "Wann kodiere ich etwas als Hauptdiagnose und wann als Nebendiagnose?"
                if st.button("Ein Patient wird mit Aszites bei bekannter Leberzirrhose stationär aufgenommen. Es wird nur der Aszites durch eine Punktion behandelt.Wie kodiere ich das?"):
                    query = ("Ein Patient wird mit Aszites bei bekannter Leberzirrhose stationär aufgenommen. Es wird nur der Aszites durch eine Punktion behandelt.Wie kodiere ich das?")
                if st.button("Hauptdiagnose: Hirntumor wie kodiere ich das?"):
                    query = "Hauptdiagnose: Hirntumor wie kodiere ich das?"

            
            with col2:
                if st.button("Welche Prozeduren werden normalerweise nicht verschlüsselt?"):
                    query = "Welche Prozeduren werden normalerweise nicht verschlüsselt?"
                if st.button("Was muss ich bei der Kodierung der Folgezusänden von Krankheiten beachten?"):
                    query = "Was muss ich bei der Kodierung der Folgezusänden von Krankheiten beachten?"
                if st.button("Was mache ich bei einer Verdachtsdiagnose, wenn mein Patien nach Hause entlassen wird?"):
                    query = "Was mache ich bei einer Verdachtsdiagnose, wenn mein Patien nach Hause entlassen wird?"

        
            if query:
                st.session_state['chat_history_page2'].append(("User", query, "new"))

                # Start timing
                start_time = time.time()
                
                with st.spinner('Bot is thinking...'):
                    # Use the VectorStore loaded at the start from the session state
                    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)

                        
                # Stop timing
                end_time = time.time()
                
                # Calculate duration
                duration = end_time - start_time

                # You can use Streamlit's text function to display the timing
                st.text(f"Response time: {duration:.2f} seconds")
    
                st.session_state['chat_history_page2'].append(("Bot", response, "new"))
    
    
                # Display new messages at the bottom
                new_messages = st.session_state['chat_history_page2'][-2:]
                for chat in new_messages:
                    background_color = "#ffeecf" if chat[2] == "new" else "#ffeecf" if chat[0] == "User" else "#ffeecf"
                    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)
    
    
                # Clear the input field after the query is made
                query = ""
    
            # Mark all messages as old after displaying
            st.session_state['chat_history_page2'] = [(sender, msg, "old") for sender, msg, _ in st.session_state['chat_history_page2']]

    except Exception as e:
        st.error(f"Upsi, an unexpected error occurred: {e}")
        # Optionally log the exception details to a file or error tracking service





def main():
    # Sidebar content
    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)
        page = st.sidebar.selectbox("Choose a page", ["Document Analysis Bot", "Coding Assistance Bot"])
        add_vertical_space(1)
        st.write('Made with ❤️ by BinDoc GmbH')

    # Main area content based on page selection
    if page == "Document Analysis Bot":
        page1()
    elif page == "Coding Assistance Bot":
        page2()


if __name__ == "__main__":
    main()