app.py

import streamlit as st
from dotenv import load_dotenv
import pickle
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

# 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 Anne')
    

openai_api_key = st.text_input("Enter your OpenAI API key:")
pdf_path = "" 


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(openai_api_key):
    openai_config = {
        "api_key": openai_api_key
    }
    return load_qa_chain(llm=OpenAI(config=openai_config), chain_type="stuff")


def main():
    st.title("BinDocs Chat App")


    uploaded_pdf = st.file_uploader("Upload a PDF file:", type=["pdf"])

    if uploaded_pdf is not None:
        pdf_path = uploaded_pdf


    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)
            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()