app.py

from dotenv import load_dotenv
import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain_community.embeddings import HuggingFaceInstructEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_community.chat_models import ChatOpenAI
from langchain_community.callbacks.manager import get_openai_callback
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from htmlTemplates import css, user_template, bot_template


def get_pdf_text(pdf_docs):
    """Extract text from multiple uploaded PDF files."""
    text = ""
    for pdf in pdf_docs:
        pdf_reader = PdfReader(pdf)
        for page in pdf_reader.pages:
            extracted_text = page.extract_text()
            if extracted_text:
                text += extracted_text + "\n"
    return text


def get_text_chunks(text):
    """Split the extracted text into smaller chunks for vector storage."""
    text_splitter = CharacterTextSplitter(
        separator="\n", chunk_size=1000, chunk_overlap=200, length_function=len
    )
    return text_splitter.split_text(text)


def get_vectorstore(text_chunks):
    """Convert text chunks into vector embeddings and store them in FAISS."""
    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore


def get_conversation_chain(vectorstore):
    """Set up the conversational AI chain using a language model and vector storage."""
    llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.8)

    memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)

    conversation_chain = ConversationalRetrievalChain.from_llm(
        llm=llm, retriever=vectorstore.as_retriever(), memory=memory
    )
    return conversation_chain


def handle_user_input(user_question):
    """Process user input and generate a response."""
    response = st.session_state.conversation({'question': user_question})
    st.session_state.chat_history = response['chat_history']

    for i, message in enumerate(st.session_state.chat_history):
        if i % 2 == 0:
            st.write(user_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)
        else:
            st.write(bot_template.replace("{{MSG}}", message.content), unsafe_allow_html=True)


def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with multiple PDFs", page_icon="📚")

    st.write(css, unsafe_allow_html=True)

    if "conversation" not in st.session_state:
        st.session_state.conversation = None

    if "chat_history" not in st.session_state:
        st.session_state.chat_history = []

    st.header("📚 Chat with Multiple PDFs")

    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_user_input(user_question)

    with st.sidebar:
        st.subheader("Upload Your PDFs")
        pdf_docs = st.file_uploader("Upload PDFs and click Process", accept_multiple_files=True)

        if st.button("Process"):
            with st.spinner("Processing..."):
                raw_text = get_pdf_text(pdf_docs)
                text_chunks = get_text_chunks(raw_text)
                vectorstore = get_vectorstore(text_chunks)
                st.session_state.conversation = get_conversation_chain(vectorstore)


if __name__ == '__main__':
    main()