app.py

import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.chat_models import ChatOpenAI
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from HTMLTemplates import css, bot_template, user_template
from langchain.llms import HuggingFaceHub

def get_pdf_text(pdf_docs):
    text=""
    for pdf in pdf_docs:
        pdf_reader=PdfReader(pdf)
        for page in pdf_reader.pages:
            text += page.extract_text()
    return text

def get_text_chunks(text):
    text_splitter=CharacterTextSplitter(
        separator="\n",
        chunk_size=1000,
        chunk_overlap=200,
        length_function=len
    )
    chunks=text_splitter.split_text(text)
    return chunks

def get_vectorstore(text_chunks):
    # embeddings=OpenAIEmbeddings()
    embeddings=HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    vectorstore=FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

def get_conversation_chain(vectorstore):
    # llm=ChatOpenAI()
    llm=HuggingFaceHub(repo_id="google/flan-t5-large", model_kwargs={"temperature":0.5, "max_length":512})
    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_userinput(user_question):
    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=":books:"
    ) 
    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=None    
    
    st.title("Chat with Multiple PDFs :books:")

    # if st.sidebar.button("Clear Conversation"):
    #     st.session_state.chat_history = []
    #     st.session_state.conversation = None
    #     clear_message = st.sidebar.empty()
    #     clear_message.success("Conversation cleared!")
    #     time.sleep(2)  # Display message for 2 seconds
    #     clear_message.empty()  # Remove message after 2 seconds

    user_question=st.text_input("Ask a Question about your PDFs")
    if user_question:
        handle_userinput(user_question)

    # st.write(user_template.replace("{{MSG}}", "Hello, Bot"), unsafe_allow_html=True)
    # st.write(bot_template.replace("{{MSG}}", "Hello, Human"), unsafe_allow_html=True)

    with st.sidebar:
        st.subheader("Documents")
        pdf_docs=st.file_uploader("Upload your PDFS 📂", accept_multiple_files=True)
        if st.button("Process"):
            with st.spinner("Processing"):
                # get pdf text (raw contents)
                raw_text=get_pdf_text(pdf_docs)

                # get text chunks
                text_chunks=get_text_chunks(raw_text)
 
                # create vector store
                vectorstore=get_vectorstore(text_chunks)

                # create conversation chain
                st.session_state.conversation=get_conversation_chain(vectorstore)

    # st.session_state.conversation

if __name__=='__main__':
    main()