app.py

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

#To use instructor embedding (free but slower) instead of OpenAI, 'pip install InstructorEmbedding sentence_transformers'
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=HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    embeddings=OpenAIEmbeddings(openai_api_key=os.getenv('OPENAI_API_KEY')) 
    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-xxl", 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_user_input(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('.env')
    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.header("Chat with Multiple PDFs :books:")
    user_question=st.text_input("Ask a question about your documents:")
    if user_question:
        handle_user_input(user_question)

    
    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs=st.file_uploader("Upload your PDFs here and select 'Process'!", accept_multiple_files=True)
        if st.button("Process"):
            with st.spinner("Loading"):
                #get pdf text, then text chunks, create vectorstore
                raw_text=get_pdf_text(pdf_docs)
                text_chunks=get_text_chunks(raw_text)
                vectorstore=get_vectorstore(text_chunks)         
                #create conversation chain
                st.session_state.conversation=get_conversation_chain(vectorstore) #doesnt reinitialize (reload everytime we click)


if __name__ =='__main__':
    main()