app.py

import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
# Huggingface embeddings using Langchain
from langchain_openai import OpenAIEmbeddings
from langchain_community.embeddings import HuggingFaceInstructEmbeddings
from langchain_community.vectorstores import Chroma
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain_openai import ChatOpenAI
from htmlTemplates import css, bot_template, user_template

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()
    #vectorstore = FAISS.from_Texts(texts=text_chunks, embeddings=embeddings)
    # Setup the Chroma database and vectorize
    vectorstore = Chroma.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

def get_conversation_chain(vectorstore):
    llm = ChatOpenAI()
    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():
    st.set_page_config(page_title="Chat with your design book 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 your design book PDFs :books:")
    user_question = st.chat_input("Enter your question:")
    if user_question:
        handle_userinput(user_question)

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

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader("Upload your pdfs here to 'Process'", accept_multiple_files=True)
        if st.button("Process"):
            with st.spinner("Processing"):
                # get pdf text
                raw_text = get_pdf_text(pdf_docs)
                #st.write(raw_text)

                # get the text chunks
                text_chunks = get_text_chunks(raw_text)


                # create vector store
                vectorstore = get_vectorstore(text_chunks)
                #st.write(vectorstore)

                # Create Conversation chain
                st.session_state.conversation = get_conversation_chain(vectorstore)


if __name__== '__main__':
    main()