src/streamlit_app.py

import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import HuggingFaceInstructEmbeddings
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.llms import HuggingFaceHub
from htmlTemplates import css, bot_template, user_template
import os

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


def get_text_chunks(text):
    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):
    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    return FAISS.from_texts(texts=text_chunks, embedding=embeddings)


def get_conversation_chain(vectorstore):
    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
    )

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


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 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 = None

    st.header("Chat with your PDFs 📚")
    user_question = st.text_input("Ask something about your PDFs:")
    if user_question:
        handle_userinput(user_question)

    with st.sidebar:
        st.subheader("Your documents")
        pdf_docs = st.file_uploader("Upload PDFs", 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()