app.py

import streamlit as st
import requests
import os
import json
from dotenv import load_dotenv
import PyPDF2
import io
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain.llms import HuggingFaceHub

load_dotenv()

# Initialize session state variables
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 = []

def reset_conversation():
    st.session_state.conversation = None
    st.session_state.chat_history = []

def get_pdf_text(pdf_docs):
    text = ""
    for pdf in pdf_docs:
        pdf_reader = PyPDF2.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 = HuggingFaceEmbeddings()
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore

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)
    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)

# Streamlit application
st.set_page_config(page_title="Chat with your PDFs", page_icon=":books:")

st.header("Chat with your PDFs :books:")

user_template = '<div style="background-color: #e6f3ff; padding: 10px; border-radius: 5px; margin-bottom: 10px;"><strong>Human:</strong> {{MSG}}</div>'
bot_template = '<div style="background-color: #f0f0f0; padding: 10px; border-radius: 5px; margin-bottom: 10px;"><strong>AI:</strong> {{MSG}}</div>'

# Sidebar
with st.sidebar:
    st.subheader("Your documents")
    pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
    if st.button("Process"):
        with st.spinner("Processing"):
            # Get PDF text
            raw_text = get_pdf_text(pdf_docs)

            # Get the 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.button('Reset Chat', on_click=reset_conversation)

# Main chat interface
if st.session_state.conversation is None:
    st.write("Please upload PDF documents and click 'Process' to start chatting.")
else:
    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_userinput(user_question)