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 OllamaEmbeddings
from langchain.vectorstores import FAISS
from langchain.callbacks.manager import CallbackManager
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.chat_models import ChatOllama
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from htmlTemplates import css, bot_template, user_template
from functools import wraps
import time


# Decorator for measuring execution time
def timeit(func):
    @wraps(func)
    def timeit_wrapper(*args, **kwargs):
        start_time = time.perf_counter()
        result = func(*args, **kwargs)
        end_time = time.perf_counter()
        total_time = end_time - start_time
        print(f"\nFunction {func.__name__} Took {total_time:.4f} seconds")
        return result

    return timeit_wrapper


# Function to get text from PDF documents
@timeit
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


# Function to split text into chunks
@timeit
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


# Function to create a vector store
@timeit
def get_vectorstore(text_chunks):
    embeddings = OllamaEmbeddings(
        # num_gpu=2
    )
    # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
    return vectorstore


# Function to create a conversation chain
@timeit
def get_conversation_chain(vectorstore):
    llm = ChatOllama(
        model="llama2:70b-chat",
        callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]),
        # num_gpu=2
    )
    # 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


# Function to handle user input and generate responses
@timeit
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
            )


# Main function
def main():
    load_dotenv()
    st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:")
    st.write(css, unsafe_allow_html=True)

    # 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 = None

    # Streamlit app layout
    st.header("Chat with multiple PDFs :books:")
    user_question = st.text_input("Ask a question about your documents:")
    if user_question:
        handle_userinput(user_question)

    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 text from PDFs
                raw_text = get_pdf_text(pdf_docs)

                # Split text into 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)


if __name__ == "__main__":
    main()