app.py

import streamlit as st
from dotenv import load_dotenv
import pickle
from PyPDF2 import PdfReader
from streamlit_extras.add_vertical_space import add_vertical_space
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.llms import OpenAI
from langchain.chains.question_answering import load_qa_chain
from langchain.callbacks import get_openai_callback
import os

#Set the sidebar style with a new background color
st.set_page_config(layout="wide", page_title="LLM Chat App", page_icon=":robot:")
st.markdown(
    """
    <style>
        .sidebar .sidebar-content {
            background-color: #E6E6FA;
        }
    </style>
    """,
    unsafe_allow_html=True
)

#Sidebar contents
with st.sidebar:
    st.title('LLM Chat App')
    st.markdown('''
    ## About
    This app is an LLM-powered chatbot built using:
    - [Streamlit](https://streamlit.io/)
    - [LangChain](https://python.langchain.com/)
    - [OpenAI](https://platform.openai.com/docs/models) LLM model
    ''')
    st.markdown('Made with by Meenu Patel')

#Main content
def main():
    st.header("Chat with PDF")

    #Upload a PDF file
    pdf = st.file_uploader("Upload your PDF", type='pdf')

    if pdf is not None:
        try:
            pdf_reader = PdfReader(pdf)
            text = ""
            for page in pdf_reader.pages:
                text += page.extract_text()

            text_splitter = RecursiveCharacterTextSplitter(
                chunk_size=1000,
                chunk_overlap=200,
                length_function=len
            )
            chunks = text_splitter.split_text(text=text)

            #embeddings
            store_name = pdf.name[:-4]
            if os.path.exists(f"{store_name}.pkl"):
                with open(f"{store_name}.pkl", "rb") as f:
                    VectorStore = pickle.load(f)
            else:
                embeddings = OpenAIEmbeddings()
                VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
                with open(f"{store_name}.pkl", "wb") as f:
                    pickle.dump(VectorStore, f)

            #Accept user questions/query
            query = st.text_input("Ask questions about your PDF file:")
            if query:
                docs = VectorStore.similarity_search(query=query, k=3)
                llm = OpenAI()
                chain = load_qa_chain(llm=llm, chain_type="stuff")
                with get_openai_callback() as cb:
                    response = chain.run(input_documents=docs, question=query)
                st.write(response)

        except Exception as e:
            st.error(f"An error occurred: {str(e)}")

if __name__ == '__main__':
    main()