app.py

import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
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

load_dotenv()

def main():
    st.title("Chat with PDF 💬")
    pdf = st.file_uploader("Upload your PDF", type='pdf')
    if pdf is not None:
        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 = OpenAIEmbeddings()
        VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
        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)
                print(cb)
            st.write(response)

if __name__ == '__main__':
    main()