app.py

import os
import pickle
import streamlit as st
from streamlit_extras.add_vertical_space import add_vertical_space
from PyPDF2 import PdfReader
from openai.embeddings_utils import get_embedding
import openai
#from dotenv import load_dotenv
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
# Sidebar contents
with st.sidebar:
    st.title('🤗LLM Chat App💬')
    st.markdown('''
    ## About
    OpenAI based LLM-powered chatbot built using:
    - [OpenAI](https://platform.openai.com/docs/models) LLM model                
    - [Streamlit](https://streamlit.io/)
    - [LangChain](https://python.langchain.com/)
    ''')
    add_vertical_space(5)
    st.write('Made with ❤️ by Harry')


# Load environment variables
#load_dotenv()

# # Retrieve OpenAI API key
#openai_api_key = os.getenv("OPENAI_API_KEY")
#if openai_api_key is None:
#     raise ValueError("The OPENAI_API_KEY environment variable is not set")

# # Set the OpenAI API key for the OpenAI library
#openai.api_key = openai_api_key

def extract_text_from_pdf(pdf):
    pdf_reader = PdfReader(pdf)
    text = ""
    for page in pdf_reader.pages:
        text += page.extract_text()
    return text
def get_embeddings(text_list):
    return [get_embedding(text) for text in text_list]
def main():
    st.header("Chat with PDF 💬")
    # Upload a PDF file
    pdf = st.file_uploader("Upload your PDF file", type='pdf')

    if pdf is not None:
        # Extract text from the PDF
                
        text = extract_text_from_pdf(pdf)
        # Split text into chunks 
        text_splitter = RecursiveCharacterTextSplitter(
            chunk_size=1000,
            chunk_overlap=200,
            length_function=len
            )
        chunks = text_splitter.split_text(text=text)
        # chunks data with langchain
        #chunks = [text[i:i+chunk_size] for i in range(0, len(text), chunk_size - chunk_overlap)]
        st.write("PDF content successfully extracted.")
        #st.write("Below is chunks data")
        #st.write(chunks)
        
        # Create or load embeddings
        store_name = pdf.name[:-4]
        st.write(f'Processing: {store_name}')
        
        if os.path.exists(f"{store_name}.pkl"):
            with open(f"{store_name}.pkl", "rb") as f:
                VectorStore = pickle.load(f)
            st.write('Embeddings loaded from the disk')
        else:
            embeddings = OpenAIEmbeddings()
            VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
            with open(f"{store_name}.pkl", "wb") as f:
                pickle.dump(VectorStore, f)
            st.write('Embeddings created and saved to disk')

        # 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(model_name="gpt-3.5-turbo") 
            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()