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 OpenAIEmbeddings
from langchain.vectorstores import FAISS

def get_html(html):
    text = ""
    for pdf in html:
        pdf_reader= PdfReader(pdf)
        for page in pdf_reader.pages:
            text += page.extract_text()
    return text

def get_chunk_text(raw_text):
    text_splitter = CharacterTextSplitter(seperator="\n", chunk_size=1000, chunk_overlap=20,length_function=len)
    chunks = text_splitter.split_text(text)
    return chunks

def get_vector_store(text_chunks):
    embeddings = OpenAIEmbeddings
    vector_store = FAISS.from_texts(texts=text_chunks,embedding = embeddings)
    return vector_store
    
            
    
def main():
    load_dotenv()
    st.set_page_config(page_title="Reads your html",page_icon=":books:")
    st.header("Get your best Element")
    st.text_input("Pass your Element with its information")

    with st.sidebar:
        st.subheader("your html")
        html_docs = st.file_uploader("upload your html file and click process")
        if st.button("process"):
            with st.spinner("processing"):
                
                #get pdf text
                raw_text = get_html(html_docs)
                
            
                #get the text chunks
                text_chunks = get_chunk_text(raw_text)
                

                #create vector store
                vectors = get_vector_store(text_chunks)

if __name__ == '__main__':
    main()