app.py

import streamlit as st
from PyPDF2 import PdfReader
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer

uploaded_files = st.file_uploader(
    "Choose a CSV file", accept_multiple_files=True
)
for uploaded_file in uploaded_files:
    pdf_reader = PdfReader(uploaded_file) # read your PDF file
    # extract the text data from your PDF file after looping through its pages with the .extract_text() method
    text_data= ""
    for page in pdf_reader.pages: # for loop method
        text_data+= page.extract_text()

    
    data = pd.Series(text_data, index = ["Resume"])
    
    st.dataframe(data) # view the text data

    from sklearn.feature_extraction.text import TfidfVectorizer
    from sklearn.metrics.pairwise import cosine_similarity
    vec = TfidfVectorizer()
    tf_idf = vec.fit_transform(data[["Resume"]])
    st.dataframe(pd.DataFrame(tf_idf.toarray(), columns=vec.get_feature_names_out()))
    cosine_sim = cosine_similarity(tf_idf, tf_idf)
    st.write(cosine_sim)