app.py

import streamlit as st
from PyPDF2 import PdfReader
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import cosine_similarity
from gliner import GLiNER
import plotly.express as px

with st.sidebar:
    st.button("DEMO APP", type="primary")
   

    expander = st.expander("**Important notes on the AI Resume Analysis based on Keywords App**")
    expander.write('''
    
    
     **Supported File Formats**
    This app accepts files in .pdf formats.
    
    **How to Use**
    Paste the job description first. Then, upload the resume of each applicant to retrieve the results. At the bottom of the app, you could upload each applicant's resume to visualize their profile as a treemap chart as well as the results in a matrix heatmap. 
    
    **Usage Limits**
    You can request results up to 20 times in total.
    
     **Subscription Management**
    This demo app offers a one-day subscription, expiring after 24 hours. If you are interested in building your own AI Resume Analysis based on Keywords Web App, we invite you to explore our NLP Web App Store on our website. You can select your desired features, place your order, and we will deliver your custom app within five business days. If you wish to delete your Account with us, please contact us at [email protected]
    
    **Customization**
    To change the app's background color to white or black, click the three-dot menu on the right-hand side of your app, go to Settings and then Choose app theme, colors and fonts.
    
    **File Handling and Errors**
    The app may display an error message if your file is corrupt, or has other errors.
    
    
    For any errors or inquiries, please contact us at [email protected]
   
    
    
''')



st.title("AI Resume Analysis based on Keywords App")
st.divider()

job = pd.Series(st.text_area("Paste the job description and then press Ctrl + Enter", key="job_desc"), name="Text")

if 'applicant_data' not in st.session_state:
    st.session_state['applicant_data'] = {}

max_attempts = 20

for i in range(1, 51):  # Looping for 2 applicants
    st.subheader(f"Applicant {i} Resume", divider="green")
    applicant_key = f"applicant_{i}"
    upload_key = f"candidate_{i}"

    if applicant_key not in st.session_state['applicant_data']:
        st.session_state['applicant_data'][applicant_key] = {'upload_count': 0, 'uploaded_file': None, 'analysis_done': False}

    if st.session_state['applicant_data'][applicant_key]['upload_count'] < max_attempts:
        uploaded_file = st.file_uploader(f"Upload Applicant's {i} resume", type="pdf", key=upload_key)

        if uploaded_file:
            st.session_state['applicant_data'][applicant_key]['uploaded_file'] = uploaded_file
            st.session_state['applicant_data'][applicant_key]['upload_count'] += 1
            st.session_state['applicant_data'][applicant_key]['analysis_done'] = False # Reset analysis flag

        if st.session_state['applicant_data'][applicant_key]['uploaded_file'] and not st.session_state['applicant_data'][applicant_key]['analysis_done']:
            pdf_reader = PdfReader(st.session_state['applicant_data'][applicant_key]['uploaded_file'])
            text_data = ""
            for page in pdf_reader.pages:
                text_data += page.extract_text()

            with st.expander(f"See Applicant's {i} resume"):
                st.write(text_data)

            data = pd.Series(text_data, name='Text')
            result = pd.concat([job, data])

            vectorizer = TfidfVectorizer()
            tfidf_matrix = vectorizer.fit_transform(result)
            cosine_sim_matrix = cosine_similarity(tfidf_matrix)

            
            for j, similarity_score in enumerate(cosine_sim_matrix[0][1:]):
                with st.popover(f"See Result for Applicant {i}"):
                    st.write(f"Similarity between Applicant's resume and job description based on keywords: {similarity_score:.2f}")
                    st.info(
                        f"A score closer to 1 (0.80, 0.90) means higher similarity between Applicant's {i} resume and job description. A score closer to 0 (0.20, 0.30) means lower similarity between Applicant's {i} resume and job description.")
            st.session_state['applicant_data'][applicant_key]['analysis_done'] = True

    else:
        st.warning(f"Applicant {i} has reached the maximum upload attempts ({max_attempts}).")
        if st.session_state['applicant_data'][applicant_key]['upload_count'] > 0:
            st.info(f"Files uploaded for Applicant {i}: {st.session_state['applicant_data'][applicant_key]['upload_count']} time(s).")


      


st.divider()

st.subheader("Visualise", divider="blue")
if 'upload_count' not in st.session_state:
    st.session_state['upload_count'] = 0

max_attempts = 3
if st.session_state['upload_count'] < max_attempts:
    uploaded_files = st.file_uploader("Upload Applicant's resume", type="pdf")
    if uploaded_files:
        st.session_state['upload_count'] += 1

        with st.spinner("Wait for it...", show_time=True):
            time.sleep(2)
            pdf_reader = PdfReader(uploaded_files)
            text_data = ""
            for page in pdf_reader.pages:
                text_data += page.extract_text()
            
                data = pd.Series(text_data, name='Text')
                frames = [job, data]
                result = pd.concat(frames)
                model = GLiNER.from_pretrained("urchade/gliner_base")
                labels = ["person", "country", "organization", "role", "skills"]
                entities = model.predict_entities(text_data, labels)
                df = pd.DataFrame(entities)
                fig = px.treemap(entities, path=[px.Constant("all"), 'text', 'label'],
                             values='score', color='label')
                fig.update_layout(margin=dict(t=50, l=25, r=25, b=25))
                st.plotly_chart(fig)
 
             

                
else:
    st.warning(f"You have reached the maximum upload attempts ({max_attempts}).")
    if 'upload_count' in st.session_state and st.session_state['upload_count'] > 0:
        st.info(f"Files uploaded {st.session_state['upload_count']} time(s).")