from sentence_transformers import SentenceTransformer import streamlit as st import pandas as pd from PyPDF2 import PdfReader from sklearn.metrics.pairwise import cosine_similarity from gliner import GLiNER import plotly.express as px import time import numpy as np with st.sidebar: st.button("DEMO APP", type="primary") expander = st.expander("**Important notes on the AI Resume Analysis based on Sentence Similarity 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. **Usage Limits** For each applicant you can upload their resume and request results once (1 request per applicant's resume). At the bottom of the app, you can also upload an applicant's resume once (1 request) to visualize their profile as a treemap chart. If you hover over the interactive graph, an icon will appear to download it. **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 Sentence Similarity 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 info@nlpblogs.com **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 info@nlpblogs.com ''') model = SentenceTransformer("all-MiniLM-L6-v2") st.title("AI Resume Analysis based on Sentence Similarity App") st.divider() job_desc = st.text_area("Paste the job description and then press Ctrl + Enter", key="job_desc") if 'applicant_data' not in st.session_state: st.session_state['applicant_data'] = {} max_attempts = 1 for i in range(1, 51): # Looping for 50 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']: try: 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) # Encode the job description and resume text separately job_embedding = model.encode([job_desc]) resume_embedding = model.encode([text_data]) with st.spinner("Wait for it...", show_time=True): similarity_score = model.similarity(job_embedding, resume_embedding)[0][0] time.sleep(2) 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 except Exception as e: st.error(f"An error occurred while processing Applicant {i}'s resume: {e}") else: st.warning(f"Maximum upload attempts has been reached ({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") model = SentenceTransformer("all-MiniLM-L6-v2") if 'upload_count' not in st.session_state: st.session_state['upload_count'] = 0 max_attempts = 1 if st.session_state['upload_count'] < max_attempts: uploaded_files = st.file_uploader("Upload Applicant's resume", type="pdf", key="applicant 1") 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() job_desc_series = pd.Series([job_desc], name='Text') # Convert job_desc to a Series data = pd.Series([text_data], name='Text') # Ensure text_data is also a Series frames = [job_desc_series, data] result = pd.concat(frames, ignore_index=True) # Concatenate along rows, reset index model1 = GLiNER.from_pretrained("urchade/gliner_base") labels = ["person", "country", "organization", "role", "skills"] entities = model1.predict_entities(text_data, labels) df = pd.DataFrame(entities) st.subheader("Applicant's Profile", divider = "orange") 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, key="figure 1") job_embedding = model.encode([job_desc]) resume_embedding = model.encode([text_data]) similarity_score = model.similarity(job_embedding, resume_embedding)[0][0] st.metric(label="Similarity Score between Applicant's Profile and Job Description", value=f"{similarity_score:.2f}", border=True) else: st.warning(f"Maximum upload attempts has been reached ({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).")