How mmahimashree/resume-screener works
The product is a Flask resume-screening and career-advice web app. A user uploads a PDF through the web interface; the server extracts and cleans its text, predicts a broad role, maps it to a more specific role, and returns an explanation. The app also offers follow-up career questions using the resume and predicted role stored in the session. The README documents the TF-IDF/model workflow; unsampled implementation details are represented only where that documentation supports them.
Main entry points: app.py Flask routes · index.html Resume and results UI · model.pkl Role classifier · tfidf.pkl TF-IDF vectorizer
Components 13
Web interface
- Resume and results UI
templates/index.html - Flask routes
app.py
Resume screening
- PDF text extraction
app.py - Text cleanup
app.py - TF-IDF features
app.py - Role classifier
model.pkl - Specific role mapping
app.py
AI career advice
- Prediction explanation
app.py - Career Q&A
app.py - Groq LLM
Model assets
- TF-IDF vectorizer
tfidf.pkl - Role encoder
encoder.pkl
Other components
- Resume owner
Connections 16
- Resume owner → Resume and results UI: uploads resume
README.md - Resume and results UI → Flask routes: submits PDF
README.md - Flask routes → Resume and results UI: renders results
app.py - Flask routes → PDF text extraction: extracts text
app.py - Flask routes → Text cleanup: cleans text
README.md - Flask routes → TF-IDF features: builds features
README.md - TF-IDF features → TF-IDF vectorizer: uses
README.md - Flask routes → Role classifier: predicts role
README.md - Flask routes → Role encoder: decodes label
app.py - Flask routes → Specific role mapping: maps role
app.py - Flask routes → Prediction explanation: requests explanation
app.py - Prediction explanation → Groq LLM: prompts model
app.py - Resume owner → Resume and results UI: asks follow-up
README.md - Resume and results UI → Career Q&A: sends question
README.md - Career Q&A → Groq LLM: requests answer
app.py - Career Q&A → Flask routes: reads session
app.py