Skip to content

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Resume ATS Score Booster

A FastAPI-based application that accepts a resume PDF, extracts its text, and returns an ATS-focused analysis with feedback and rewritten bullet points.

Features

  • Upload a PDF resume through a FastAPI endpoint
  • Extract text from the PDF using PyMuPDF
  • Analyze the content with Gemini (when configured)
  • Store analysis results in a local SQLite database
  • Return structured ATS feedback and rewritten bullet suggestions

Project Structure

config/                 # Settings and environment configuration
src/
  api/                  # API routes
  services/             # PDF parsing and LLM analysis
  schemas/              # Pydantic response models
  models.py             # SQLAlchemy models
  database.py           # Database setup
  main.py               # FastAPI app entry point
requirements.txt
.env

Setup

  1. Create and activate a virtual environment
cd /Users/pratimabhat/Documents/Projects/resume-ats-score-booster
python3 -m venv venv
source venv/bin/activate
  1. Install dependencies
pip install -r requirements.txt
  1. Configure environment variables

Edit the .env file and set your Gemini API key:

GEMINI_API_KEY=your_gemini_api_key_here
  1. Run the app
uvicorn src.main:app --reload

The API will be available at:

API Example

Upload a PDF using curl:

curl -X POST "http://127.0.0.1:8000/pipeline/upload" \
  -F "file=@path/to/resume.pdf"

Notes

  • The app uses SQLite and creates the database file automatically on startup.
  • If the Gemini API key is not configured, the app uses a safe fallback analysis instead of failing.

About

An open-source ATS Resume Matcher and Fine-Tuning pipeline. Uses LLMs (GPT-4o/Claude) to parse CVs, calculate ATS compatibility scores, isolate recent jobs, and automatically rewrite bullet points to boost match rates.

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages