An Enterprise-grade Applicant Tracking System (ATS) built using RAG (Retrieval-Augmented Generation). This system goes beyond traditional keyword-matching by using semantic search and Large Language Models (LLMs) to read, analyze, and score candidate resumes against Job Descriptions.
- 🧠 Semantic RAG Search: Don't just search for keywords; ask complex questions like "Find me a backend dev with 3 years of experience" and get precise answers.
- 🎯 JD Matcher & Scoring: Paste a Job Description and get an automated JSON-based Match Percentage, along with 'Why they fit' and 'Missing Skills'.
- 📤 Drag & Drop Upload: HR can easily upload new PDF resumes directly from the UI to update the Vector Database instantly.
- 📇 Candidate Profile Cards: Beautiful UI that displays shortlisted candidates with instant 'Download Resume' buttons.
- 🛡️ Zero Hallucination: Strictly constrained AI that only answers based on the uploaded database.
- Frontend: Streamlit
- Data Extraction: PyMuPDF (
fitz) - Vector Database: ChromaDB (Local Semantic Search)
- LLM Engine: Groq API (Llama-3.3-70b-versatile)
1. Clone the repository:
git clone [https://github.com/YourUsername/AI-Smart-ATS.git](https://github.com/YourUsername/AI-Smart-ATS.git)
cd AI-Smart-ATS