proj/README.md

Full-Stack AI Recruitment Engine

A production-ready candidate ranking platform built with Next.js, FastAPI, and Groq LLMs.

Features

• Multi-Agent Evaluation: Sequential and parallel agent pipeline (Signal Extraction, Founder Eval, Tech Eval, HR Agent, etc.).
• Groq Key Rotation: Automatic round-robin cycling of multiple API keys to prevent rate limits.
• CSV Data Ingestion: Parse resumes and candidate data directly from CSV files.
• Glassmorphic UI: Modern, high-performance dashboard with animations and progress tracking.

---

Backend Setup (FastAPI)

1. Navigate to backend:

   cd backend
   

2. Create and Activate Virtual Environment:

   python -m venv venv
   # Windows:
   venv\Scripts\activate
   

3. Install Dependencies:

   pip install -r requirements.txt
   

4. Environment Variables: Create a .env file in the backend/ folder based on .env.example:

   GROQ_API_KEYS=key1,key2,key3
   GROQ_MODEL=llama3-70b-8192
   PORT=8000
   

5. Run Backend:

   uvicorn app.main:app --reload
   

---

Frontend Setup (Next.js)

1. Navigate to frontend:

   cd frontend
   

2. Install Dependencies:

   npm install
   

3. Environment Variables: Create a .env.local file in the frontend/ folder:

   NEXT_PUBLIC_API_URL=http://localhost:8000
   

4. Run Frontend:

   npm run dev
   

---

Usage Guide

1. Paste Job Description: Enter the target role details in the textarea.
2. Upload CSV: Upload a CSV containing candidate data (columns: name, email, skills, experience, projects, education, resume_text).
3. Evaluate: Click "Run Evaluation" and watch the AI agents process each candidate.
4. Deep Dive: Click on any candidate row to see the full multi-agent breakdown and final synthesis.