🌌 QUANTIS INTERVIEW GRID

Immersive AI Interview Simulation Platform

Quantis Interview Grid transforms a job description into a role-specific interview simulation with dynamic questions, voice interaction, structured scoring, rich performance analytics, and personalized preparation resources.

---

📋 Table of Contents

• Overview
• Application Preview
• Features
• Architecture
• Tech Stack
• Project Structure
• Installation
• Usage
• API Reference
• Configuration
• Testing
• Security Notes

---

🧠 Overview

Quantis is designed to feel like a real interview environment, not a static demo.

Core goals:

• Generate context-aware questions based on JD + interview type
• Support both typed and voice-assisted answer workflows
• Evaluate interview quality across weighted dimensions
• Produce actionable reports with metrics and preparation resources
• Persist user history for repeat practice and progress tracking

---

💻 Application Preview

---

✨ Features

Feature	Description
🎯 Dynamic Role-Based Questions	Uses JD analysis + interview type to generate realistic prompts
🌌 Immersive 3D UI	Live Three.js scene, glass panels, animated score visuals
🎙️ Voice Interview Mode	STT input, TTS question playback, live transcript capture
📊 Structured Scoring	Relevance, clarity, depth, structure, confidence
📄 Final Report Intelligence	Metrics, hiring likelihood, next steps, prep resources
🔐 Auth & History	Register/login, stored runs, run detail retrieval
📎 Resume Gap Analysis	Resume vs JD fit score, missing skills, action plan
📈 Observability	Prometheus metrics endpoint + summary API
🔄 Resilient LLM Calls	Retry/backoff + circuit breaker behavior for Groq calls
🗄️ Session Persistence	DB-backed sessions with optional Redis cache fast-path

---

🏗️ Architecture

┌─────────────────────────────────────────────────────────────┐
│                 React 3D Interview UI                       │
│  setup • interview • report • auth/history • voice mode     │
└───────────────┬─────────────────────────────────────────────┘
                │ HTTP + Browser Voice APIs
┌───────────────▼─────────────────────────────────────────────┐
│                      FastAPI Backend                        │
│                                                             │
│  /auth/*, /history*   identity + run history                │
│  /setup               JD analysis + question generation     │
│  /evaluate            answer capture (per-question)         │
│  /report              full scoring + final insights         │
│  /resume-gap-analysis resume/JD fit + action plan           │
│  /metrics             Prometheus scrape endpoint            │
│  /observability/*     request latency and error summaries   │
└───────────────┬─────────────────────────────────────────────┘
                │
      ┌─────────▼─────────┐          ┌────────────────────────┐
      │ SQLAlchemy (DB)   │          │ Groq API (LLM provider)│
      │ sessions/users/runs│         │ structured AI responses│
      └─────────┬─────────┘          └────────────────────────┘
                │
      ┌─────────▼─────────┐
      │ Redis Cache       │
      │ optional hot reads│
      └───────────────────┘

---

🛠️ Tech Stack

Layer	Technology
Frontend	React 18, Framer Motion, Recharts
3D / Visuals	Three.js, @react-three/fiber, @react-three/drei
Backend	FastAPI, Pydantic, Uvicorn
AI	Groq (OpenAI-compatible API)
Persistence	SQLAlchemy + SQLite/Postgres
Cache	Redis (optional)
Auth	JWT (PyJWT), password hashing (passlib)
Observability	prometheus-client
Migrations	Alembic
Testing	Pytest

---

📁 Project Structure

.
├── backend/
│   ├── app/
│   │   ├── main.py
│   │   ├── models.py
│   │   ├── schemas.py
│   │   ├── db.py
│   │   ├── repositories/
│   │   └── services/
│   │       ├── ai_client.py
│   │       ├── interview_service.py
│   │       ├── auth_service.py
│   │       ├── history_service.py
│   │       └── cache.py
│   ├── alembic/
│   ├── tests/
│   ├── requirements.txt
│   └── .env.example
├── frontend/
│   ├── src/
│   │   ├── components/
│   │   ├── hooks/
│   │   ├── pages/
│   │   ├── services/
│   │   └── styles/
│   └── package.json
├── bootstrap.ps1
├── Makefile
└── README.md

---

🚀 Installation

Prerequisites

• Python 3.12+
• Node.js 18+
• Groq API key

Backend

cd backend
python -m venv venv
venv\Scripts\activate
pip install -r requirements.txt
copy .env.example .env
alembic -c alembic.ini upgrade head
uvicorn backend.main:app --reload

Frontend

cd frontend
npm install
npm start

---

💻 Usage

1. Open http://localhost:3000
2. Select interview type + add JD text (or drop file)
3. Enter simulation and answer all questions
4. Generate report with metrics and prep guidance
5. Optional: sign in to save and review historical runs

---

🔌 API Reference

Method	Endpoint	Description
GET	/	Health check
POST	/auth/register	Register account
POST	/auth/login	Login and receive JWT
GET	/history	List user interview runs
GET	/history/{run_id}	Detailed run data
POST	/setup	Create session + questions
POST	/evaluate	Record answer for a question
POST	/report	Compute final scored report
POST	/resume-gap-analysis	Resume/JD fit analysis
GET	/metrics	Prometheus metrics
GET	/observability/summary	Authenticated latency/error summary

---

⚙️ Configuration

Set values in backend/.env:

GROQ_API_KEY=your_groq_api_key_here
GROQ_MODEL=llama-3.1-70b-versatile
CORS_ORIGINS=http://localhost:3000
SESSION_TTL_MINUTES=120
DATABASE_URL=sqlite:///./quantis_interview_grid.db
REDIS_URL=redis://localhost:6379/0
JWT_SECRET=change_me_to_32_plus_chars
JWT_EXPIRE_HOURS=72

---

🧪 Testing

cd backend
python -m pytest tests

cd ../frontend
npm run build

---

🔒 Security Notes

• Use a strong JWT_SECRET (32+ chars) for production.
• Redis is optional; fallback works without it.

---

License

This project is licensed under the MIT License. See LICENSE.

Built with ❤️ by Crasta Telvin

⭐ Star this repo if you find it useful!