MockMind

MockMind is a full-stack AI-powered mock interview platform. Candidates can start a quick interview for a target role or upload a PDF resume so MockMind can extract skills, projects, experience, and education before generating tailored technical questions.

Features

• Email/password signup and login with JWT authentication
• Resume PDF parsing with skill, project, education, and experience extraction
• AI-generated technical questions using Google Gemini
• Easy, medium, hard, and random difficulty options
• Five, ten, or fifteen question interview sessions
• Answer evaluation with per-question feedback, an overall score, improvement areas, and confidence scoring
• MongoDB-backed interview history with detailed session views
• React frontend with protected routes and browser-based speech input support

Project Structure

MockMind/
├── mockmind-backend/       # FastAPI API, auth, resume parsing, Gemini, MongoDB
├── mockmind-frontend/      # React + Vite web application
└── README.md

Requirements

• Python 3.10 or newer
• Node.js 18 or newer and npm
• A running MongoDB instance
• A Google Gemini API key

Configuration

Create mockmind-backend/.env locally. Never commit this file or place real credentials in the repository.

MONGO_URI=mongodb://localhost:27017
DB_NAME=mockmind
JWT_SECRET=replace-with-a-long-random-secret
JWT_EXPIRE_HOURS=72
GEMINI_API_KEY=your-gemini-api-key

The backend loads these values with python-dotenv. The root .gitignore ignores .env files across the whole project while allowing a future .env.example template to be committed.

Backend Setup

From the repository root:

cd mockmind-backend
python -m venv .venv

Activate the virtual environment:

# Windows PowerShell
.venv\Scripts\Activate.ps1

# macOS/Linux
source .venv/bin/activate

Install dependencies and start the API:

pip install -r requirement.txt
uvicorn main:app --reload

The API runs at http://localhost:8000. Interactive API documentation is available at http://localhost:8000/docs.

Frontend Setup

In a second terminal:

cd mockmind-frontend
npm install
npm run dev

The Vite development server runs at http://localhost:5173. By default, the frontend calls the backend at http://localhost:8000. To use another API URL, create mockmind-frontend/.env.local:

VITE_API_URL=http://localhost:8000

Available frontend commands:

npm run dev      # Start the development server
npm run build    # Create a production build
npm run lint     # Run ESLint
npm run preview  # Preview the production build locally

API Overview

All interview and resume endpoints require a bearer token returned by signup or login.

Method	Endpoint	Purpose
POST	/auth/signup	Create an account
POST	/auth/login	Authenticate a user
POST	/resume/parse	Parse an uploaded PDF resume
POST	/interview/generate	Generate interview questions
POST	/interview/evaluate	Evaluate submitted answers and save the session
GET	/interview/history	List the signed-in user's sessions
GET	/interview/history/{session_id}	Get one saved session

Typical Flow

1. Start MongoDB and configure the backend .env file.
2. Run the FastAPI backend.
3. Run the Vite frontend.
4. Create an account or log in.
5. Choose Resume Mode or Quick Start Mode and configure the session.
6. Answer the generated questions and submit the session.
7. Review the score and feedback, then revisit sessions from Interview History.

Notes

• Resume uploads must be text-based PDF files; scanned PDFs without a text layer are rejected.
• Gemini is used for question generation and answer evaluation, so a valid API key and network access are required for those workflows.
• CORS is currently configured for the local frontend at http://localhost:5173.