APEX AI — Formula 1 Intelligence Platform

APEX AI is a production-grade Formula 1 Intelligence Platform built for engineers, analysts, and enthusiasts who demand deep telemetry insights, AI-driven race predictions, and real-time strategic analysis. The platform draws design inspiration from Mercedes AMG Petronas, F1 TV, and Bloomberg Terminal, bringing a professional analytics aesthetic to the world of motorsport data.

---

Overview

The platform consists of two independently deployable services:

• Frontend — A Next.js application featuring a dark-themed, telemetry-focused dashboard with real-time data visualizations, an AI race engineer chatbot, prediction models, and intelligence reports.
• Backend — A Python FastAPI service that exposes a structured REST API serving driver data, lap telemetry, race predictions, strategic insights, and a chat inference endpoint.

---

Tech Stack

Frontend

Technology	Purpose
Next.js 16 (App Router)	React framework with server-side rendering
TypeScript	End-to-end type safety
Tailwind CSS v4	Utility-first styling
shadcn/ui	Accessible, composable UI components
Framer Motion	Smooth animations and transitions
Recharts	Data visualization and charting
TanStack Query	Server state management and caching
Zustand	Global client state management
Lucide React	Icon library

Backend

Technology	Purpose
Python 3.x	Runtime
FastAPI	High-performance ASGI web framework
Uvicorn	ASGI server with hot-reload
Pydantic v2	Data validation and serialization

---

Features

Dashboard

Real-time race overview with driver championship standings, live race position history charted lap-by-lap, team constructor standings, and AI-generated strategic insights panel.

Telemetry

Head-to-head driver telemetry comparison across a full lap. Charts include speed trace, throttle application, brake pressure, and gear selection, all synchronized by lap distance. Includes sector-by-sector time analysis and tyre compound degradation visualization.

AI Race Engineer

An interactive chat interface backed by the backend inference endpoint. Ask questions about sector performance, tyre strategy, undercut windows, or driver comparisons and receive structured, telemetry-aware responses.

Predictions

AI-generated race outcome probabilities. Includes win probability rankings, podium prediction display, and a stacked outcome distribution chart showing each driver's probability of finishing in the top three positions.

Intelligence Reports

A filterable archive of detailed technical, strategic, and race reports. Each report includes full article content, author attribution, estimated read time, and tag taxonomy.

Settings

User preferences panel for theme, telemetry refresh rate, and unit system configuration.

---

Project Structure

APEX-AI/
├── frontend/
│   └── apex-ai/
│       ├── app/
│       │   ├── (platform)/
│       │   │   ├── dashboard/       page.tsx
│       │   │   ├── telemetry/       page.tsx
│       │   │   ├── ai-engineer/     page.tsx
│       │   │   ├── predictions/     page.tsx
│       │   │   ├── reports/         page.tsx
│       │   │   ├── chatbot/         page.tsx
│       │   │   └── settings/        page.tsx
│       │   ├── globals.css
│       │   └── layout.tsx
│       ├── components/
│       │   ├── charts/              Recharts dashboard components
│       │   ├── layout/              Sidebar and navbar
│       │   ├── predictions/         Podium, outcome charts, rankings
│       │   ├── reports/             Report card components
│       │   ├── telemetry/           Telemetry chart suite
│       │   └── ui/                  Shared component primitives
│       ├── lib/
│       │   ├── mock-data.ts         Frontend static mock data
│       │   └── store.ts             Zustand global state
│       └── types/
│           └── index.ts             TypeScript type definitions
│
└── backend/
    ├── main.py                      FastAPI application entry point
    ├── models.py                    Pydantic models
    ├── mock_data.py                 Python mock data and logic
    ├── requirements.txt             Python dependencies
    └── routers/
        ├── drivers.py               /api/drivers endpoints
        ├── telemetry.py             /api/telemetry endpoints
        ├── predictions.py           /api/predictions endpoints
        ├── reports.py               /api/reports endpoints
        └── chat.py                  /api/chat endpoint

---

API Reference

The backend runs on http://localhost:8000. Full interactive documentation is auto-generated at /docs (Swagger UI) and /redoc (ReDoc).

Core Endpoints

Method	Endpoint	Description
GET	/api/dashboard	Consolidated dashboard payload
GET	/api/drivers	All 20 drivers
GET	/api/drivers/standings	Championship order
GET	/api/drivers/{id}	Single driver by ID
GET	/api/telemetry/live	Lap telemetry (supports driver1 and driver2 query params)
GET	/api/telemetry/sectors	Sector analysis table
GET	/api/telemetry/tyres	Tyre degradation data
GET	/api/telemetry/pitstops	Pit stop records
GET	/api/telemetry/positions	Lap-by-lap race positions
GET	/api/predictions/race	Win/podium/DNF probabilities
GET	/api/predictions/race/podium	Predicted top 3
GET	/api/predictions/insights	Active AI strategic alerts
GET	/api/reports	All reports (filterable by category, featured)
GET	/api/reports/{id}	Single report
POST	/api/chat	Chat inference (body: {"message": "..."})
GET	/api/chat/suggestions	Pre-built prompt suggestions
GET	/api/health	Backend health and race status

---

Getting Started

Prerequisites

• Node.js 18 or later
• Python 3.10 or later
• npm or pnpm

1. Clone the Repository

git clone https://github.com/Sreejith-nair511/APEX-AI.git
cd APEX-AI

2. Start the Backend

cd backend

# Create and activate virtual environment
python -m venv venv
.\venv\Scripts\activate        # Windows
source venv/bin/activate       # macOS / Linux

# Install dependencies
pip install -r requirements.txt

# Start the server
uvicorn main:app --reload --port 8000

The API will be available at http://localhost:8000. The Swagger UI documentation will be available at http://localhost:8000/docs.

3. Start the Frontend

Open a second terminal:

cd frontend/apex-ai

# Install dependencies
npm install

# Start the development server
npm run dev

The application will be available at http://localhost:3000.

4. Production Build (Frontend)

cd frontend/apex-ai
npm run build

---

Design System

The platform uses a custom dark design system built on Oklch color tokens defined in globals.css.

• Primary accent: Red (#DC2626) used for live indicators, CTAs, and critical alerts
• Typography: Inter (Google Fonts)
• Theme: Dark by default with glassmorphism used sparingly for depth
• Animations: Framer Motion for page transitions and data reveals
• Chart palette: Team-accurate F1 colors applied consistently across all visualizations

---

Development Notes

• The frontend currently uses static mock data from lib/mock-data.ts. The backend exposes equivalent API endpoints, and the frontend can be wired to consume them via TanStack Query by replacing the static imports with useQuery calls to http://localhost:8000/api/....
• The fix.py file in the frontend directory was a one-time utility script used during development to fix escaped backtick characters. It can be deleted safely.
• The backend chat endpoint uses keyword matching for demo purposes. It can be replaced with any LLM provider (OpenAI, Gemini, Anthropic) by updating mock_data.get_chat_reply.

---

License

MIT