Skip to main content
FastAPI AI Kit

Quickstart

Get from git clone to a running API endpoint in under 10 minutes.

Prerequisites

  • Python 3.11+
  • Docker and docker-compose
  • An OpenAI or Anthropic API key

Step 1 — Clone the repo

After purchasing, you'll receive an invitation to the private GitHub repository.

git clone https://github.com/fastapikit/starter my-ai-api
cd my-ai-api

Step 2 — Configure environment

cp .env.example .env

Open .env and fill in at minimum:

# Database (docker-compose handles this locally)
DATABASE_URL=postgresql+asyncpg://user:pass@localhost:5432/aikit

# Redis (docker-compose handles this locally)
REDIS_URL=redis://localhost:6379/0

# LLM provider — choose one
OPENAI_API_KEY=sk-...
# ANTHROPIC_API_KEY=sk-ant-...

# Auth secret — generate with: openssl rand -hex 32
SECRET_KEY=your-secret-key-here

Step 3 — Start Docker services

docker-compose up -d

This starts PostgreSQL, Redis, and runs Alembic migrations automatically. The API starts on port 8000.

Step 4 — Verify

curl http://localhost:8000/healthz
# → {"status": "ok", "db": "connected", "redis": "connected"}

Open the interactive API docs at http://localhost:8000/docs.

Step 5 — Create a user and get an API key

# Register
curl -X POST http://localhost:8000/auth/register \
  -H "Content-Type: application/json" \
  -d '{"email": "dev@example.com", "password": "securepassword"}'

# Get JWT token
curl -X POST http://localhost:8000/auth/token \
  -d "username=dev@example.com&password=securepassword"

# Issue an API key (use the JWT token from above)
curl -X POST http://localhost:8000/api-keys \
  -H "Authorization: Bearer <your-jwt>" \
  -d '{"name": "dev-key", "tier": "pro"}'

Step 6 — Make your first AI call

curl http://localhost:8000/v1/chat \
  -H "X-API-Key: <your-api-key>" \
  -H "Content-Type: application/json" \
  -d '{"message": "Explain async Python in one sentence."}'

You'll get a streaming or buffered response, with token counts in the response headers.

Next steps

PreviousIntroductionNextProject Structure