Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs-chat.die-coaching-akademie.de/llms.txt

Use this file to discover all available pages before exploring further.

​
Requirements

Python

The project uses Python with FastAPI, Uvicorn, Jinja2, Pydantic, python-dotenv, and the OpenAI SDK.

Environment file

Copy .env.example to .env and add local values. Do not commit .env.

​
Local setup

1

Create a virtual environment

cd faq_bot
python3 -m venv .venv
source .venv/bin/activate
2

Install dependencies

pip install -r requirements.txt
3

Create local configuration

cp .env.example .env
Add a real OpenAI API key locally:
OPENAI_API_KEY=sk-your-openai-api-key
OPENAI_MODEL=gpt-4o-mini
ALLOWED_ORIGINS=http://127.0.0.1:8000,http://localhost:8000
LOG_LEVEL=INFO
RESPONSE_CACHE_TTL_SECONDS=3600
RESPONSE_CACHE_MAX_ITEMS=200
ADMIN_TOKEN=change-me
ANALYTICS_ENABLED=true
4

Start the app

uvicorn app:app --reload
5

Verify health

curl http://127.0.0.1:8000/health
Expected shape:
{
  "status": "ok",
  "knowledge_base_entries": 219,
  "openai_configured": true
}

​
Docker alternative

The Docker setup remains an alternative local/container path. Production currently uses systemd and Nginx. 
cd faq_bot
cp .env.example .env
docker compose up --build -d
The production Hetzner deployment documented in this repository does not use Docker. Use Docker only when you explicitly want a container-based local or alternative deployment.