IONOS Agent Docs v1.0 just launched!⭐ Star us on GitHub
docsGetting StartedEnvironment Variables

Environment Variables

Create a .env file in both frontend and backend folders, or one at the root.

Frontend .env

Streamlit (Recommended):

BACKEND_URL=http://localhost:8000
IONOS_API_KEY=your_ionos_api_key_here

Next.js (Alternative):

NEXT_PUBLIC_APP_BASE_URL=http://localhost:8000

Backend .env

Go to your Studio settings here: https://studio.ionos.de/platform/org/YOUR_ORG_ID/settings

IONOS_API_KEY=your_ionos_api_key_here
TAVILY_API_KEY=your_tavily_api_key_here
 
# Optional: IONOS Studio fine-tuned models
STUDIO_API_KEY=your_studio_api_key_here
STUDIO_ORG_ID=your_studio_org_id_here
STUDIO_BASE=https://studio.ionos.de/api/v1
 
# Fine-tuned model UUIDs
STUDIO_MODEL_QWEN_GDPR=model_uuid_here
STUDIO_MODEL_GRANITE_GDPR=model_uuid_here
STUDIO_QWEN3_SHAREGPT=model_uuid_here

Variable Description

Frontend:

  • BACKEND_URL (Streamlit): URL of the backend API (default: http://backend-service:8000 for Kubernetes, use http://localhost:8000 for local dev).
  • IONOS_API_KEY (Streamlit): Required for fetching inference models directly from IONOS Hub API.
  • NEXT_PUBLIC_APP_BASE_URL (Next.js): URL of the backend for API calls.

Backend:

  • IONOS_API_KEY: Secret key for IONOS AI Models Hub access (required for inference models with web search).
  • TAVILY_API_KEY: API key for Tavily real-time web search tool (required for inference model agent functionality).
  • STUDIO_API_KEY: API key for IONOS AI Model Studio (optional, required only if using fine-tuned models).
  • STUDIO_ORG_ID: Your IONOS Studio organization ID (optional, required only if using fine-tuned models).
  • STUDIO_BASE: Base URL for Studio API (optional, defaults to https://studio.ionos.de/api/v1).
  • STUDIO_MODEL_*: UUIDs of your fine-tuned models in IONOS Studio (optional, add as many as you need).
PrerequisitesSetup