Backend Setup (FastAPI)

1. Navigate to backend

cd backend

2. Create a virtual environment and activate it

a) Windows (PowerShell)

python -m venv .venv
.\.venv\Scripts\Activate.ps1

b) macOS / Linux (bash/zsh)

python3 -m venv .venv
source .venv/bin/activate

3. Install dependencies

pip install -r requirements.txt

4. Set environment variables

Recommended: Create a .env file in the backend folder:

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

Alternative (shell environment variables):

Windows PowerShell:

$env:IONOS_API_KEY = "<your_ionos_api_key>"
$env:TAVILY_API_KEY = "<your_tavily_api_key>"

macOS/Linux:

export IONOS_API_KEY="<your_ionos_api_key>"
export TAVILY_API_KEY="<your_tavily_api_key>"

Required:

IONOS_API_KEY: For accessing IONOS AI Models Hub (inference models)
TAVILY_API_KEY: For web search functionality (essential for the ReAct agent)

Optional (for IONOS Studio fine-tuned models):

STUDIO_API_KEY: API key for IONOS AI Model Studio
STUDIO_ORG_ID: Your IONOS Studio organization ID (get from https://studio.ionos.de/platform/org/YOUR_ORG_ID/settings)
STUDIO_BASE: Base URL for Studio API (defaults to https://studio.ionos.de/api/v1)
STUDIO_MODEL_*: UUIDs of your fine-tuned models

5. Run the server

uvicorn main:app --host 127.0.0.1 --port 8000 --reload

The API will be available at http://localhost:8000.

6. Test the chat endpoint

Run these from another terminal:

a) Windows (PowerShell)

Invoke-RestMethod `
	-Uri "http://127.0.0.1:8000/" `
	-Method Post `
	-Headers @{ "x-model-id" = "mistralai/Mistral-Small-24B-Instruct" } `
	-Body (@{ messages = @(@{ type = "human"; content = "Hello!" }) } | ConvertTo-Json -Depth 3) `
	-ContentType "application/json"

b) macOS / Linux (bash/zsh)

curl -s -X POST "http://127.0.0.1:8000/" \
  -H "x-model-id: mistralai/Mistral-Small-24B-Instruct" \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"type":"human","content":"Hello!"}]}'

Environment Variables Agent Tools