Docs | Tosche Station

Arquitetura

┌──────────────────┐    ┌──────────────────┐    ┌──────────────────┐
│                  │    │                  │    │                  │
│  Tosche Station Chatbot │───▶│  AI Firewall (Imperva) │───▶│  Provedor LLM     │
│                  │◀───│                  │◀───│                  │
│  POST /chatbot   │    │  Inspect + Block │    │  OpenAI / Claude │
│                  │    │  • Injection     │    │  Ollama / Custom │
│                  │    │  • Data Leak     │    │                  │
└──────────────────┘    └──────────────────┘    └──────────────────┘

Provedores LLM

Provedor Custom (via AI Firewall)

Recomendado

Permite inserir um proxy de segurança (AI Firewall) entre o app e o LLM para detectar/bloquear prompt injection, data leakage, etc.

docker run -d --name tosche-station \ -e LLM_PROVIDER=custom \ -e LLM_BASE_URL=https://ai-firewall.yourcompany.com/v1 \ -e LLM_API_KEY=your-api-key \ -e LLM_MODEL=gpt-4o \ -e AI_MODE=vulnerable \ -p 8080:8080 tosche-station:2.1

OpenAI (Direto)

docker run -d --name tosche-station \ -e LLM_PROVIDER=openai \ -e LLM_API_KEY=sk-your-openai-key \ -e LLM_MODEL=gpt-4o-mini \ -p 8080:8080 tosche-station:2.1

Anthropic (Direto)

docker run -d --name tosche-station \ -e LLM_PROVIDER=anthropic \ -e LLM_API_KEY=sk-ant-your-anthropic-key \ -e LLM_MODEL=claude-sonnet-4-20250514 \ -p 8080:8080 tosche-station:2.1

OpenRouter

docker run -d --name tosche-station \ -e LLM_PROVIDER=openrouter \ -e LLM_API_KEY=sk-or-your-openrouter-key \ -e LLM_MODEL=meta-llama/llama-3-70b-instruct \ -p 8080:8080 tosche-station:2.1

Ollama (Local)

# Start Ollama first ollama serve & ollama pull llama3 # Then run Tosche Station docker run -d --name tosche-station \ -e LLM_PROVIDER=ollama \ -e LLM_BASE_URL=http://host.docker.internal:11434 \ -e LLM_MODEL=llama3 \ -p 8080:8080 tosche-station:2.1

None (baseado em regras)

Default mode. No LLM — chatbot uses pattern matching rules.

docker run -d --name tosche-station \ -e LLM_PROVIDER=none \ -p 8080:8080 tosche-station:2.1

Por que usar Custom Provider?

O provedor custom permite rotear todo o tráfego LLM através de um proxy de segurança como Imperva AI Firewall, que inspeciona as solicitações e respostas em busca de ameaças.

Prompt Injection

Detects & blocks injection attempts before reaching the LLM

Data Leakage

Prevents sensitive data from being returned in LLM responses

Audit Trail

Full logging of all LLM interactions for compliance

Variáveis de Ambiente

Variable	Default	Description
LLM_PROVIDER	none	none \| openai \| anthropic \| openrouter \| ollama \| custom
LLM_API_KEY	(empty)	API key for the LLM provider
LLM_MODEL	(auto)	Model name (auto-defaults per provider)
LLM_BASE_URL	(auto)	Override API base URL (required for custom/ollama)
LAB_MODE	vulnerable	vulnerable \| baseline
AI_MODE	vulnerable	vulnerable \| guarded
CSP_MODE	off	off \| report \| enforce
FORCE_LANG	(empty)	Force language: es \| en \| pt
APP_PORT	8080	Server port

Exemplo Docker