Configure AI concierge settings and persona
URL where Ollama is running (default: http://localhost:11434)
Maximum tokens in response (100-4000)
This prompt defines Lira's behavior, personality, and expertise. Be specific about trading knowledge, risk awareness, and communication style.
• Ollama (Recommended): Free, private, runs locally
1. Install: ollama.com
2. Run: ollama pull llama3.2
3. Start: ollama serve
• OpenAI: Get your key from platform.openai.com
• Anthropic: Get your key from console.anthropic.com
Lower values (0-0.5) make responses more focused and deterministic. Higher values (1-2) increase creativity and variation.
Define how Lira behaves, communicates, and assists. Include trading expertise, risk awareness, personality traits, and response style.
All API keys are encrypted using AES-256 before storage. Never share your configuration with untrusted parties.