安全护栏

安全是任何 AI 应用程序的关键组成部分。Llama Stack 提供了一个护盾系统，该系统可以在多个接触点应用。

# Register a safety shield
shield_id = "content_safety"
client.shields.register(shield_id=shield_id, provider_shield_id="llama-guard-basic")

# Run content through shield
response = client.safety.run_shield(
    shield_id=shield_id, messages=[{"role": "user", "content": "User message here"}]
)

if response.violation:
    print(f"Safety violation detected: {response.violation.user_message}")