Get policy | Lakera API documentation

1 import requests 2 3 url = "https://platform.lakera.ai/api/v1-beta/policies/policyId" 4 5 headers = {"Authorization": "Bearer <token>"} 6 7 response = requests.get(url, headers=headers) 8 9 print(response.json())

1 { 2 "name": "string", 3 "policy_mode": "IO", 4 "input_detectors": [ 5 { 6 "type": "prompt_attack", 7 "threshold": "l1_confident", 8 "override_list": [ 9 "string" 10 ], 11 "allowed_domains": [ 12 "my-trusted-domain.com", 13 "another-safe-domain.com" 14 ] 15 } 16 ], 17 "output_detectors": [ 18 { 19 "type": "prompt_attack", 20 "threshold": "l1_confident", 21 "override_list": [ 22 "string" 23 ], 24 "allowed_domains": [ 25 "my-trusted-domain.com", 26 "another-safe-domain.com" 27 ] 28 } 29 ] 30 }

Authentication

AuthorizationBearer

Bearer authentication using API key. Generate an API key from the Lakera platform. Example: Bearer sk_123…

Path parameters

policyIdstringRequired

Response

Policy details

namestring

A descriptive name for the policy

policy_modeenum

Set to "IO" for screening model inputs and outputs

Allowed values:

input_detectorslist of objects

List of detector configurations to apply to LLM inputs

output_detectorslist of objects

List of detector configurations to apply to LLM outputs