Policies and guardrails

Policies are a crucial component in managing and securing your AI application. They allow you to define rules and guardrails that govern the behavior of your AI model.

​

Understanding Policies

A policy is a set of rules that are applied to either the input, output, or both in your AI application. Each policy consists of one or more rules, which are evaluated to ensure compliance with your defined standards.

​

Policy Structure

A policy is defined using the following structure:

• id: Unique ID for the policy.
• definition: A short description.
• rules: A list of rules that are applied to the policy see rules catalog.
  • type: Supported rule types are classifier, rubric, jailbreak, pii, contains,regex,similarity and factuality. For model based rules, you can specify the revision, e.g., jailbreak@47ffb2e, see more in model based rules
  • expected: If match, it should fail or pass the evaluation.
  • value: a string value, depending on the rule type, e.g., for classifier it’s the class name, for rubric it’s the criteria, for pii it’s the pii types (phone, email, etc)
  • threshold: a float value, depending on the rule type. e.g., for jailbreak, classifier and pii it’s the model min output score, similarity is the cosine score.
• target: The target of the policy, which can be either input, output, or both, being the user, assistant and both messages, respectivelly.

​

Example Policy

policy = {
    "id": "my-policy-id",
    "definition": "...",
    "rules": [
        {
            "type": "classifier",
            "value": "topic A",
            "expeted": "fail",
            "threshold": 0.9
        }
    ],
    "target": "output"
}

​

Create policy before evaluating

http.post('/v1/applications/my-app/policies', json=policy)

​

List your policies

http.get('/v1/applications/my-app/policies')

​

Update your policy

http.put('/v1/applications/my-app/policies/my-policy-id', json=policy)

​

Delete your policy

http.delete('/v1/applications/my-app/policies/my-policy-id')