AI Lakera Guard Configuration

Parameters

See plugin common configurations for configuration options available to all plugins.

This plugin supports referencing sensitive parameter values from environment variables using the env:// prefix, or from a secret manager, such as HashiCorp Vault’s KV secrets engine, using the secret:// prefix. For more information, see environment variables in plugin and secrets.

• api_key — string · required

  Valid values: non-empty

  API key used to authenticate to the Lakera Guard API. It is sent as a Bearer token in the Authorization header. The value is encrypted before being stored.

• lakera_endpoint — string · optional · default: https://api.lakera.ai/v2/guard

  URL of the Lakera Guard v2 endpoint. Set this to point at a self-hosted or regional Lakera Guard deployment.

• project_id — string · optional

  Lakera project ID whose policy (detectors and thresholds) should be applied to the scan.

• direction — string · optional · default: input

  Valid values: input, output, or both

  Which traffic to scan. With input, only the request prompt is scanned. With output, only the LLM response is scanned, including streaming responses. With both, both are scanned.

• action — string · optional · default: block

  Valid values: block or alert

  How to handle a flagged verdict. With block, the request or response is denied. With alert, the traffic is passed through and the verdict is only logged, which is useful for evaluating a policy before enforcing it.

• deny_code — integer · optional · default: 200

  Valid values: between 200 and 599 inclusive

  HTTP status code returned when blocking flagged traffic. The default 200 returns a provider-compatible completion whose content is the failure message, so SDK clients handle it gracefully. Set a 4xx value to surface the block as an HTTP error instead.

• request_failure_message — string · optional · default: Request blocked by Lakera Guard

  Message returned in the deny response when the request prompt is flagged.

• response_failure_message — string · optional · default: Response blocked by Lakera Guard

  Message returned in the deny response when the LLM response is flagged.

• reveal_failure_categories — boolean · optional · default: false

  If true, append the flagged detector categories (and their confidence levels) to the failure message.

• fail_open — boolean · optional · default: false

  Behavior when the call to the Lakera Guard API fails or times out. If false, the traffic is blocked (fail closed). If true, the traffic is allowed (fail open).

• fail_mode — string · optional · default: skip

  Valid values: skip, warn, or error

  Behavior when the request format is not recognized as AI traffic, for example when the route does not also configure ai-proxy or ai-proxy-multi. With skip, the request passes unchecked. With warn, it passes unchecked and a warning is logged. With error, the request is rejected with HTTP 500. None of these outcomes means a Lakera scan succeeded.

• timeout — integer · optional · default: 5000

  Valid values: greater than or equal to 1

  Timeout in milliseconds for the request to the Lakera Guard API.

• ssl_verify — boolean · optional · default: true

  If true, verify the TLS certificate of the Lakera Guard endpoint.