permissiveContentTransformations
Guardrails that allow for permissively transforming text input, including potentially unsafe content, to text responses.
Declaration
static let permissiveContentTransformations: SystemLanguageModel.GuardrailsMentioned in
Discussion
In this mode, requests you make to the model that generate a string won’t throw LanguageModelSession.GenerationError.guardrailViolation(_:) errors. However, when the purpose of your instructions and prompts isn’t to transform input from a person, the model may still refuse to respond to potentially unsafe prompts by generating an explanation.
When you generate responses other than string, this mode behaves the same way as default.