Oracle Cloud Infrastructure Documentation / Release Notes

Add Safety Modes to Cohere Models in OCI Generative AI

You can now add an optional safety mode to OCI Generative AI Cohere models during a chat session. This parameter adds a safety instruction to the model's generated responses.

Safety Mode Options
  • Strict
    Aims to avoid sensitive topics, such as violent or sexual acts and profanity. This mode aims to provide a safer experience by prohibiting responses or recommendations that it finds inappropriate. Strict mode is suited for corporate use, such as for corporate communications and customer service.
  • Contextual
    Puts fewer constraints than the strict mode on the output. It maintains core protections by aiming to reject harmful or illegal suggestions, but it allows profanity and some toxic content, sexually explicit and violent content, and content that contains medical, financial, or legal information. Contextual mode is suited for entertainment, creative, or academic use.
Available models

This feature is only available for cohere.command-r-08-2024, cohere.command-r-plus-08-2024 and Cohere models released after these models. See the model release dates.

To learn more about safety modes, see Chat in Generative AI. For information about the service, see Generative AI documentation.