March 1st 2024
We are delighted to introduce our latest features and fixes from the recent period, enhancing your experience with improved functionality and performance.
Toxicity Policy
We’ve launched the Toxicity Policy, designed to detect and filter out explicit, offensive, or inappropriate language in user interactions. This policy ensures that both user inputs and LLM responses remain respectful and free from toxic language. Whether intentional or accidental, offensive language is immediately flagged and filtered to maintain safe and respectful communications.
Allowed Topics Policy
We’re also introducing the Allowed Topics Policy, which helps guide conversations toward relevant, pre-approved topics, ensuring that discussions stay focused and within defined boundaries. This policy ensures that interactions remain on-topic by restricting the conversation to a set of allowed subjects. Whether you’re focused on customer support, education, or other specific domains, this policy ensures that conversations stay relevant.