- Issue created by @lussoluca
Right now, any content written by the user in a chat is sent to the chosen LLM, and every content produced by the LLM is sent back to the user. This can lead to a series of issues, like sharing personal information with external providers, hallucinations, policy violations, and so on.
✨ Create the concept of Guardrail agents Active introduces the concepts of guardrails and guardrails set; we can also use them on agents to make sure no unwanted contents are sent to an LLM or back to the user.
Add a new select to the agent configuration form to choose which guardrail set to apply.
A new select in the agent configuration form.
None.
None.
Active
1.2
Code