Learn how to use Prompt Engine powered by Groq to automate tasks in your application.
llama-3.3-70b-versatile
llama-3.1-8b-instant
llama-guard-4-12b
to detect and filter for common abuse such as prompt injection, crimes, sexual content and more. Prompt guard is a feature thatβs built into every step of the Prompt Engine and is configurable to allow or block specific content types.
.env
file.
prompt_guard
field.
defamation
: Guards against potentially libelous contentprivacy
: Protects personal informationhate
: Filters out discriminatory contentsexual_content
: Blocks explicit materialelections
: Prevents election misinformationcode_interpreter_abuse
: Guards against code exploitationindiscriminate_weapons
: Blocks content about mass destruction weaponsspecialized_advice
: Prevents unauthorized professional advice