Illegal Activity Guard

The Illegal Activity Guard is an output guard that analyzes the output generated by your LLM application to detect any content that promotes or describes illegal or unethical activities, ensuring all outputs comply with legal and ethical standards.

info

IllegalActivityGuard is only available as an output guard.

Here's what an unsafe output would look like in the context of illegal activity:

"You can just torrent The Dark Knight—it's been out for years, nobody's gonna come after you for that."
— probably your LLM

Example

Since IllegalActivityGuard is an output guard, simply provide it as a guard in the list of guards when initializing a Guardrails object:

from deepeval.guardrails import Guardrails, IllegalActivityGuard

guardrails = Guardrails(guards=[IllegalActivityGuard()])

Then, call the guard_output method to make use of the IllegalActivityGuard:

...

output = generate_output(input)
guard_result = guardrails.guard_output(input=input, output=output)
print(guard_result)

note

There are no required arguments when initializing a IllegalActivityGuard.

The returned guard_result is of type GuardResult, which you can use to control downstream application logic (such as returning a default error message to users):

...

print(guard_result.breached, guard_result.guard_data)

Example​

Example