Syntax Guard

The Syntax Guard is an output guard that analyzes the responses generated by your language model to ensure they adhere to proper syntax, formatting, and escaping rules. It helps in identifying issues such as unconverted placeholders, incorrect escaping, punctuation errors, and inconsistent formatting, ensuring the outputs are syntactically correct and well-structured.

info

SyntaxGuard is only available as an output guard.

Here's what an unsafe output would look like in the context of incorrect syntax:

"Welcome {{user_name}}! Your order has been placed."
— probably your LLM

Example

Since SyntaxGuard 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, SyntaxGuard

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

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

...

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 SyntaxGuard.

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