You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/templates/guardrails-output-parser
Harrison Chase a7d5e0ce8a
add guardrails profanity (#12609)
8 months ago
..
guardrails_output_parser add guardrails profanity (#12609) 8 months ago
tests add guardrails profanity (#12609) 8 months ago
LICENSE add guardrails profanity (#12609) 8 months ago
README.md add guardrails profanity (#12609) 8 months ago
pyproject.toml add guardrails profanity (#12609) 8 months ago

README.md

guardrails-output-parser

Uses guardrails-ai to validate output.

This example protects against profanity, but with Guardrails you can protect against a multitude of things.

If Guardrails does not find any profanity, then the translated output is returned as is.

If Guardrails does find profanity, then an empty string is returned.