[backport -> release/3.6.x] feat(plugins): ai-prompt-guard-plugin #12337 #12427
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* feat(plugins): ai-prompt-guard-plugin * fix(ai-prompt-guard): fixes from code review * Update kong/plugins/ai-prompt-guard/schema.lua Co-authored-by: Vinicius Mignot <[email protected]> --------- Co-authored-by: Jack Tysoe <[email protected]> Co-authored-by: Vinicius Mignot <[email protected]>
github-actions
bot
added
chore
flrgh
approved these changes
Jan 25, 2024
locao
approved these changes
Jan 25, 2024
tysoekong
added
the
cherry-pick kong-ee
|
Cherry-pick failed for |
|
Cherry-pick failed for Please cherry-pick the changes locally. git remote add upstream https://github.com/kong/kong-ee
git fetch upstream release/3.6.x
git worktree add -d .worktree/cherry-pick-12427-to-release/3.6.x-to-upstream upstream/release/3.6.x
cd .worktree/cherry-pick-12427-to-release/3.6.x-to-upstream
git checkout -b cherry-pick-12427-to-release/3.6.x-to-upstream
ancref=$(git merge-base 31f40482368ec5c16acfa0c334e2f1347828286d b3308d575605626aea054849f8e0bcedb9e7e0c2)
git cherry-pick -x $ancref..b3308d575605626aea054849f8e0bcedb9e7e0c2 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Automated backport to
release/3.6.x, triggered by a label in #12341.Original description
Summary
This commit offers another plugin that extends the functionality of "AI Proxy" in #12207.
It compares the user's
llm/v1/chatorllm/v1/completionsrequest against a series of regular expressions, in two config arrays:If the request matches any regex pattern in deny, the caller is 400'd.
If any allow is specified, by the request matches none of them, the caller is also 400'd.
Engineering design document is available for this feature, but it is quite simple. Comprehensive tests supplied.
This reason for its development, is that many of our users would like to block specific prompts, words, phrases, or otherwise more tightly control how an AI / LLM model is used, if being called via Kong, and this applies especially with the
AI Proxyplugin that will simplify this process.Checklist
changelog/unreleased/kongorskip-changeloglabel added on PR if changelog is unnecessary. README.md