Extend AI Tutor Tester to get responses from LLMGuard - #60224
Merged
Conversation
Erin007
changed the title
Erin007
changed the title
Erin007
marked this pull request as ready for review
August 8, 2024 13:38
Contributor
Author
snickell
approved these changes
Aug 8, 2024
snickell
left a comment
snickell
left a comment
Contributor
There was a problem hiding this comment.
Assuming we do the followup work (e.g. #60221) and pull the EC2 instance out of the loop, I'm game to merge this now so @samantha-code can test.
Contributor
Author
|
@samantha-code merged ✅ |
8 tasks
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
CT-721
For internal testing of the chat safety layer, it will more efficient to get bulk responses back rather than test inputs 1 by 1. In this PR I extend the functionality of the AI Tutor Tester to conditionally be ably to hit the LLMGuard endpoint based on selection from a dropdown. The message safety check is currently hitting an EC2 instance that has been set up as an endpoint until we have a better long-term solution that will allow us to run Python alongside our Ruby code. This is a very lightweight, temporary solution to unblock testing of LLMGuard.
The uploaded csv should have one column
studentInputand theaiResponsecolumn will be set as "ok" if LLMGuard deems the input "safe", "toxic" if it catches toxic content and "error" if something in the process goes wrong.llmguard_example.mov