38 investigate genai evaluation tools - Githubissues

FullFact / health-misinfo-shared

Raphael health misinformation project, shared by Full Fact and Google

MIT License

0 stars 0 forks source link

38 investigate genai evaluation tools #72

Closed dearden closed 4 months ago

dearden commented 4 months ago

Fixes #38 .

Adds dev scripts for doing prompt/model evaluation using PromptFoo and AutoSxS.

There's no functional scripts in this, it is just demonstrative scripts of how to use these evaluation tools.

Pull request checklist

[x] I have linked my PR to an issue
[x] I’ve used conventional commits
[x] My branch is up-to-date with main
[x] Where appropriate, I have added or updated tests
[x] Where appropriate, I have updated documentation to reflect my changes