Add moderations API to OpenAI::Client
What does this MR do and why?
This MR adds moderations
api to Gitlab::Llm::OpenAi::Client
for users of this client to utilize.
Example response:
Gitlab::Llm::OpenAi::Client.new(User.first).moderations(input: 'hi')
=> {"id"=>"modr-7AEg8b8vwgoLno0lJKDJ6BEyjO8Pf",
"model"=>"text-moderation-004",
"results"=>
[{"flagged"=>false,
"categories"=>{"sexual"=>false, "hate"=>false, "violence"=>false, "self-harm"=>false, "sexual/minors"=>false, "hate/threatening"=>false, "violence/graphic"=>false},
"category_scores"=>
{"sexual"=>7.04759731888771e-05,
"hate"=>1.410793828426904e-07,
"violence"=>1.953629436002302e-08,
"self-harm"=>1.1341324580860235e-11,
"sexual/minors"=>2.1905959712853473e-08,
"hate/threatening"=>4.442902643009283e-12,
"violence/graphic"=>2.6168814337701463e-10}}]}
Mentions https://gitlab.com/gitlab-org/gitlab/-/issues/408171
Screenshots or screen recordings
Screenshots are required for UI changes, and strongly recommended for all other merge requests.
How to set up and validate locally
- Open rails console
rails c
- Set your OpenAI key
Gitlab::CurrentSettings.update!(openai_api_key: "")
- Perform a sample request and observe results
Gitlab::Llm::OpenAi::Client.new(User.first).moderations(input: 'hi')
- Verify response is from OpenAI moderations endpoint
MR acceptance checklist
This checklist encourages us to confirm any changes have been analyzed to reduce risks in quality, performance, reliability, security, and maintainability.
-
I have evaluated the MR acceptance checklist for this MR.
Edited by George Koltsov