Skip to content

Draft: Questions testing

Alexandru Croitor requested to merge llm_test_questions into master

What does this MR do and why?

Add rake task to run chat agent on a set of questions

Adding a rake tasks to test which tools are being picked by the chat agent for specific questions. It should allow us to evaluate pthe performance of the chat agent by evaluating if it is picking up the expected tools for the question to be answered.

Screenshots or screen recordings

Screenshots are required for UI changes, and strongly recommended for all other merge requests.

Before After

How to set up and validate locally

run the rake task: rake gitlab:llm:zero_shot:test:questions

MR acceptance checklist

This checklist encourages us to confirm any changes have been analyzed to reduce risks in quality, performance, reliability, security, and maintainability.

Edited by Alexandru Croitor

Merge request reports