LLM Validator: Improve questions and prompt generation#317
Merged
Conversation
academo
requested review from
oshirohugo,
wbrowne and
xnyo
and removed request for
a team
academo
commented
Mar 31, 2025
xnyo
approved these changes
Apr 1, 2025
Member
xnyo
left a comment
xnyo
left a comment
There was a problem hiding this comment.
I haven't tested this but the code LGTM apart from a few minor nitpicks. Awesome work! 🙌
| Answer string `json:"answer"` | ||
| Files []string `json:"files"` | ||
| ShortAnswer bool `json:"short_answer"` | ||
| ExpectedShortAnswer bool |
Member
There was a problem hiding this comment.
Nit: You should mark the field with a json:"-" tag if you want to make the json encoder/decoder ignore it:
github-project-automation
Bot
moved this from 🔬 In review
to 🚀 Shipped
in Grafana Catalog Team
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
main change
It now asks the model one question at the time instead of all questions at once.
This change allows the model to focus on replying a single question which greatly improves its answers. It also means the validator now consumes more api credits from google when running.
Other changes
gemini-2.0-flash-001(stable gemini flash 2)