simonw / simonw/llm

How to collect prompt/response feedback?!

Open
#706 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
12.5k
Forks
998
Avg merge
3d 13h
Merged PRs (30d)
10

Description

Hey llm community. I'd like to share a little plugin that I started: https://github.com/luebken/llm-logs-feedback. The idea is to quickly annotate a prompt/response tuple with feedback. At a later stage, I'd like to learn from the feedback I've stored and possibly adjust my prompts.

WDYT?

This is a preview version to gain feedback (pun intended) on the idea, the CLI design and the database schema. More things to come.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Review the linked llm-logs-feedback plugin first, focusing on its CLI design and database schema as described here. Before implementation, clarify whether this issue requests a specific change; done is an agreed scope and acceptance criteria for collecting and learning from prompt/response feedback.

Written by the indexing model from the issue text.

Assessment

Domain
ai, cli, databases
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.