Skip to contents

Training data from chat feedback

Source: R/feedback.R
dragon_feedback.Rd

Ratings and edits made in dragon_chat() or the app's Chat panel are saved under feedback/ in the runs directory. This turns them into data for the next stage:

Usage

dragon_feedback(runs_dir = dragon_runs_dir(), label = NULL)

Arguments

runs_dir

Runs directory holding feedback/feedback.jsonl.

label

Optional filter: only feedback given to this run id or backend model.

Value

A list with records (a data frame of every feedback event), sft (dataset or NULL), and pairs (dataset or NULL).

Details

  • sft: a conversations dataset (dragon_conversations()) of replies the user liked or edited, each with the turns that led to it. Edited text replaces the model's reply.

  • pairs: a preference dataset (dragon_map_pairs()) for prompts that received both a liked (or edited) reply and a disliked one.

Both are written as JSONL under feedback/ so runs trained on them stay reproducible through dragon_code().

Examples

if (interactive()) {
fb <- dragon_feedback()
fb$records
better <- dragon_train(fb$sft, dpo, wait = TRUE)       # continue from the run people chatted with
dpo2 <- dragon_prefer(fb$pairs, better, wait = TRUE)
}