Skip to content

feat: adds extra parameters for iterating on docs

Eduardo Bonet requested to merge ebonet/add-limit-to-duochat into main

What does this merge request do and why?

duo chat eval lacks a few of useful parameters when debugging or iterating. This MR adds rate_limit, dataset parameters (limit, offset, example), and experiment_prefix to the docs evaluation

How to set up and validate locally

poetry run eli5 duo-chat evaluate docs --rate-limit=2 --limit=10

Merge request checklist

  • Tests added for new functionality. If not, please raise an issue to follow up.
  • Documentation added/updated, if needed.

Merge request reports