Skip to content

Conversation

@jqnatividad
Copy link
Collaborator

previously, it was hardcoded to top 10, now its configurable and defaults to top 50.

The default system prompt now has a {TOP_N} sentinel value that is replaced with the specified --enum-threshold

previously, it was hardcoded to top 10, now its configurable and defaults to top 50
@jqnatividad jqnatividad requested a review from Copilot August 30, 2025 13:37
Copy link
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR adds a configurable enum threshold parameter to the describegpt command, allowing users to control how many top frequent values are included in frequency distributions before other values are grouped into an "Other" category.

  • Adds --enum-threshold flag with default value of 50 (previously hardcoded to 10)
  • Updates system prompt template to use dynamic {TOP_N} placeholder replacement
  • Modifies cache key generation to include the enum threshold for proper cache invalidation

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File Description
src/cmd/describegpt.rs Adds enum-threshold parameter, updates frequency command calls, and modifies cache key generation
resources/describegpt_defaults.json Updates system prompt template to use dynamic TOP_N placeholder instead of hardcoded "10"

@jqnatividad jqnatividad merged commit 5700deb into master Aug 30, 2025
13 of 14 checks passed
@jqnatividad jqnatividad deleted the describegpt-more-configuable-data-analysis branch August 30, 2025 13:47
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants