feat: describegpt add controlled vocabulary support for tags
#3122
Conversation
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
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds controlled vocabulary support for tag inference in the describegpt command. It introduces two new command-line options: --num-tags to limit the maximum number of tags generated (default: 10), and --tag-vocab to provide a CSV file containing a controlled vocabulary of allowed tags. When no vocabulary file is provided, the model continues to use free-form tag generation as before.
Key changes:
- Added
--num-tagsand--tag-vocabcommand-line options with appropriate documentation - Modified prompt generation to incorporate tag vocabulary constraints when provided
- Updated the default prompt template to use the new
{NUM_TAGS}and{TAG_VOCAB}variables - Version bump from 4.1.0 to 5.0.0 reflecting the new feature
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| src/cmd/describegpt.rs | Added two new flags (flag_num_tags, flag_tag_vocab) to the Args struct, implemented tag vocabulary file validation and reading, and integrated the vocabulary content into prompt generation via template variable replacement |
| resources/describegpt_defaults.toml | Updated metadata (name/author casing, version bump to 5.0.0), added {TAG_VOCAB} variable documentation, modified tags_prompt to use {NUM_TAGS} variable and include {TAG_VOCAB} content for controlled vocabulary guidance |
- call it Attribution instead of Footnote - make sure all describegpt output has detailed attribution metadata
- simplified tag vocab format; added examples in usage text - factor in Copilot recommendations re conditional prompt_file_kind generation - more detailed Attribution metadata
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
…view Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
…ility/parseability [skip ci]
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
No description provided.