feat: describegpt - major refactor
#3143
Merged
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
Collaborator
jqnatividad
commented
Dec 1, 2025
- made data dictionary generation "neuro-symbolic"
- more robust Polars SQL generation
- more configurable parameters for dictionary and tags generation
- more verbose JSON output
as LLMs sometime start comments in the middle of the line (which is actually OK for readability)
- also add SQL comment prefix to Attribution when generating SQL
…dictionary and tags
Contributor
There was a problem hiding this comment.
Pull request overview
This PR refactors the describegpt command to use a "neuro-symbolic" approach for data dictionary generation. The core improvement separates code-based dictionary generation (statistics, enumerations, examples) from LLM-generated content (labels and descriptions), making the system more robust and configurable.
Key Changes:
- Introduced code-based dictionary generation that parses stats/frequency CSVs and generates structured entries
- Added configurable parameters:
--num-examplesand--truncate-strfor controlling dictionary output - Implemented more verbose JSON output with metadata fields (enum_threshold, num_examples, truncate_str)
Reviewed changes
Copilot reviewed 5 out of 5 changed files in this pull request and generated 5 comments.
Show a summary per file
| File | Description |
|---|---|
| src/cmd/sqlp.rs | Enhanced SQL comment regex to handle whitespace-prefixed comments |
| src/cmd/describegpt.rs | Major refactor implementing neuro-symbolic dictionary generation with new parsing functions and data structures |
| resources/describegpt_defaults.toml | Simplified dictionary prompt to only request labels/descriptions, updated Polars SQL guidance |
| docs/nyc311-describegpt.md | Updated example output showing new dictionary format with additional metadata columns |
| docs/nyc311-describegpt.json | Updated JSON output structure with new field format and attribution metadata |
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
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.