A DuckDB extension for row classification
DuckDB extension that labels rows in CSV, Parquet or DuckDB tables with Jev, reported at about ten seconds per thousand rows.
This summary is based on how curated lists describe the project; its README was not available to review.
Overview
An X post by Hamilton Ulmer describing a DuckDB extension that classifies rows in any CSV, Parquet or DuckDB table using Jev from SQL.
The post reports about ten seconds for a thousand rows and says the ergonomics beat building a bespoke classifier. It suits analysts who want to tag or clean data without leaving their query tool.
What the decision model decides
| Type | Question | Answers |
|---|---|---|
| Choice | Which label fits this row?(inferred) | — |
How it works
- Load a table in DuckDB
- Call the extension's classify function in SQL
- Jev returns a label per row
- Use labels in further queries
Strengths
- Classification stays inside SQL
- Reported ~10 s per 1,000 rows
Caveats
- Known only from a social post; repository not linked in the listing
- Requires TypeSafe access
At a glance
- Type
- Discussion
- Status
- prototype
- Runtime
- DuckDB extension
Use cases and integrations
How curated lists describe it
X: classifies rows in any CSV, Parquet, or DuckDB table with Jev, reporting about ten seconds for a thousand rows and better ergonomics than a bespoke classifier.
yibie/awesome-jevDuckDB extension that classifies rows in CSV, Parquet, or DuckDB tables with Jev, about 10 seconds per 1,000 rows.
hellogumbo/awesome-jev
Frequently asked questions
What does it do?
Lets you classify table rows with Jev from DuckDB SQL.
How fast is it?
The post reports about ten seconds per thousand rows.
Where is it described?
https://x.com/hamiltonulmer/status/2100370557405667768
Related projects
dbt package whose macros run Jev Choice, Noul and Score over SQL values in DuckDB and ClickHouse models.
ProjectbetaSQL (Jinja)DuckDB extension that asks Jev about every row in SQL and returns answers as ENUM, DOUBLE or STRUCT columns.
PluginbetaC++dbt package and Terraform module adding jev_noul, jev_choice, jev_score and jev_ask SQL functions to Snowflake.
LibrarybetaSQLPostgreSQL extension with jev(), jev_prob, jev_choice and jev_score to filter, rank and classify rows by plain-language conditions.
PluginbetaCCLI that scans tabular, structured and text files or databases and asks Jev which fields look anomalous, building a review queue.
CLIbetaPythonDuckDB extension adding decide_probability, decide_choice and decide_score SQL functions backed by Jev or local open decision models.
PluginbetaC++