devwithjevNatural-Language Flight Destination Search in SQL
Syed registered the Jev model from @typesafeai as a UDF on a DuckDB flights database to query 218 flight destinations in natural language. Changing the query sentence re-ranks destinations by meaning.
Syed@smhumair𝕏
Registered Jev model from @typesafeai as a UDF on a flights @duckdb database. Now I can query a table in natural language, inside SQL: WHERE jev(destination, 'a beach that also has mountains') Dataset has 218 flight destinations. I just change the sentence and it re-ranks by meaning: → "beach or tropical" → "ski destination" → "beach and with nearby mountains" No embeddings. No vector DB. No pipel
Example queries include “a beach that also has mountains,” “beach or tropical,” “ski destination,” and “beach and with nearby mountains.”
Also filed under Tools & apps
- Meta Ad Analysis Chrome Extension
The Chrome extension analyzes ads from Meta’s Ads Library using JEV (typesafe/jev-1.13) via OpenRouter, surfacing result potential, angle, hook, and niche. The user’s key stays in their browser.
- Jev Plugin for the PI Harness
The repository provides a Jev plugin for the PI Harness.
- Jev Suggestion Plugin for Hermes
The repository is a Hermes plugin named `jev-suggest`.
- OpenRouter Draft Evaluator
This local prototype evaluates and compares drafts generated with OpenRouter using Jev.