CalibratedDecisions.

Post · Search & RAG

jev() for PostgreSQL

Search a table in plain language, with no index and no embeddings.

Open x.com ↗
Zachi @iam_zachi

I think I just cooked something 🔥

jev(): a PostgreSQL extension that searches your whole database in natural language. No index, no embeddings, just one function.

WHERE jev(people, 'could work from home')
or
WHERE jev(people, 'name sounds european')

129 rows judged in ~1s

Video from the post

How builders describe it

The pg-jev author demos jev(), a PostgreSQL extension that filters table rows with natural-language conditions and no index or embeddings, judging 129 rows in about a second.
**I made a fuzzy sql function using jev. ** Ask your database: **WHERE jev(people, 'could work from home')** or **WHERE jev(people, 'name sounds european')** Tada, jev will search and judge the rows using your prompt.

The decision Jev makes

Rank candidates against a query, or answer whether a passage is relevant.

Where it fits

Search pipelines retrieve too much. These projects use Jev as a reranker or relevance check after the first search, so only useful results reach the user or the model. All 108 search & rag projects →

Related projects