Semantic operators
Filter, classify and route text with typed JEV decisions. Use the workspace, HTTP API or SQL interface.
Operator referenceOPEN SOURCE · BUILT ON POSTGRESQL
A self-developing SQL database with JEV semantic operators and natural-language queries.
Apache 2.0 / PostgreSQL at the core
01 / FROM QUESTION TO QUERY
Ask in ordinary language. Inspect the generated query, correct the interpretation and rerun it from history.
“For each supplier, show the total quantity delivered, largest total first.”
SELECT
SUM("r0"."quantity") AS "result_1",
"r0"."supplier" AS "result_2"
FROM "deliveries" AS "r0"
GROUP BY "r0"."supplier"
ORDER BY SUM("r0"."quantity") DESC NULLS LAST| result_1 | result_2 |
|---|---|
| 36 | Birch |
| 30 | Aster |
| 8 | Cedar |
02 / A PLACE FOR EACH KIND OF WORK
Let JEV evaluate independent semantic questions together. Let PostgreSQL handle the relational work.
03 / MORE THAN A QUERY BOX
Connect existing data, turn meaning into typed evidence, and keep control of what changes.
Filter, classify and route text with typed JEV decisions. Use the workspace, HTTP API or SQL interface.
Operator referenceAttach authorized PostgreSQL tables and views. Query the source without copying every row into another database.
User guidePreview inserts, updates and deletes before committing. Extract typed entries from text with source evidence.
Text import guideUncertainty stays explicit.
VALUEUNKNOWNNOT_EVALUATED04 / BUILD WITH IT
Open source. Apache 2.0. Yours to inspect and extend.