Jev (TypeSafe)

Node catalog Artificial intelligence
On this page

Structured decisions: choices, scores and yes/no probabilities with Jev.

Usage and specifics

Choose a compatible engine and credential, then define the decision schema and input. Structured output must satisfy the contract expected by downstream nodes.

Technical type : jev. Runtime : nodulz.

Credentials and prerequisites

Create credentials in your nodulz instance’s Credentials area, then select them on the node. Availability depends on ownership and sharing. See the credentials guide for access and rotation.

Parameters

Names below are technical keys. Defaults are not a ready-to-run configuration: complete fields required by your operation. Paths containing [] describe list items; some fields depend on the selected mode.

Parameter Type Default Values / limits
credentialId string - -
model string "jev-latest" -
state string "{{ input }}" -
questions array [{"id":"result","type":"noul","instructions":"","criteria":""}] -
questions[].id string "result" -
questions[].type enum "noul" noul, choice, score
questions[].instructions string "" -
questions[].criteria string "" -

Initial configuration

Initial catalog configuration example, to adapt before running. Keep secrets in credentials.

json
{
  "model": "jev-latest",
  "state": "{{ input }}",
  "questions": [
    {
      "id": "result",
      "type": "noul",
      "instructions": "",
      "criteria": ""
    }
  ]
}

Verification

Test with representative data. Check node output in the inspector and logs, then use editor mapping for downstream fields. A trigger test with a simulated payload does not validate external service delivery.

See also : Expressions and data, Executions, Node catalog.