Skip to main content
POST
/
prompts
/
{promptId}
/
evaluators
Create an evaluator
curl --request POST \
  --url https://api.adaline.ai/v2/prompts/{promptId}/evaluators \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "projectId": "<string>",
  "title": "<string>",
  "datasetId": "<string>",
  "config": {
    "type": "llm-as-a-judge",
    "group": "ai-powered",
    "value": "<string>"
  }
}
'
{
  "id": "<string>",
  "promptId": "<string>",
  "title": "<string>",
  "datasetId": "<string>",
  "config": {
    "type": "llm-as-a-judge",
    "group": "ai-powered",
    "value": "<string>"
  },
  "status": "active",
  "createdAt": 17450965800000,
  "updatedAt": 17450965800000
}

Authorizations

​
Authorization
string
header
required

Workspace API key. Pass as Authorization: Bearer <key>.

Path Parameters

​
promptId
string
required

Unique identifier for an entity, between 20 and 80 characters.

Required string length: 20 - 80

Body

application/json
​
projectId
string
required

Unique identifier for an entity, between 20 and 80 characters.

Required string length: 20 - 80
​
title
string
required

Display title for an evaluator, up to 200 characters.

Required string length: 1 - 200
​
datasetId
string
required

Unique identifier for an entity, between 20 and 80 characters.

Required string length: 20 - 80
​
config
LLM as a Judge · object
required

Evaluator configuration, discriminated by type.

Response

Evaluator created.

An evaluator configuration for running evaluations on datasets.

​
id
string
required

Unique identifier for an entity, between 20 and 80 characters.

Required string length: 20 - 80
​
promptId
string
required

Unique identifier for an entity, between 20 and 80 characters.

Required string length: 20 - 80
​
title
string
required

Display title for an evaluator, up to 200 characters.

Required string length: 1 - 200
​
datasetId
string
required

Unique identifier for an entity, between 20 and 80 characters.

Required string length: 20 - 80
​
config
LLM as a Judge · object
required

Evaluator configuration, discriminated by type.

​
status
enum<string>
required

Evaluator lifecycle status.

Available options:
active,
archived
​
createdAt
integer<int64>
required

Unix timestamp in milliseconds.

Required range: 1672511400000 <= x <= 33229420200000
​
updatedAt
integer<int64>
required

Unix timestamp in milliseconds.

Required range: 1672511400000 <= x <= 33229420200000