Skip to main content
POST
/
metrics
Create metric
curl --request POST \
  --url https://api.galtea.ai/metrics \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "id": "metric_123",
  "parentMetricId": "metric_122",
  "organizationId": "org_123",
  "userId": "user_123",
  "name": "Accuracy",
  "evaluationParams": [
    "input",
    "actualOutput",
    "expectedOutput"
  ],
  "source": "PARTIAL_PROMPT",
  "judgePrompt": "Evaluate the accuracy of the response",
  "tags": [
    "accuracy",
    "quality"
  ],
  "description": "Measures the accuracy of responses",
  "documentationUrl": "https://docs.example.com/metrics/accuracy",
  "evaluatorModelName": "GPT-4",
  "areEvalParamsTop": true,
  "specificationIds": [
    "spec_123"
  ],
  "userGroupIds": [
    "ug_123"
  ],
  "createdAt": "2023-11-07T05:31:56Z",
  "legacyAt": "2023-11-07T05:31:56Z",
  "disabledAt": "2023-11-07T05:31:56Z"
}
'
import requests

url = "https://api.galtea.ai/metrics"

payload = {
    "id": "metric_123",
    "parentMetricId": "metric_122",
    "organizationId": "org_123",
    "userId": "user_123",
    "name": "Accuracy",
    "evaluationParams": ["input", "actualOutput", "expectedOutput"],
    "source": "PARTIAL_PROMPT",
    "judgePrompt": "Evaluate the accuracy of the response",
    "tags": ["accuracy", "quality"],
    "description": "Measures the accuracy of responses",
    "documentationUrl": "https://docs.example.com/metrics/accuracy",
    "evaluatorModelName": "GPT-4",
    "areEvalParamsTop": True,
    "specificationIds": ["spec_123"],
    "userGroupIds": ["ug_123"],
    "createdAt": "2023-11-07T05:31:56Z",
    "legacyAt": "2023-11-07T05:31:56Z",
    "disabledAt": "2023-11-07T05:31:56Z"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    id: 'metric_123',
    parentMetricId: 'metric_122',
    organizationId: 'org_123',
    userId: 'user_123',
    name: 'Accuracy',
    evaluationParams: ['input', 'actualOutput', 'expectedOutput'],
    source: 'PARTIAL_PROMPT',
    judgePrompt: 'Evaluate the accuracy of the response',
    tags: ['accuracy', 'quality'],
    description: 'Measures the accuracy of responses',
    documentationUrl: 'https://docs.example.com/metrics/accuracy',
    evaluatorModelName: 'GPT-4',
    areEvalParamsTop: true,
    specificationIds: ['spec_123'],
    userGroupIds: ['ug_123'],
    createdAt: '2023-11-07T05:31:56Z',
    legacyAt: '2023-11-07T05:31:56Z',
    disabledAt: '2023-11-07T05:31:56Z'
  })
};

fetch('https://api.galtea.ai/metrics', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));
<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.galtea.ai/metrics",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'id' => 'metric_123',
    'parentMetricId' => 'metric_122',
    'organizationId' => 'org_123',
    'userId' => 'user_123',
    'name' => 'Accuracy',
    'evaluationParams' => [
        'input',
        'actualOutput',
        'expectedOutput'
    ],
    'source' => 'PARTIAL_PROMPT',
    'judgePrompt' => 'Evaluate the accuracy of the response',
    'tags' => [
        'accuracy',
        'quality'
    ],
    'description' => 'Measures the accuracy of responses',
    'documentationUrl' => 'https://docs.example.com/metrics/accuracy',
    'evaluatorModelName' => 'GPT-4',
    'areEvalParamsTop' => true,
    'specificationIds' => [
        'spec_123'
    ],
    'userGroupIds' => [
        'ug_123'
    ],
    'createdAt' => '2023-11-07T05:31:56Z',
    'legacyAt' => '2023-11-07T05:31:56Z',
    'disabledAt' => '2023-11-07T05:31:56Z'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.galtea.ai/metrics"

	payload := strings.NewReader("{\n  \"id\": \"metric_123\",\n  \"parentMetricId\": \"metric_122\",\n  \"organizationId\": \"org_123\",\n  \"userId\": \"user_123\",\n  \"name\": \"Accuracy\",\n  \"evaluationParams\": [\n    \"input\",\n    \"actualOutput\",\n    \"expectedOutput\"\n  ],\n  \"source\": \"PARTIAL_PROMPT\",\n  \"judgePrompt\": \"Evaluate the accuracy of the response\",\n  \"tags\": [\n    \"accuracy\",\n    \"quality\"\n  ],\n  \"description\": \"Measures the accuracy of responses\",\n  \"documentationUrl\": \"https://docs.example.com/metrics/accuracy\",\n  \"evaluatorModelName\": \"GPT-4\",\n  \"areEvalParamsTop\": true,\n  \"specificationIds\": [\n    \"spec_123\"\n  ],\n  \"userGroupIds\": [\n    \"ug_123\"\n  ],\n  \"createdAt\": \"2023-11-07T05:31:56Z\",\n  \"legacyAt\": \"2023-11-07T05:31:56Z\",\n  \"disabledAt\": \"2023-11-07T05:31:56Z\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
HttpResponse<String> response = Unirest.post("https://api.galtea.ai/metrics")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"id\": \"metric_123\",\n  \"parentMetricId\": \"metric_122\",\n  \"organizationId\": \"org_123\",\n  \"userId\": \"user_123\",\n  \"name\": \"Accuracy\",\n  \"evaluationParams\": [\n    \"input\",\n    \"actualOutput\",\n    \"expectedOutput\"\n  ],\n  \"source\": \"PARTIAL_PROMPT\",\n  \"judgePrompt\": \"Evaluate the accuracy of the response\",\n  \"tags\": [\n    \"accuracy\",\n    \"quality\"\n  ],\n  \"description\": \"Measures the accuracy of responses\",\n  \"documentationUrl\": \"https://docs.example.com/metrics/accuracy\",\n  \"evaluatorModelName\": \"GPT-4\",\n  \"areEvalParamsTop\": true,\n  \"specificationIds\": [\n    \"spec_123\"\n  ],\n  \"userGroupIds\": [\n    \"ug_123\"\n  ],\n  \"createdAt\": \"2023-11-07T05:31:56Z\",\n  \"legacyAt\": \"2023-11-07T05:31:56Z\",\n  \"disabledAt\": \"2023-11-07T05:31:56Z\"\n}")
  .asString();
require 'uri'
require 'net/http'

url = URI("https://api.galtea.ai/metrics")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"id\": \"metric_123\",\n  \"parentMetricId\": \"metric_122\",\n  \"organizationId\": \"org_123\",\n  \"userId\": \"user_123\",\n  \"name\": \"Accuracy\",\n  \"evaluationParams\": [\n    \"input\",\n    \"actualOutput\",\n    \"expectedOutput\"\n  ],\n  \"source\": \"PARTIAL_PROMPT\",\n  \"judgePrompt\": \"Evaluate the accuracy of the response\",\n  \"tags\": [\n    \"accuracy\",\n    \"quality\"\n  ],\n  \"description\": \"Measures the accuracy of responses\",\n  \"documentationUrl\": \"https://docs.example.com/metrics/accuracy\",\n  \"evaluatorModelName\": \"GPT-4\",\n  \"areEvalParamsTop\": true,\n  \"specificationIds\": [\n    \"spec_123\"\n  ],\n  \"userGroupIds\": [\n    \"ug_123\"\n  ],\n  \"createdAt\": \"2023-11-07T05:31:56Z\",\n  \"legacyAt\": \"2023-11-07T05:31:56Z\",\n  \"disabledAt\": \"2023-11-07T05:31:56Z\"\n}"

response = http.request(request)
puts response.read_body
{
  "id": "metric_123",
  "metricGroupId": "metric_123",
  "parentMetricId": "metric_122",
  "organizationId": "org_123",
  "userId": "user_123",
  "name": "Accuracy",
  "evaluationParams": [
    "input",
    "actualOutput",
    "expectedOutput"
  ],
  "source": "PARTIAL_PROMPT",
  "judgePrompt": "Evaluate the accuracy of the response",
  "tags": [
    "accuracy",
    "quality"
  ],
  "description": "Measures the accuracy of responses",
  "documentationUrl": "https://docs.example.com/metrics/accuracy",
  "evaluatorModelName": "GPT-4",
  "areEvalParamsTop": true,
  "isBeingOptimized": true,
  "specificationIds": [
    "spec_123"
  ],
  "userGroupIds": [
    "ug_123"
  ],
  "createdAt": "2023-11-07T05:31:56Z",
  "legacyAt": "2023-11-07T05:31:56Z",
  "disabledAt": "2023-11-07T05:31:56Z"
}
{
  "error": "Error type",
  "message": "Error message description"
}
{
  "error": "Error type",
  "message": "Error message description"
}

Authorizations

​
Authorization
string
header
required

API key authorization. Pass your API key in the Authorization header as a Bearer token. Both new (gsk_*) and legacy (gsk-) API keys are accepted, e.g. Authorization: Bearer gsk_... or Authorization: Bearer gsk-....

Body

application/json
​
id
string
Example:

"metric_123"

​
parentMetricId
string | null

Id of the direct parent metric. On create, providing this value turns the new metric into a revision: it joins the parent's family and (if the parent is active) flips the parent to legacy. Omit or null to create a root metric in a fresh group. On responses, this is the recorded parent edge (null for roots).

Example:

"metric_122"

​
organizationId
string | null
Example:

"org_123"

​
userId
string | null
Example:

"user_123"

​
name
string
Example:

"Accuracy"

​
evaluationParams
string[]

Ordered list of inference-result fields the evaluator needs (e.g. input, actualOutput, expectedOutput, retrievalContext). Determines which data the evaluation engine extracts from each inference result.

Example:
["input", "actualOutput", "expectedOutput"]
​
source
enum<string> | null

Evaluation method for the metric. FULL_PROMPT is deprecated for creation — POST /metrics rejects it with a 400. Use PARTIAL_PROMPT for new AI Evaluation metrics. The value remains in the enum because existing FULL_PROMPT metrics are still returned by reads and filters.

Available options:
SELF_HOSTED,
FULL_PROMPT,
PARTIAL_PROMPT,
HUMAN_EVALUATION,
GEVAL,
DEEPEVAL,
DETERMINISTIC
Example:

"PARTIAL_PROMPT"

​
judgePrompt
string | null
Example:

"Evaluate the accuracy of the response"

​
tags
string[]
Example:
["accuracy", "quality"]
​
description
string | null
Example:

"Measures the accuracy of responses"

​
documentationUrl
string | null
Example:

"https://docs.example.com/metrics/accuracy"

​
evaluatorModelName
string | null
Example:

"GPT-4"

​
areEvalParamsTop
boolean | null

When true, evaluationParams are injected at the top level of the evaluator prompt instead of nested inside the conversation context.

​
specificationIds
string[]
Example:
["spec_123"]
​
userGroupIds
string[]
Example:
["ug_123"]
​
createdAt
string<date-time>
​
legacyAt
string<date-time> | null
​
disabledAt
string<date-time> | null

Response

Metric created successfully

​
id
string
Example:

"metric_123"

​
metricGroupId
string
read-only

Identifier shared by every metric in the same revision family. Server-managed — derived from parentMetricId on create (or generated for roots). Cannot be set by the caller.

Example:

"metric_123"

​
parentMetricId
string | null

Id of the direct parent metric. On create, providing this value turns the new metric into a revision: it joins the parent's family and (if the parent is active) flips the parent to legacy. Omit or null to create a root metric in a fresh group. On responses, this is the recorded parent edge (null for roots).

Example:

"metric_122"

​
organizationId
string | null
Example:

"org_123"

​
userId
string | null
Example:

"user_123"

​
name
string
Example:

"Accuracy"

​
evaluationParams
string[]

Ordered list of inference-result fields the evaluator needs (e.g. input, actualOutput, expectedOutput, retrievalContext). Determines which data the evaluation engine extracts from each inference result.

Example:
["input", "actualOutput", "expectedOutput"]
​
source
enum<string> | null

Evaluation method for the metric. FULL_PROMPT is deprecated for creation — POST /metrics rejects it with a 400. Use PARTIAL_PROMPT for new AI Evaluation metrics. The value remains in the enum because existing FULL_PROMPT metrics are still returned by reads and filters.

Available options:
SELF_HOSTED,
FULL_PROMPT,
PARTIAL_PROMPT,
HUMAN_EVALUATION,
GEVAL,
DEEPEVAL,
DETERMINISTIC
Example:

"PARTIAL_PROMPT"

​
judgePrompt
string | null
Example:

"Evaluate the accuracy of the response"

​
tags
string[]
Example:
["accuracy", "quality"]
​
description
string | null
Example:

"Measures the accuracy of responses"

​
documentationUrl
string | null
Example:

"https://docs.example.com/metrics/accuracy"

​
evaluatorModelName
string | null
Example:

"GPT-4"

​
areEvalParamsTop
boolean | null

When true, evaluationParams are injected at the top level of the evaluator prompt instead of nested inside the conversation context.

​
isBeingOptimized
boolean
read-only

Whether the metric is currently being optimized.

​
specificationIds
string[]
Example:
["spec_123"]
​
userGroupIds
string[]
Example:
["ug_123"]
​
createdAt
string<date-time>
​
legacyAt
string<date-time> | null
​
disabledAt
string<date-time> | null