Create evaluations for a single inference result

Create evaluations for a specific turn in a conversation. This is useful for production monitoring where you want to evaluate turn-by-turn performance. See Evaluations.

POST /evaluations/fromInferenceResult

Create evaluations for a single inference result

cURL

curl --request POST \
  --url https://api.galtea.ai/evaluations/fromInferenceResult \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "inferenceResultId": "ir_123",
  "metrics": [
    {
      "id": "id_123",
      "name": "Example Name",
      "score": 0.95
    }
  ],
  "specificationIds": [
    "<string>"
  ]
}
'

import requests

url = "https://api.galtea.ai/evaluations/fromInferenceResult"

payload = {
    "inferenceResultId": "ir_123",
    "metrics": [
        {
            "id": "id_123",
            "name": "Example Name",
            "score": 0.95
        }
    ],
    "specificationIds": ["<string>"]
}
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({
    inferenceResultId: 'ir_123',
    metrics: [{id: 'id_123', name: 'Example Name', score: 0.95}],
    specificationIds: ['<string>']
  })
};

fetch('https://api.galtea.ai/evaluations/fromInferenceResult', 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/evaluations/fromInferenceResult",
  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([
    'inferenceResultId' => 'ir_123',
    'metrics' => [
        [
                'id' => 'id_123',
                'name' => 'Example Name',
                'score' => 0.95
        ]
    ],
    'specificationIds' => [
        '<string>'
    ]
  ]),
  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/evaluations/fromInferenceResult"

	payload := strings.NewReader("{\n  \"inferenceResultId\": \"ir_123\",\n  \"metrics\": [\n    {\n      \"id\": \"id_123\",\n      \"name\": \"Example Name\",\n      \"score\": 0.95\n    }\n  ],\n  \"specificationIds\": [\n    \"<string>\"\n  ]\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/evaluations/fromInferenceResult")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"inferenceResultId\": \"ir_123\",\n  \"metrics\": [\n    {\n      \"id\": \"id_123\",\n      \"name\": \"Example Name\",\n      \"score\": 0.95\n    }\n  ],\n  \"specificationIds\": [\n    \"<string>\"\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

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

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  \"inferenceResultId\": \"ir_123\",\n  \"metrics\": [\n    {\n      \"id\": \"id_123\",\n      \"name\": \"Example Name\",\n      \"score\": 0.95\n    }\n  ],\n  \"specificationIds\": [\n    \"<string>\"\n  ]\n}"

response = http.request(request)
puts response.read_body

201

[
  {
    "id": "eval_123",
    "metricId": "metric_123",
    "sessionId": "session_123",
    "userId": "user_123",
    "status": "SUCCESS",
    "inferenceResultId": "ir_123",
    "score": 0.95,
    "reason": "High quality response",
    "error": "<string>",
    "canRetry": false,
    "creditsUsed": 1,
    "conversationSimulatorVersion": "1.0.0",
    "humanEvaluatorId": "<string>",
    "humanEvaluatorStartedAt": "2023-11-07T05:31:56Z",
    "humanScore": 123,
    "humanReason": "<string>",
    "humanEvaluatorFinishedAt": "2023-11-07T05:31:56Z",
    "failedTurns": [
      "<string>"
    ],
    "monitorId": "<string>",
    "monitorSettledAtTurn": 123,
    "monitorSamplingPercentage": 123,
    "deletedAt": "2023-11-07T05:31:56Z",
    "evaluatedAt": "2023-11-07T05:31:56Z",
    "metricLegacyAt": "2023-11-07T05:31:56Z",
    "metricDisabledAt": "2023-11-07T05:31:56Z",
    "testCaseLegacyAt": "2023-11-07T05:31:56Z",
    "createdAt": "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

inferenceResultId · string · required

The ID of the inference result (turn) to evaluate

Example:

"ir_123"

metrics · object[]

Metrics to evaluate. Optional if specificationIds is provided or the product has specifications with linked metrics.

Show child attributes

specificationIds · string[]

Specification IDs whose linked metrics will be evaluated. Can be combined with metrics; the API merges and deduplicates.

Response

201

application/json

Evaluations created successfully

id · string · required

Example:

"eval_123"

metricId · string · required

Example:

"metric_123"

sessionId · string · required

Example:

"session_123"

userId · string | null · required

Example:

"user_123"

status · enum<string> · required

Available options: PENDING, PENDING_HUMAN, SUCCESS, FAILED, SKIPPED, CANCELLED

Example:

"SUCCESS"

inferenceResultId · string | null · required

Example:

"ir_123"

score · number | null · required

Example:

0.95

reason · string | null · required

Example:

"High quality response"

error · string | null · required

canRetry · boolean | null · required

Example:

false

creditsUsed · integer | null · required

Example:

1

conversationSimulatorVersion · string | null · required

Example:

"1.0.0"

humanEvaluatorId · string | null · required

User ID of the human evaluator

humanEvaluatorStartedAt · string<date-time> | null · required

humanScore · number | null · required

Human-provided annotation score

humanReason · string | null · required

Human-provided annotation reason

humanEvaluatorFinishedAt · string<date-time> | null · required

Timestamp when human evaluation was submitted

failedTurns · string[] · required

Conversation turns that failed

monitorId · string | null · required

ID of the monitor that dispatched this evaluation

monitorSettledAtTurn · integer | null · required

Session turn count when the monitor scored it

monitorSamplingPercentage · number | null · required

Sampling percentage in effect when the monitor scored this session

deletedAt · string<date-time> | null · required

evaluatedAt · string<date-time> | null · required

metricLegacyAt · string<date-time> | null · required

metricDisabledAt · string<date-time> | null · required

testCaseLegacyAt · string<date-time> | null · required

createdAt · string<date-time>