Submit a human evaluation or annotation score
curl --request POST \
--url https://api.galtea.ai/evaluations/{id}/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"score": 0.95,
"reason": "Evaluation reason"
}
'import requests
url = "https://api.galtea.ai/evaluations/{id}/submit"
payload = {
"score": 0.95,
"reason": "Evaluation reason"
}
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({score: 0.95, reason: 'Evaluation reason'})
};
fetch('https://api.galtea.ai/evaluations/{id}/submit', 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/{id}/submit",
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([
'score' => 0.95,
'reason' => 'Evaluation reason'
]),
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/{id}/submit"
payload := strings.NewReader("{\n \"score\": 0.95,\n \"reason\": \"Evaluation reason\"\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/{id}/submit")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"score\": 0.95,\n \"reason\": \"Evaluation reason\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.galtea.ai/evaluations/{id}/submit")
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 \"score\": 0.95,\n \"reason\": \"Evaluation reason\"\n}"
response = http.request(request)
puts response.read_body{
"id": "eval_123",
"metricId": "metric_123",
"sessionId": "session_123",
"productId": "product_123",
"userId": "user_123",
"status": "SUCCESS",
"inferenceResultId": "ir_123",
"score": 0.95,
"reason": "High quality response",
"error": "<string>",
"canRetry": false,
"creditsUsed": 1,
"judgeInputTokens": 4100,
"judgeOutputTokens": 16800,
"judgeReasoningTokens": 12400,
"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,
"runId": "<string>",
"deletedAt": "2023-11-07T05:31:56Z",
"evaluatedAt": "2023-11-07T05:31:56Z",
"metricLegacyAt": "2023-11-07T05:31:56Z",
"passed": true,
"metricPassThreshold": 0.5,
"metricDisabledAt": "2023-11-07T05:31:56Z",
"metricExcludedFromAnalyticsAt": "2023-11-07T05:31:56Z",
"metricExcludedByUserId": "<string>",
"testCaseLegacyAt": "2023-11-07T05:31:56Z",
"scoreBreakdown": {
"version": 123,
"model": "<string>",
"type": "yes_no",
"value": 123,
"confidence": 123,
"pYes": 0.5,
"goodAnswer": "yes",
"probabilities": {},
"levelScores": [
123
],
"doesNotApply": true
},
"confidence": 0.9,
"longInput": true,
"createdAt": "2023-11-07T05:31:56Z"
}{
"error": "Error type",
"message": "Error message description"
}{
"error": "Error type",
"message": "Error message description"
}{
"error": "Error type",
"message": "Error message description"
}{
"error": "Error type",
"message": "Error message description"
}Submit a human evaluation or annotation score
Submit a score and optional reason. For HUMAN_EVALUATION metrics, enforces user group permissions and updates both score sets. For PENDING_HUMAN evaluations, also sets status to SUCCESS. For other metrics, works as an annotation — writes only humanScore/humanReason/humanEvaluatorFinishedAt, leaving AI score/reason and status untouched. Works on any evaluation status. See Evaluations.
POST
/
evaluations
/
{id}
/
submit
Submit a human evaluation or annotation score
curl --request POST \
--url https://api.galtea.ai/evaluations/{id}/submit \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"score": 0.95,
"reason": "Evaluation reason"
}
'import requests
url = "https://api.galtea.ai/evaluations/{id}/submit"
payload = {
"score": 0.95,
"reason": "Evaluation reason"
}
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({score: 0.95, reason: 'Evaluation reason'})
};
fetch('https://api.galtea.ai/evaluations/{id}/submit', 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/{id}/submit",
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([
'score' => 0.95,
'reason' => 'Evaluation reason'
]),
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/{id}/submit"
payload := strings.NewReader("{\n \"score\": 0.95,\n \"reason\": \"Evaluation reason\"\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/{id}/submit")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"score\": 0.95,\n \"reason\": \"Evaluation reason\"\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.galtea.ai/evaluations/{id}/submit")
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 \"score\": 0.95,\n \"reason\": \"Evaluation reason\"\n}"
response = http.request(request)
puts response.read_body{
"id": "eval_123",
"metricId": "metric_123",
"sessionId": "session_123",
"productId": "product_123",
"userId": "user_123",
"status": "SUCCESS",
"inferenceResultId": "ir_123",
"score": 0.95,
"reason": "High quality response",
"error": "<string>",
"canRetry": false,
"creditsUsed": 1,
"judgeInputTokens": 4100,
"judgeOutputTokens": 16800,
"judgeReasoningTokens": 12400,
"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,
"runId": "<string>",
"deletedAt": "2023-11-07T05:31:56Z",
"evaluatedAt": "2023-11-07T05:31:56Z",
"metricLegacyAt": "2023-11-07T05:31:56Z",
"passed": true,
"metricPassThreshold": 0.5,
"metricDisabledAt": "2023-11-07T05:31:56Z",
"metricExcludedFromAnalyticsAt": "2023-11-07T05:31:56Z",
"metricExcludedByUserId": "<string>",
"testCaseLegacyAt": "2023-11-07T05:31:56Z",
"scoreBreakdown": {
"version": 123,
"model": "<string>",
"type": "yes_no",
"value": 123,
"confidence": 123,
"pYes": 0.5,
"goodAnswer": "yes",
"probabilities": {},
"levelScores": [
123
],
"doesNotApply": true
},
"confidence": 0.9,
"longInput": true,
"createdAt": "2023-11-07T05:31:56Z"
}{
"error": "Error type",
"message": "Error message description"
}{
"error": "Error type",
"message": "Error message description"
}{
"error": "Error type",
"message": "Error message description"
}{
"error": "Error type",
"message": "Error message description"
}Authorizations
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-....
Path Parameters
Evaluation ID
Example:
"eval_123"
Body
application/json
Response
Evaluation submitted successfully
Example:
"eval_123"
Example:
"metric_123"
Example:
"session_123"
Product the evaluated session belongs to
Example:
"product_123"
Example:
"user_123"
Available options:
PENDING, PENDING_HUMAN, SUCCESS, FAILED, SKIPPED, CANCELLED, OUTDATED Example:
"SUCCESS"
Example:
"ir_123"
Example:
0.95
Example:
"High quality response"
Example:
false
Example:
1
Tokens the judge received, prompt plus session content
Example:
4100
Tokens the judge produced, reasoning included
Example:
16800
Reasoning tokens, a subset of judgeOutputTokens
Example:
12400
Example:
"1.0.0"
User ID of the human evaluator
Human-provided annotation score
Human-provided annotation reason
Timestamp when human evaluation was submitted
Conversation turns that failed
ID of the monitor that dispatched this evaluation
Session turn count when the monitor scored it
Sampling percentage in effect when the monitor scored this session
ID of the run that launched this evaluation
Whether the reported score (the reviewer's when set, else the judge's) reaches the metric's pass threshold. Null when the evaluation has no reported score, is outdated or deleted, is a long classifier input, or its metric is not loaded.
The pass threshold that decides passed: the metric's, copied onto the evaluation when it was created.
Required range:
0 <= x <= 1CLASSIFIER only: what the classifier answered; null for every other source.
Show child attributes
Show child attributes
CLASSIFIER only: how sure the classifier was, from 0 to 1; null for every other source. Values do not compare across question types.
Required range:
0 <= x <= 1Example:
0.9
True for a CLASSIFIER evaluation whose input ran past what the classifier scores reliably (CLASSIFIER_RELIABLE_INPUT_TOKENS judge input tokens) and that no reviewer has scored; false for every other evaluation.