Skip to main content
GET
/
evaluations
Get evaluations
curl --request GET \
  --url https://api.galtea.ai/evaluations \
  --header 'Authorization: Bearer <token>'
import requests

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

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)
const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.galtea.ai/evaluations', 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",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_ENCODING => "",
CURLOPT_MAXREDIRS => 10,
CURLOPT_TIMEOUT => 30,
CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
CURLOPT_CUSTOMREQUEST => "GET",
CURLOPT_HTTPHEADER => [
"Authorization: Bearer <token>"
],
]);

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

curl_close($curl);

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

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

func main() {

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

req, _ := http.NewRequest("GET", url, nil)

req.Header.Add("Authorization", "Bearer <token>")

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

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

fmt.Println(string(body))

}
HttpResponse<String> response = Unirest.get("https://api.galtea.ai/evaluations")
.header("Authorization", "Bearer <token>")
.asString();
require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body
[
  {
    "id": "eval_123",
    "metricId": "metric_123",
    "sessionId": "session_123",
    "userId": "user_123",
    "status": "SUCCESS",
    "testCaseId": "tc_123",
    "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>"
    ],
    "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-....

Query Parameters

ids
string[]

Filter by evaluation IDs

productIds
string[]

Filter by product IDs

sessionIds
string[]

Filter by session IDs

inferenceResultIds
string[]

Filter by inference result IDs (for single-turn evaluations)

metricIds
string[]

Filter by metric IDs

metricGroupIds
string[]

Filter by metric group IDs (matches all revisions of a metric)

testCaseIds
string[]

Filter by test case IDs

testIds
string[]

Filter by test IDs (include only). Use an empty string ("") to select evaluations without a test

excludeTestIds
string[]

Omit evaluations linked to the specified test IDs. Use an empty string ("") to omit evaluations without a test

versionIds
string[]

Filter by version IDs

specificationIds
string[]

Filter by specification IDs (returns evaluations whose metric is linked to any of the given specifications)

statuses
enum<string>[]

Filter by evaluation statuses

Available options:
PENDING,
PENDING_HUMAN,
SUCCESS,
FAILED,
SKIPPED,
CANCELLED
evaluationTypes
string[]

Filter by evaluation types

metricSources
string[]

Filter by metric sources

sort
string[]

Sort instructions (field and direction pairs)

canRetry
boolean

Filter evaluations that can be retried

augmentedTestCase
boolean

Filter evaluations by whether their test case is augmented

isProduction
boolean

Filter evaluations by the joined Session.isProduction flag. Prefer this over the legacy testIds/excludeTestIds empty-string trick.

humanEvaluatorId
string

Filter by human evaluator user ID

fromCreatedAt
string<date-time>

Filter evaluations created at or after this timestamp (ISO 8601 format)

toCreatedAt
string<date-time>

Filter evaluations created at or before this timestamp (ISO 8601 format)

limit
integer
default:10000

Maximum number of results

Required range: 0 <= x <= 9007199254740991
offset
integer
default:0

Number of results to skip

Required range: x >= 0

Response

Evaluations retrieved 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"

testCaseId
string | null
required
Example:

"tc_123"

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

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>