Create single-turn evaluations

curl --request POST \
  --url https://api.galtea.ai/evaluations/singleTurn \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "metrics": [
    {
      "id": "id_123",
      "name": "Example Name",
      "score": 0.95
    }
  ],
  "actualOutput": "Model response text",
  "versionId": "ver_123",
  "productId": "prod_123",
  "testCaseId": "tc_123",
  "input": "What is the capital of France?",
  "retrievalContext": "Retrieved context document",
  "inputTokens": 123,
  "outputTokens": 123,
  "cacheReadInputTokens": 123,
  "tokens": 123,
  "cost": 123,
  "costPerInputToken": 123,
  "costPerOutputToken": 123,
  "costPerCacheReadInputToken": 123,
  "conversationSimulatorVersion": "<string>",
  "isProduction": true,
  "runId": "run_123"
}
'

import requests

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

payload = {
    "metrics": [
        {
            "id": "id_123",
            "name": "Example Name",
            "score": 0.95
        }
    ],
    "actualOutput": "Model response text",
    "versionId": "ver_123",
    "productId": "prod_123",
    "testCaseId": "tc_123",
    "input": "What is the capital of France?",
    "retrievalContext": "Retrieved context document",
    "inputTokens": 123,
    "outputTokens": 123,
    "cacheReadInputTokens": 123,
    "tokens": 123,
    "cost": 123,
    "costPerInputToken": 123,
    "costPerOutputToken": 123,
    "costPerCacheReadInputToken": 123,
    "conversationSimulatorVersion": "<string>",
    "isProduction": True,
    "runId": "run_123"
}
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({
    metrics: [{id: 'id_123', name: 'Example Name', score: 0.95}],
    actualOutput: 'Model response text',
    versionId: 'ver_123',
    productId: 'prod_123',
    testCaseId: 'tc_123',
    input: 'What is the capital of France?',
    retrievalContext: 'Retrieved context document',
    inputTokens: 123,
    outputTokens: 123,
    cacheReadInputTokens: 123,
    tokens: 123,
    cost: 123,
    costPerInputToken: 123,
    costPerOutputToken: 123,
    costPerCacheReadInputToken: 123,
    conversationSimulatorVersion: '<string>',
    isProduction: true,
    runId: 'run_123'
  })
};

fetch('https://api.galtea.ai/evaluations/singleTurn', 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/singleTurn",
  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([
    'metrics' => [
        [
                'id' => 'id_123',
                'name' => 'Example Name',
                'score' => 0.95
        ]
    ],
    'actualOutput' => 'Model response text',
    'versionId' => 'ver_123',
    'productId' => 'prod_123',
    'testCaseId' => 'tc_123',
    'input' => 'What is the capital of France?',
    'retrievalContext' => 'Retrieved context document',
    'inputTokens' => 123,
    'outputTokens' => 123,
    'cacheReadInputTokens' => 123,
    'tokens' => 123,
    'cost' => 123,
    'costPerInputToken' => 123,
    'costPerOutputToken' => 123,
    'costPerCacheReadInputToken' => 123,
    'conversationSimulatorVersion' => '<string>',
    'isProduction' => true,
    'runId' => 'run_123'
  ]),
  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/singleTurn"

	payload := strings.NewReader("{\n  \"metrics\": [\n    {\n      \"id\": \"id_123\",\n      \"name\": \"Example Name\",\n      \"score\": 0.95\n    }\n  ],\n  \"actualOutput\": \"Model response text\",\n  \"versionId\": \"ver_123\",\n  \"productId\": \"prod_123\",\n  \"testCaseId\": \"tc_123\",\n  \"input\": \"What is the capital of France?\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"inputTokens\": 123,\n  \"outputTokens\": 123,\n  \"cacheReadInputTokens\": 123,\n  \"tokens\": 123,\n  \"cost\": 123,\n  \"costPerInputToken\": 123,\n  \"costPerOutputToken\": 123,\n  \"costPerCacheReadInputToken\": 123,\n  \"conversationSimulatorVersion\": \"<string>\",\n  \"isProduction\": true,\n  \"runId\": \"run_123\"\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/singleTurn")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"metrics\": [\n    {\n      \"id\": \"id_123\",\n      \"name\": \"Example Name\",\n      \"score\": 0.95\n    }\n  ],\n  \"actualOutput\": \"Model response text\",\n  \"versionId\": \"ver_123\",\n  \"productId\": \"prod_123\",\n  \"testCaseId\": \"tc_123\",\n  \"input\": \"What is the capital of France?\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"inputTokens\": 123,\n  \"outputTokens\": 123,\n  \"cacheReadInputTokens\": 123,\n  \"tokens\": 123,\n  \"cost\": 123,\n  \"costPerInputToken\": 123,\n  \"costPerOutputToken\": 123,\n  \"costPerCacheReadInputToken\": 123,\n  \"conversationSimulatorVersion\": \"<string>\",\n  \"isProduction\": true,\n  \"runId\": \"run_123\"\n}")
  .asString();

require 'uri'
require 'net/http'

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

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  \"metrics\": [\n    {\n      \"id\": \"id_123\",\n      \"name\": \"Example Name\",\n      \"score\": 0.95\n    }\n  ],\n  \"actualOutput\": \"Model response text\",\n  \"versionId\": \"ver_123\",\n  \"productId\": \"prod_123\",\n  \"testCaseId\": \"tc_123\",\n  \"input\": \"What is the capital of France?\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"inputTokens\": 123,\n  \"outputTokens\": 123,\n  \"cacheReadInputTokens\": 123,\n  \"tokens\": 123,\n  \"cost\": 123,\n  \"costPerInputToken\": 123,\n  \"costPerOutputToken\": 123,\n  \"costPerCacheReadInputToken\": 123,\n  \"conversationSimulatorVersion\": \"<string>\",\n  \"isProduction\": true,\n  \"runId\": \"run_123\"\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": "<string>",
    "error": "<string>",
    "canRetry": true,
    "creditsUsed": 123,
    "conversationSimulatorVersion": "<string>",
    "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",
    "passed": true,
    "metricPassThreshold": 0.5,
    "metricDisabledAt": "2023-11-07T05:31:56Z",
    "runId": "<string>",
    "metricExcludedFromAnalyticsAt": "2023-11-07T05:31:56Z",
    "metricExcludedByUserId": "<string>",
    "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"
}

POST

evaluations

singleTurn

Create single-turn evaluations

curl --request POST \
  --url https://api.galtea.ai/evaluations/singleTurn \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "metrics": [
    {
      "id": "id_123",
      "name": "Example Name",
      "score": 0.95
    }
  ],
  "actualOutput": "Model response text",
  "versionId": "ver_123",
  "productId": "prod_123",
  "testCaseId": "tc_123",
  "input": "What is the capital of France?",
  "retrievalContext": "Retrieved context document",
  "inputTokens": 123,
  "outputTokens": 123,
  "cacheReadInputTokens": 123,
  "tokens": 123,
  "cost": 123,
  "costPerInputToken": 123,
  "costPerOutputToken": 123,
  "costPerCacheReadInputToken": 123,
  "conversationSimulatorVersion": "<string>",
  "isProduction": true,
  "runId": "run_123"
}
'

import requests

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

payload = {
    "metrics": [
        {
            "id": "id_123",
            "name": "Example Name",
            "score": 0.95
        }
    ],
    "actualOutput": "Model response text",
    "versionId": "ver_123",
    "productId": "prod_123",
    "testCaseId": "tc_123",
    "input": "What is the capital of France?",
    "retrievalContext": "Retrieved context document",
    "inputTokens": 123,
    "outputTokens": 123,
    "cacheReadInputTokens": 123,
    "tokens": 123,
    "cost": 123,
    "costPerInputToken": 123,
    "costPerOutputToken": 123,
    "costPerCacheReadInputToken": 123,
    "conversationSimulatorVersion": "<string>",
    "isProduction": True,
    "runId": "run_123"
}
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({
    metrics: [{id: 'id_123', name: 'Example Name', score: 0.95}],
    actualOutput: 'Model response text',
    versionId: 'ver_123',
    productId: 'prod_123',
    testCaseId: 'tc_123',
    input: 'What is the capital of France?',
    retrievalContext: 'Retrieved context document',
    inputTokens: 123,
    outputTokens: 123,
    cacheReadInputTokens: 123,
    tokens: 123,
    cost: 123,
    costPerInputToken: 123,
    costPerOutputToken: 123,
    costPerCacheReadInputToken: 123,
    conversationSimulatorVersion: '<string>',
    isProduction: true,
    runId: 'run_123'
  })
};

fetch('https://api.galtea.ai/evaluations/singleTurn', 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/singleTurn",
  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([
    'metrics' => [
        [
                'id' => 'id_123',
                'name' => 'Example Name',
                'score' => 0.95
        ]
    ],
    'actualOutput' => 'Model response text',
    'versionId' => 'ver_123',
    'productId' => 'prod_123',
    'testCaseId' => 'tc_123',
    'input' => 'What is the capital of France?',
    'retrievalContext' => 'Retrieved context document',
    'inputTokens' => 123,
    'outputTokens' => 123,
    'cacheReadInputTokens' => 123,
    'tokens' => 123,
    'cost' => 123,
    'costPerInputToken' => 123,
    'costPerOutputToken' => 123,
    'costPerCacheReadInputToken' => 123,
    'conversationSimulatorVersion' => '<string>',
    'isProduction' => true,
    'runId' => 'run_123'
  ]),
  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/singleTurn"

	payload := strings.NewReader("{\n  \"metrics\": [\n    {\n      \"id\": \"id_123\",\n      \"name\": \"Example Name\",\n      \"score\": 0.95\n    }\n  ],\n  \"actualOutput\": \"Model response text\",\n  \"versionId\": \"ver_123\",\n  \"productId\": \"prod_123\",\n  \"testCaseId\": \"tc_123\",\n  \"input\": \"What is the capital of France?\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"inputTokens\": 123,\n  \"outputTokens\": 123,\n  \"cacheReadInputTokens\": 123,\n  \"tokens\": 123,\n  \"cost\": 123,\n  \"costPerInputToken\": 123,\n  \"costPerOutputToken\": 123,\n  \"costPerCacheReadInputToken\": 123,\n  \"conversationSimulatorVersion\": \"<string>\",\n  \"isProduction\": true,\n  \"runId\": \"run_123\"\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/singleTurn")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"metrics\": [\n    {\n      \"id\": \"id_123\",\n      \"name\": \"Example Name\",\n      \"score\": 0.95\n    }\n  ],\n  \"actualOutput\": \"Model response text\",\n  \"versionId\": \"ver_123\",\n  \"productId\": \"prod_123\",\n  \"testCaseId\": \"tc_123\",\n  \"input\": \"What is the capital of France?\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"inputTokens\": 123,\n  \"outputTokens\": 123,\n  \"cacheReadInputTokens\": 123,\n  \"tokens\": 123,\n  \"cost\": 123,\n  \"costPerInputToken\": 123,\n  \"costPerOutputToken\": 123,\n  \"costPerCacheReadInputToken\": 123,\n  \"conversationSimulatorVersion\": \"<string>\",\n  \"isProduction\": true,\n  \"runId\": \"run_123\"\n}")
  .asString();

require 'uri'
require 'net/http'

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

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  \"metrics\": [\n    {\n      \"id\": \"id_123\",\n      \"name\": \"Example Name\",\n      \"score\": 0.95\n    }\n  ],\n  \"actualOutput\": \"Model response text\",\n  \"versionId\": \"ver_123\",\n  \"productId\": \"prod_123\",\n  \"testCaseId\": \"tc_123\",\n  \"input\": \"What is the capital of France?\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"inputTokens\": 123,\n  \"outputTokens\": 123,\n  \"cacheReadInputTokens\": 123,\n  \"tokens\": 123,\n  \"cost\": 123,\n  \"costPerInputToken\": 123,\n  \"costPerOutputToken\": 123,\n  \"costPerCacheReadInputToken\": 123,\n  \"conversationSimulatorVersion\": \"<string>\",\n  \"isProduction\": true,\n  \"runId\": \"run_123\"\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": "<string>",
    "error": "<string>",
    "canRetry": true,
    "creditsUsed": 123,
    "conversationSimulatorVersion": "<string>",
    "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",
    "passed": true,
    "metricPassThreshold": 0.5,
    "metricDisabledAt": "2023-11-07T05:31:56Z",
    "runId": "<string>",
    "metricExcludedFromAnalyticsAt": "2023-11-07T05:31:56Z",
    "metricExcludedByUserId": "<string>",
    "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"
}

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

metrics

object[]

required

Show child attributes

actualOutput

string | null

required

Example:

"Model response text"

versionId

string | null

Version to attach the evaluation to. Optional: when omitted, provide productId and the API reuses the product's latest version (creating a default first version if the product has none). One of versionId or productId is required.

Example:

"ver_123"

productId

string | null

Product to anchor the evaluation when versionId is omitted. Ignored when versionId is provided.

Example:

"prod_123"

testCaseId

string | null

Required when isProduction is false. Must be omitted when isProduction is true.

Example:

"tc_123"

input

string | null

User input/prompt. Required when isProduction is true. Must be omitted when isProduction is false.

Example:

"What is the capital of France?"

retrievalContext

string | null

RAG retrieval context used to generate the actual output

Example:

"Retrieved context document"

inputTokens

number | null

Input token count for the LLM call

outputTokens

number | null

Output token count for the LLM call

cacheReadInputTokens

number | null

Input tokens served from a prompt cache

tokens

number | null

Total token count, when the caller has no breakdown

cost

number | null

Total cost of the LLM call

costPerInputToken

number | null

Price per input token

costPerOutputToken

number | null

Price per output token

costPerCacheReadInputToken

number | null

Price per cache-read input token

conversationSimulatorVersion

string | null

Version of the conversation simulator that produced this turn, if simulated

isProduction

boolean | null

When true, creates a production evaluation (input required, testCaseId must be omitted). When false (default), testCaseId is required and input must be omitted.

runId

string | null

Attribute this evaluation to a run you opened with POST /runs, and close that run yourself. Without it the API opens its own run and closes it when the launch finishes. A run the platform opened is refused.

Example:

"run_123"

Response

Evaluations created successfully

string

required

Example:

"eval_123"

metricId

string

required

Example:

"metric_123"

sessionId

string

required

Example:

"session_123"

productId

string | null

required

Example:

"product_123"

userId

string | null

required

Example:

"user_123"

status

enum<string>

required

Available options:

PENDING,

PENDING_HUMAN,

SUCCESS,

FAILED,

SKIPPED,

CANCELLED,

OUTDATED

Example:

"SUCCESS"

inferenceResultId

string | null

required

Example:

"ir_123"

score

number | null

required

Example:

0.95

reason

string | null

required

error

string | null

required

canRetry

boolean

required

creditsUsed

integer | null

required

conversationSimulatorVersion

string | null

required

humanEvaluatorId

string | null

required

humanEvaluatorStartedAt

string<date-time> | null

required

humanScore

number | null

required

humanReason

string | null

required

humanEvaluatorFinishedAt

string<date-time> | null

required

failedTurns

string[]

required

deletedAt

string<date-time> | null

required

evaluatedAt

string<date-time> | null

required

metricLegacyAt

string<date-time> | null

required

passed

boolean | null

required

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.

metricPassThreshold

number

required

The pass threshold that decides passed: the metric's, copied onto the evaluation when it was created.

Required range: 0 <= x <= 1

metricDisabledAt

string<date-time> | null

required

runId

string | null

required

metricExcludedFromAnalyticsAt

string<date-time> | null

required

metricExcludedByUserId

string | null

required

createdAt

string<date-time>

Overview

Endpoints

Create single-turn evaluations

Authorizations

Body

Response