Create evaluations for a single trace
curl --request POST \
--url https://api.galtea.ai/evaluations/fromInferenceResult \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"sessionId": "session_123",
"inferenceResultId": "ir_123",
"metrics": [
{
"id": "id_123",
"name": "Example Name",
"score": 0.95
}
],
"specificationIds": [
"<string>"
],
"runId": "run_123"
}
'import requests
url = "https://api.galtea.ai/evaluations/fromInferenceResult"
payload = {
"sessionId": "session_123",
"inferenceResultId": "ir_123",
"metrics": [
{
"id": "id_123",
"name": "Example Name",
"score": 0.95
}
],
"specificationIds": ["<string>"],
"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({
sessionId: 'session_123',
inferenceResultId: 'ir_123',
metrics: [{id: 'id_123', name: 'Example Name', score: 0.95}],
specificationIds: ['<string>'],
runId: 'run_123'
})
};
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([
'sessionId' => 'session_123',
'inferenceResultId' => 'ir_123',
'metrics' => [
[
'id' => 'id_123',
'name' => 'Example Name',
'score' => 0.95
]
],
'specificationIds' => [
'<string>'
],
'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/fromInferenceResult"
payload := strings.NewReader("{\n \"sessionId\": \"session_123\",\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 \"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/fromInferenceResult")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"sessionId\": \"session_123\",\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 \"runId\": \"run_123\"\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 \"sessionId\": \"session_123\",\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 \"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"
}{
"error": "Error type",
"message": "Error message description"
}Create evaluations for a single trace
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 trace
curl --request POST \
--url https://api.galtea.ai/evaluations/fromInferenceResult \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"sessionId": "session_123",
"inferenceResultId": "ir_123",
"metrics": [
{
"id": "id_123",
"name": "Example Name",
"score": 0.95
}
],
"specificationIds": [
"<string>"
],
"runId": "run_123"
}
'import requests
url = "https://api.galtea.ai/evaluations/fromInferenceResult"
payload = {
"sessionId": "session_123",
"inferenceResultId": "ir_123",
"metrics": [
{
"id": "id_123",
"name": "Example Name",
"score": 0.95
}
],
"specificationIds": ["<string>"],
"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({
sessionId: 'session_123',
inferenceResultId: 'ir_123',
metrics: [{id: 'id_123', name: 'Example Name', score: 0.95}],
specificationIds: ['<string>'],
runId: 'run_123'
})
};
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([
'sessionId' => 'session_123',
'inferenceResultId' => 'ir_123',
'metrics' => [
[
'id' => 'id_123',
'name' => 'Example Name',
'score' => 0.95
]
],
'specificationIds' => [
'<string>'
],
'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/fromInferenceResult"
payload := strings.NewReader("{\n \"sessionId\": \"session_123\",\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 \"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/fromInferenceResult")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"sessionId\": \"session_123\",\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 \"runId\": \"run_123\"\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 \"sessionId\": \"session_123\",\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 \"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"
}{
"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-....
Body
application/json
Example:
"session_123"
The ID of the trace (one conversation turn) to evaluate
Example:
"ir_123"
Metrics to evaluate. Optional if specificationIds is provided or the product has specifications with linked metrics.
Show child attributes
Show child attributes
Specification IDs whose linked metrics will be evaluated. Can be combined with metrics; the API merges and deduplicates.
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
Example:
"eval_123"
Example:
"metric_123"
Example:
"session_123"
Example:
"product_123"
Example:
"user_123"
Available options:
PENDING, PENDING_HUMAN, SUCCESS, FAILED, SKIPPED, CANCELLED, OUTDATED Example:
"SUCCESS"
Example:
"ir_123"
Example:
0.95
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 <= 1