Update inference result

Update an existing inference result. See Inference Results.

PATCH /inferenceResults/{id}

Update inference result

cURL

curl --request PATCH \
  --url https://api.galtea.ai/inferenceResults/{id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "actualOutput": "Model response text",
  "retrievalContext": "Retrieved context document",
  "error": "<string>",
  "latency": 123
}
'

import requests

url = "https://api.galtea.ai/inferenceResults/{id}"

payload = {
    "actualOutput": "Model response text",
    "retrievalContext": "Retrieved context document",
    "error": "<string>",
    "latency": 123
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.patch(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'PATCH',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    actualOutput: 'Model response text',
    retrievalContext: 'Retrieved context document',
    error: '<string>',
    latency: 123
  })
};

fetch('https://api.galtea.ai/inferenceResults/{id}', 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/inferenceResults/{id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PATCH",
  CURLOPT_POSTFIELDS => json_encode([
    'actualOutput' => 'Model response text',
    'retrievalContext' => 'Retrieved context document',
    'error' => '<string>',
    'latency' => 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/inferenceResults/{id}"

	payload := strings.NewReader("{\n  \"actualOutput\": \"Model response text\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"error\": \"<string>\",\n  \"latency\": 123\n}")

	req, _ := http.NewRequest("PATCH", 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.patch("https://api.galtea.ai/inferenceResults/{id}")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"actualOutput\": \"Model response text\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"error\": \"<string>\",\n  \"latency\": 123\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.galtea.ai/inferenceResults/{id}")

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

request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"actualOutput\": \"Model response text\",\n  \"retrievalContext\": \"Retrieved context document\",\n  \"error\": \"<string>\",\n  \"latency\": 123\n}"

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

200

{
  "id": "ir_123",
  "sessionId": "session_123",
  "userId": "user_123",
  "index": 0,
  "status": "PENDING",
  "error": null,
  "input": {
    "user_message": "User input text"
  },
  "actualOutput": "Model response",
  "latency": 150,
  "inputTokens": 100,
  "outputTokens": 50,
  "cacheReadInputTokens": 20,
  "tokens": 150,
  "costPerInputToken": 0.00001,
  "costPerOutputToken": 0.00003,
  "costPerCacheReadInputToken": 0.000005,
  "cost": 0.001,
  "creditsUsed": 1,
  "conversationSimulatorVersion": "1.0.0",
  "traceId": "a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4",
  "createdAt": "2023-11-07T05:31:56Z",
  "deletedAt": "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-....

Path Parameters

id · string · required

Inference result ID

Body

application/json

actualOutput · string object

Agent output. Plain text by default (the scored scalar); for voice, an envelope { assistant_message, content: [{ type, uri, transcript }] } carrying audio parts. An audio part without a transcript is rejected with a 400.

Example:

"Model response text"

retrievalContext · string

Example:

"Retrieved context document"

error · string | null

Error message explaining why this inference result failed or was skipped

latency · integer

Response

200

application/json

Inference result updated successfully

id · string

Example:

"ir_123"

sessionId · string

Example:

"session_123"

userId · string | null

Example:

"user_123"

index · integer

Order index within the session

Example:

0

status · enum<string>

Available options: PENDING, GENERATED, FAILED, SKIPPED

Example:

"PENDING"

error · string | null

Error message explaining why this inference result failed or was skipped

Example:

null

input · object | null

Structured input data. For plain text input, format is { user_message: "..." }

Example:

{ "user_message": "User input text" }

actualOutput · string object

The agent turn output. Plain text by default (the scored scalar). For voice turns, an envelope { assistant_message, content: [{ type, uri, transcript }] } carrying audio parts — the scored scalar stays the canonical transcript.

Example:

"Model response"

latency · integer | null

Example:

150

inputTokens · integer | null

Example:

100

outputTokens · integer | null

Example:

50

cacheReadInputTokens · integer | null

Example:

20

tokens · integer | null

Total tokens

Example:

150

costPerInputToken · number | null

Example:

0.00001

costPerOutputToken · number | null

Example:

0.00003

costPerCacheReadInputToken · number | null

Example:

0.000005

cost · number | null

Example:

0.001

creditsUsed · integer | null

Example:

1

conversationSimulatorVersion · string | null

Example:

"1.0.0"

traceId · string | null

W3C trace ID for the root span created during direct inference. The same trace ID is propagated to the user endpoint via the traceparent header.

Example:

"a1b2c3d4e5f6a1b2c3d4e5f6a1b2c3d4"

createdAt · string<date-time>

deletedAt · string<date-time> | null