curl --request PATCH \
--url https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"configId": "6683f1c2a4b19e0012ab34cd",
"enabled": true,
"startUrl": "https://ajuda.acme.com",
"cron": "0 0 3 * * *",
"allowedDomains": "ajuda.acme.com",
"pathFilter": "/artigos",
"excludePathFilter": "/artigos/rascunhos",
"defaultScraperTag": "ajuda",
"defaultScraperTopic": "Autoatendimento",
"maxAgeMs": 86400000,
"locales": [
"pt-BR"
],
"cleaningEnabled": false
}
'import requests
url = "https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config"
payload = {
"configId": "6683f1c2a4b19e0012ab34cd",
"enabled": True,
"startUrl": "https://ajuda.acme.com",
"cron": "0 0 3 * * *",
"allowedDomains": "ajuda.acme.com",
"pathFilter": "/artigos",
"excludePathFilter": "/artigos/rascunhos",
"defaultScraperTag": "ajuda",
"defaultScraperTopic": "Autoatendimento",
"maxAgeMs": 86400000,
"locales": ["pt-BR"],
"cleaningEnabled": False
}
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({
configId: '6683f1c2a4b19e0012ab34cd',
enabled: true,
startUrl: 'https://ajuda.acme.com',
cron: '0 0 3 * * *',
allowedDomains: 'ajuda.acme.com',
pathFilter: '/artigos',
excludePathFilter: '/artigos/rascunhos',
defaultScraperTag: 'ajuda',
defaultScraperTopic: 'Autoatendimento',
maxAgeMs: 86400000,
locales: ['pt-BR'],
cleaningEnabled: false
})
};
fetch('https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config', 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.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config",
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([
'configId' => '6683f1c2a4b19e0012ab34cd',
'enabled' => true,
'startUrl' => 'https://ajuda.acme.com',
'cron' => '0 0 3 * * *',
'allowedDomains' => 'ajuda.acme.com',
'pathFilter' => '/artigos',
'excludePathFilter' => '/artigos/rascunhos',
'defaultScraperTag' => 'ajuda',
'defaultScraperTopic' => 'Autoatendimento',
'maxAgeMs' => 86400000,
'locales' => [
'pt-BR'
],
'cleaningEnabled' => false
]),
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.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config"
payload := strings.NewReader("{\n \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n \"enabled\": true,\n \"startUrl\": \"https://ajuda.acme.com\",\n \"cron\": \"0 0 3 * * *\",\n \"allowedDomains\": \"ajuda.acme.com\",\n \"pathFilter\": \"/artigos\",\n \"excludePathFilter\": \"/artigos/rascunhos\",\n \"defaultScraperTag\": \"ajuda\",\n \"defaultScraperTopic\": \"Autoatendimento\",\n \"maxAgeMs\": 86400000,\n \"locales\": [\n \"pt-BR\"\n ],\n \"cleaningEnabled\": false\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.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n \"enabled\": true,\n \"startUrl\": \"https://ajuda.acme.com\",\n \"cron\": \"0 0 3 * * *\",\n \"allowedDomains\": \"ajuda.acme.com\",\n \"pathFilter\": \"/artigos\",\n \"excludePathFilter\": \"/artigos/rascunhos\",\n \"defaultScraperTag\": \"ajuda\",\n \"defaultScraperTopic\": \"Autoatendimento\",\n \"maxAgeMs\": 86400000,\n \"locales\": [\n \"pt-BR\"\n ],\n \"cleaningEnabled\": false\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config")
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 \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n \"enabled\": true,\n \"startUrl\": \"https://ajuda.acme.com\",\n \"cron\": \"0 0 3 * * *\",\n \"allowedDomains\": \"ajuda.acme.com\",\n \"pathFilter\": \"/artigos\",\n \"excludePathFilter\": \"/artigos/rascunhos\",\n \"defaultScraperTag\": \"ajuda\",\n \"defaultScraperTopic\": \"Autoatendimento\",\n \"maxAgeMs\": 86400000,\n \"locales\": [\n \"pt-BR\"\n ],\n \"cleaningEnabled\": false\n}"
response = http.request(request)
puts response.read_body[
{
"startUrl": "https://ajuda.acme.com",
"cron": "0 0 3 * * *",
"allowedDomains": "ajuda.acme.com",
"pathFilter": "/artigos",
"excludePathFilter": "/artigos/rascunhos",
"defaultScraperTag": "ajuda",
"type": "SCRAPY",
"createdAt": "2026-08-10T14:32:05",
"configId": "6683f1c2a4b19e0012ab34cd",
"enabled": true,
"defaultScraperTopic": "Autoatendimento",
"maxAgeMs": 86400000,
"locales": [
"pt-BR"
],
"cleaningEnabled": false,
"updatedAt": "2026-08-10T18:20:41"
}
]{
"error": "Forbidden: token holds no claim for the requested account"
}{
"error": "Forbidden: token holds no claim for the requested account"
}{
"error": "Forbidden: token holds no claim for the requested account"
}Create or update a content source
Send configId to change an existing source, or omit it to create one — a configId that matches no source of this knowledge base is refused, never created under the id you sent. Every field is optional and an omitted one keeps what is stored. maxAgeMs is the exception worth reading: omit it to keep the current freshness window, send null to restore the crawler’s default, send a number of milliseconds to apply it — 0 forces a full re-crawl on the next run.
curl --request PATCH \
--url https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"configId": "6683f1c2a4b19e0012ab34cd",
"enabled": true,
"startUrl": "https://ajuda.acme.com",
"cron": "0 0 3 * * *",
"allowedDomains": "ajuda.acme.com",
"pathFilter": "/artigos",
"excludePathFilter": "/artigos/rascunhos",
"defaultScraperTag": "ajuda",
"defaultScraperTopic": "Autoatendimento",
"maxAgeMs": 86400000,
"locales": [
"pt-BR"
],
"cleaningEnabled": false
}
'import requests
url = "https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config"
payload = {
"configId": "6683f1c2a4b19e0012ab34cd",
"enabled": True,
"startUrl": "https://ajuda.acme.com",
"cron": "0 0 3 * * *",
"allowedDomains": "ajuda.acme.com",
"pathFilter": "/artigos",
"excludePathFilter": "/artigos/rascunhos",
"defaultScraperTag": "ajuda",
"defaultScraperTopic": "Autoatendimento",
"maxAgeMs": 86400000,
"locales": ["pt-BR"],
"cleaningEnabled": False
}
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({
configId: '6683f1c2a4b19e0012ab34cd',
enabled: true,
startUrl: 'https://ajuda.acme.com',
cron: '0 0 3 * * *',
allowedDomains: 'ajuda.acme.com',
pathFilter: '/artigos',
excludePathFilter: '/artigos/rascunhos',
defaultScraperTag: 'ajuda',
defaultScraperTopic: 'Autoatendimento',
maxAgeMs: 86400000,
locales: ['pt-BR'],
cleaningEnabled: false
})
};
fetch('https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config', 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.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config",
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([
'configId' => '6683f1c2a4b19e0012ab34cd',
'enabled' => true,
'startUrl' => 'https://ajuda.acme.com',
'cron' => '0 0 3 * * *',
'allowedDomains' => 'ajuda.acme.com',
'pathFilter' => '/artigos',
'excludePathFilter' => '/artigos/rascunhos',
'defaultScraperTag' => 'ajuda',
'defaultScraperTopic' => 'Autoatendimento',
'maxAgeMs' => 86400000,
'locales' => [
'pt-BR'
],
'cleaningEnabled' => false
]),
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.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config"
payload := strings.NewReader("{\n \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n \"enabled\": true,\n \"startUrl\": \"https://ajuda.acme.com\",\n \"cron\": \"0 0 3 * * *\",\n \"allowedDomains\": \"ajuda.acme.com\",\n \"pathFilter\": \"/artigos\",\n \"excludePathFilter\": \"/artigos/rascunhos\",\n \"defaultScraperTag\": \"ajuda\",\n \"defaultScraperTopic\": \"Autoatendimento\",\n \"maxAgeMs\": 86400000,\n \"locales\": [\n \"pt-BR\"\n ],\n \"cleaningEnabled\": false\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.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n \"enabled\": true,\n \"startUrl\": \"https://ajuda.acme.com\",\n \"cron\": \"0 0 3 * * *\",\n \"allowedDomains\": \"ajuda.acme.com\",\n \"pathFilter\": \"/artigos\",\n \"excludePathFilter\": \"/artigos/rascunhos\",\n \"defaultScraperTag\": \"ajuda\",\n \"defaultScraperTopic\": \"Autoatendimento\",\n \"maxAgeMs\": 86400000,\n \"locales\": [\n \"pt-BR\"\n ],\n \"cleaningEnabled\": false\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.cloudhumans.com/claudia/v1/knowledge-bases/{kbId}/scraper-config")
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 \"configId\": \"6683f1c2a4b19e0012ab34cd\",\n \"enabled\": true,\n \"startUrl\": \"https://ajuda.acme.com\",\n \"cron\": \"0 0 3 * * *\",\n \"allowedDomains\": \"ajuda.acme.com\",\n \"pathFilter\": \"/artigos\",\n \"excludePathFilter\": \"/artigos/rascunhos\",\n \"defaultScraperTag\": \"ajuda\",\n \"defaultScraperTopic\": \"Autoatendimento\",\n \"maxAgeMs\": 86400000,\n \"locales\": [\n \"pt-BR\"\n ],\n \"cleaningEnabled\": false\n}"
response = http.request(request)
puts response.read_body[
{
"startUrl": "https://ajuda.acme.com",
"cron": "0 0 3 * * *",
"allowedDomains": "ajuda.acme.com",
"pathFilter": "/artigos",
"excludePathFilter": "/artigos/rascunhos",
"defaultScraperTag": "ajuda",
"type": "SCRAPY",
"createdAt": "2026-08-10T14:32:05",
"configId": "6683f1c2a4b19e0012ab34cd",
"enabled": true,
"defaultScraperTopic": "Autoatendimento",
"maxAgeMs": 86400000,
"locales": [
"pt-BR"
],
"cleaningEnabled": false,
"updatedAt": "2026-08-10T18:20:41"
}
]{
"error": "Forbidden: token holds no claim for the requested account"
}{
"error": "Forbidden: token holds no claim for the requested account"
}{
"error": "Forbidden: token holds no claim for the requested account"
}Authorizations
Path Parameters
Body
What to change on a content source, or the source to create.
true (the default) lets the crawler remove navigation and support contacts and reorganize the text with an LLM. false stores the source text without that rewrite: use it for a source that is already clean content, such as a CloudChat portal. Images are described as text either way. Omit to keep the current setting.
false
Response
Every source of this knowledge base, as stored after the change.