curl --request POST \
--url https://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "Help center",
"root_url": "https://example.com/docs",
"include_paths": [
"/docs"
],
"max_pages": 100,
"auto_sync": true,
"sync_interval_hours": 24
}
'import requests
url = "https://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources"
payload = {
"name": "Help center",
"root_url": "https://example.com/docs",
"include_paths": ["/docs"],
"max_pages": 100,
"auto_sync": True,
"sync_interval_hours": 24
}
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({
name: 'Help center',
root_url: 'https://example.com/docs',
include_paths: ['/docs'],
max_pages: 100,
auto_sync: true,
sync_interval_hours: 24
})
};
fetch('https://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources', 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://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources",
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([
'name' => 'Help center',
'root_url' => 'https://example.com/docs',
'include_paths' => [
'/docs'
],
'max_pages' => 100,
'auto_sync' => true,
'sync_interval_hours' => 24
]),
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://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources"
payload := strings.NewReader("{\n \"name\": \"Help center\",\n \"root_url\": \"https://example.com/docs\",\n \"include_paths\": [\n \"/docs\"\n ],\n \"max_pages\": 100,\n \"auto_sync\": true,\n \"sync_interval_hours\": 24\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://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"Help center\",\n \"root_url\": \"https://example.com/docs\",\n \"include_paths\": [\n \"/docs\"\n ],\n \"max_pages\": 100,\n \"auto_sync\": true,\n \"sync_interval_hours\": 24\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources")
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 \"name\": \"Help center\",\n \"root_url\": \"https://example.com/docs\",\n \"include_paths\": [\n \"/docs\"\n ],\n \"max_pages\": 100,\n \"auto_sync\": true,\n \"sync_interval_hours\": 24\n}"
response = http.request(request)
puts response.read_body{
"data": {
"source": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"knowledge_base_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"name": "Help center",
"root_url": "<string>",
"include_paths": [
"<string>"
],
"exclude_paths": [
"<string>"
],
"max_pages": 50,
"auto_sync": true,
"sync_interval_hours": 24,
"status": "idle",
"last_error": "<string>",
"last_crawled_at": "2023-11-07T05:31:56Z",
"pages_crawled": 123,
"credits_spent": 123,
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z"
}
}
}Create a crawl source
Register a website as a crawl source for a knowledge base. You can provide an optional custom name; when omitted, the source receives a URL-based display name that can be edited later. The crawler fetches pages under root_url (same host only, static HTML — no JavaScript rendering, max 2 MB per page), indexes them as documents and charges credits per crawled page. Trigger a crawl with POST /knowledge-bases/{id}/crawl-sources/{sourceId}/run, or enable auto_sync for periodic re-crawls. Required scope: knowledge:write (keys without scope restrictions have full access).
curl --request POST \
--url https://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "Help center",
"root_url": "https://example.com/docs",
"include_paths": [
"/docs"
],
"max_pages": 100,
"auto_sync": true,
"sync_interval_hours": 24
}
'import requests
url = "https://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources"
payload = {
"name": "Help center",
"root_url": "https://example.com/docs",
"include_paths": ["/docs"],
"max_pages": 100,
"auto_sync": True,
"sync_interval_hours": 24
}
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({
name: 'Help center',
root_url: 'https://example.com/docs',
include_paths: ['/docs'],
max_pages: 100,
auto_sync: true,
sync_interval_hours: 24
})
};
fetch('https://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources', 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://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources",
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([
'name' => 'Help center',
'root_url' => 'https://example.com/docs',
'include_paths' => [
'/docs'
],
'max_pages' => 100,
'auto_sync' => true,
'sync_interval_hours' => 24
]),
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://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources"
payload := strings.NewReader("{\n \"name\": \"Help center\",\n \"root_url\": \"https://example.com/docs\",\n \"include_paths\": [\n \"/docs\"\n ],\n \"max_pages\": 100,\n \"auto_sync\": true,\n \"sync_interval_hours\": 24\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://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"name\": \"Help center\",\n \"root_url\": \"https://example.com/docs\",\n \"include_paths\": [\n \"/docs\"\n ],\n \"max_pages\": 100,\n \"auto_sync\": true,\n \"sync_interval_hours\": 24\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://app.famulor.io/api/v1/knowledge-bases/{id}/crawl-sources")
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 \"name\": \"Help center\",\n \"root_url\": \"https://example.com/docs\",\n \"include_paths\": [\n \"/docs\"\n ],\n \"max_pages\": 100,\n \"auto_sync\": true,\n \"sync_interval_hours\": 24\n}"
response = http.request(request)
puts response.read_body{
"data": {
"source": {
"id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"knowledge_base_id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
"name": "Help center",
"root_url": "<string>",
"include_paths": [
"<string>"
],
"exclude_paths": [
"<string>"
],
"max_pages": 50,
"auto_sync": true,
"sync_interval_hours": 24,
"status": "idle",
"last_error": "<string>",
"last_crawled_at": "2023-11-07T05:31:56Z",
"pages_crawled": 123,
"credits_spent": 123,
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z"
}
}
}Authorizations
API key (fam_..., created under Settings → API Keys) or an OAuth 2.0 access token (fam_at_...). REST operations also require API Access for the credential's workspace. Keys can be restricted to scopes such as assistants:read, calls:write, campaigns:write, automations:read, dashboards:read, dashboards:write, leads:write, segments:write, loop:read, loop:write, phone_numbers:write, sip_trunks:write, knowledge:write, voices:read, billing:read, billing:write, settings:write, platform:read, platform:write; a *:write scope implies the matching *:read. Automation and dashboard endpoints also accept the legacy calls:* scope. Keys without scope restrictions have full access within the workspace's available capabilities.
Path Parameters
Knowledge base ID.
Body
Root URL to crawl (http/https).
Optional custom display name shown for this source. If omitted, a URL-based name is assigned and can be edited later.
1 - 128"Help center"
Optional paths to restrict crawling (e.g. ["/docs"]). Empty = whole host. End an entry with $ to match only that exact page (for example /impressum$); without $ it is a prefix.
Optional paths to skip (e.g. ["/admin"]). Max 200 per source, 500 per knowledge base. End an entry with $ to match only that exact page (for example /impressum$); without $ it is a prefix.
Maximum pages per run. Default 50.
1 <= x <= 500Re-crawl automatically on a schedule. Default false.
Hours between auto-sync crawls. Default 24. Common values: 24 = daily, 168 = weekly, 720 = monthly, 2160 = every 3 months, 4320 = every 6 months.
x >= 1Response
The created crawl source.
Show child attributes
Show child attributes