Crawl a public website into a knowledge base
curl --request POST \
--url https://api.pyai.com/v1/knowledgebases/{id}/crawls \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"url": "<string>",
"max_pages": 25
}
'import requests
url = "https://api.pyai.com/v1/knowledgebases/{id}/crawls"
payload = {
"url": "<string>",
"max_pages": 25
}
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({url: '<string>', max_pages: 25})
};
fetch('https://api.pyai.com/v1/knowledgebases/{id}/crawls', 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.pyai.com/v1/knowledgebases/{id}/crawls",
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([
'url' => '<string>',
'max_pages' => 25
]),
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.pyai.com/v1/knowledgebases/{id}/crawls"
payload := strings.NewReader("{\n \"url\": \"<string>\",\n \"max_pages\": 25\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.pyai.com/v1/knowledgebases/{id}/crawls")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"<string>\",\n \"max_pages\": 25\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.pyai.com/v1/knowledgebases/{id}/crawls")
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 \"url\": \"<string>\",\n \"max_pages\": 25\n}"
response = http.request(request)
puts response.read_body{
"object": "knowledgebase.crawl",
"seed_url": "<string>",
"max_pages": 123,
"discovered": 123,
"accepted": 123,
"reused": 123,
"skipped": [
{
"url": "<string>",
"reason": "<string>"
}
],
"documents": [
{
"id": "<string>",
"url": "<string>",
"title": "<string>",
"reused": true
}
]
}{
"title": "<string>",
"status": 123,
"type": "<string>",
"detail": "<string>",
"request_id": "<string>"
}{
"title": "<string>",
"status": 123,
"type": "<string>",
"detail": "<string>",
"request_id": "<string>"
}Knowledge Bases
Crawl a public website into a knowledge base
Discover same-origin pages from a public seed URL (robots.txt / sitemap, then a shallow link walk), rank them, and register each selected page as a normal URL document. Private, loopback, and metadata addresses are rejected. Defaults to 25 pages, hard-capped at 40. Already-ingested URLs in this knowledge base are reused. Poll document status until indexed before treating the site as ready. Requires the kb:manage scope.
POST
/
v1
/
knowledgebases
/
{id}
/
crawls
Crawl a public website into a knowledge base
curl --request POST \
--url https://api.pyai.com/v1/knowledgebases/{id}/crawls \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"url": "<string>",
"max_pages": 25
}
'import requests
url = "https://api.pyai.com/v1/knowledgebases/{id}/crawls"
payload = {
"url": "<string>",
"max_pages": 25
}
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({url: '<string>', max_pages: 25})
};
fetch('https://api.pyai.com/v1/knowledgebases/{id}/crawls', 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.pyai.com/v1/knowledgebases/{id}/crawls",
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([
'url' => '<string>',
'max_pages' => 25
]),
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.pyai.com/v1/knowledgebases/{id}/crawls"
payload := strings.NewReader("{\n \"url\": \"<string>\",\n \"max_pages\": 25\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.pyai.com/v1/knowledgebases/{id}/crawls")
.header("Authorization", "Bearer <token>")
.header("Content-Type", "application/json")
.body("{\n \"url\": \"<string>\",\n \"max_pages\": 25\n}")
.asString();require 'uri'
require 'net/http'
url = URI("https://api.pyai.com/v1/knowledgebases/{id}/crawls")
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 \"url\": \"<string>\",\n \"max_pages\": 25\n}"
response = http.request(request)
puts response.read_body{
"object": "knowledgebase.crawl",
"seed_url": "<string>",
"max_pages": 123,
"discovered": 123,
"accepted": 123,
"reused": 123,
"skipped": [
{
"url": "<string>",
"reason": "<string>"
}
],
"documents": [
{
"id": "<string>",
"url": "<string>",
"title": "<string>",
"reused": true
}
]
}{
"title": "<string>",
"status": 123,
"type": "<string>",
"detail": "<string>",
"request_id": "<string>"
}{
"title": "<string>",
"status": 123,
"type": "<string>",
"detail": "<string>",
"request_id": "<string>"
}Authorizations
apiKeyxApiKey
Body
application/json
Response
Pages registered (pending ingestion)