Train Neo4J Website

Crawl websites and generate a knowledge graph using Neo4J based on the provided URLs and crawl settings.

POST /knowledge_graph/neo4j/website/

Train Neo4J Website

cURL

curl --request POST \
  --url https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/website/ \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "urls": [
    "https://example.com"
  ],
  "source": "website",
  "max_crawl_pages": 1,
  "max_crawl_depth": 0,
  "dynamic_content_wait_secs": 5,
  "actor": "apify/website-content-crawler",
  "crawler_type": "cheerio"
}
'

import requests

url = "https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/website/"

payload = {
    "urls": ["https://example.com"],
    "source": "website",
    "max_crawl_pages": 1,
    "max_crawl_depth": 0,
    "dynamic_content_wait_secs": 5,
    "actor": "apify/website-content-crawler",
    "crawler_type": "cheerio"
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    urls: ['https://example.com'],
    source: 'website',
    max_crawl_pages: 1,
    max_crawl_depth: 0,
    dynamic_content_wait_secs: 5,
    actor: 'apify/website-content-crawler',
    crawler_type: 'cheerio'
  })
};

fetch('https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/website/', 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://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/website/",
  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([
    'urls' => [
        'https://example.com'
    ],
    'source' => 'website',
    'max_crawl_pages' => 1,
    'max_crawl_depth' => 0,
    'dynamic_content_wait_secs' => 5,
    'actor' => 'apify/website-content-crawler',
    'crawler_type' => 'cheerio'
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($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://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/website/"

	payload := strings.NewReader("{\n  \"urls\": [\n    \"https://example.com\"\n  ],\n  \"source\": \"website\",\n  \"max_crawl_pages\": 1,\n  \"max_crawl_depth\": 0,\n  \"dynamic_content_wait_secs\": 5,\n  \"actor\": \"apify/website-content-crawler\",\n  \"crawler_type\": \"cheerio\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("x-api-key", "<api-key>")
	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://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/website/")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"urls\": [\n    \"https://example.com\"\n  ],\n  \"source\": \"website\",\n  \"max_crawl_pages\": 1,\n  \"max_crawl_depth\": 0,\n  \"dynamic_content_wait_secs\": 5,\n  \"actor\": \"apify/website-content-crawler\",\n  \"crawler_type\": \"cheerio\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://rag-prod.studio.lyzr.ai/v4/knowledge_graph/neo4j/website/")

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

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"urls\": [\n    \"https://example.com\"\n  ],\n  \"source\": \"website\",\n  \"max_crawl_pages\": 1,\n  \"max_crawl_depth\": 0,\n  \"dynamic_content_wait_secs\": 5,\n  \"actor\": \"apify/website-content-crawler\",\n  \"crawler_type\": \"cheerio\"\n}"

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

200

{
  "message": "Website training complete",
  "rag_id": "6848ff3c4c291b4bef798e0c",
  "pages_trained": 12
}

{
  "detail": "Invalid permission"
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>"
    }
  ]
}

Authorizations

x-api-key · string · header · required

Query Parameters

rag_id · string · required

The ID of the RAG system to train

Body

application/json

urls · string[] · required

List of website URLs to crawl

Example:

["https://example.com"]

source · string · required

Data source identifier

Example:

"website"

max_crawl_pages · integer · required

Maximum number of pages to crawl

Example:

1

max_crawl_depth · integer · required

Maximum crawl depth

Example:

0

dynamic_content_wait_secs · integer · required

Time to wait for dynamic content to load (in seconds)

Example:

5

actor · string · required

Apify actor used for crawling

Example:

"apify/website-content-crawler"

crawler_type · string · required

Type of crawler used

Example:

"cheerio"

Response

200

application/json

Website successfully crawled and knowledge graph trained

message · string

Example:

"Website training complete"

rag_id · string

Example:

"6848ff3c4c291b4bef798e0c"

pages_trained · integer

Example:

12