List Crawl Preview Pages

get/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages

Request example

curl --request GET \
  --url https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages"
headers = {
    "Authorization": "Bearer <token>",
}

response = requests.request("GET", url, headers=headers)

print(response.text)

const response = await fetch('https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages', {
  method: 'GET',
  headers: {
    'Authorization': 'Bearer <token>'
  }
});

const data = await response.json();
console.log(data);

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => 'https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_CUSTOMREQUEST => 'GET',
  CURLOPT_HTTPHEADER => [
    'Authorization: Bearer <token>',
  ],
]);

$response = curl_exec($curl);
curl_close($curl);

echo $response;

package main

import (
	"fmt"
	"io"
	"net/http"
)

func main() {
	url := "https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages"

	req, _ := http.NewRequest("GET", url, nil)
	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)
	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))
}

HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages"))
    .header("Authorization", "Bearer <token>")
    .method("GET", HttpRequest.BodyPublishers.noBody())
    .build();

HttpResponse<String> response = HttpClient.newHttpClient()
    .send(request, HttpResponse.BodyHandlers.ofString());

System.out.println(response.body());

require 'uri'
require 'net/http'

url = URI('https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages')

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = url.scheme == 'https'

request = Net::HTTP::Get.new(url)
request['Authorization'] = 'Bearer <token>'

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

Response

{
  "data": [
    {
      "description": "How invoices, plans, and payment methods work.",
      "etag": null,
      "page_id": "0b6e9a1f3c5d7e9f1a3b5c7d9e1f3a5b7c9d1e3f5a7b9c1d3e5f7a9b1c3d5e7f",
      "source_url": "https://docs.example.com/guides/billing",
      "title": "Billing | Docs site"
    },
    {
      "description": null,
      "etag": null,
      "page_id": "5e0f9a6c2b8d4e1f7a3c9b5d1e7f3a9c5b1d7e3f9a5c1b7d3e9f5a1c7b3d9e5f",
      "source_url": "https://docs.example.com/pricing",
      "title": "Pricing | Docs site"
    }
  ],
  "next_cursor": null
}

{
  "code": "knowledge_fs_invalid_request",
  "message": "Agent Knowledge Base request is invalid.",
  "status": 400,
  "violations": [
    {
      "field": [
        "limit"
      ],
      "type": "less_than_equal"
    }
  ]
}

{
  "code": "knowledge_fs_invalid_request",
  "message": "Agent Knowledge Base request is invalid.",
  "status": 400
}

{
  "code": "knowledge_fs_invalid_request",
  "failure": {
    "category": "validation",
    "code": "KNOWLEDGE_FS_INVALID_REQUEST",
    "message": "The Agent Knowledge Base request is invalid.",
    "retryPolicy": "never",
    "traceId": "7f3c1a90-2e64-4b7d-8a51-6c0d9e2f4b83"
  },
  "message": "The Agent Knowledge Base request is invalid.",
  "status": 400
}

{
  "code": "knowledge_fs_invalid_credential",
  "message": "Invalid Agent Knowledge Base service credential.",
  "status": 401
}

{
  "code": "unauthorized",
  "message": "Access token is invalid",
  "status": 401
}

{
  "code": "forbidden",
  "message": "Sorry, you have reached the knowledge base request rate limit of your subscription.",
  "status": 403
}

{
  "code": "knowledge_fs_access_denied",
  "message": "Agent Knowledge Base operation is not allowed.",
  "status": 403
}

{
  "code": "knowledge_fs_resource_not_found",
  "failure": {
    "category": "not_found",
    "code": "KNOWLEDGE_FS_NOT_FOUND",
    "message": "The requested Agent Knowledge Base resource was not found.",
    "retryPolicy": "never",
    "traceId": "7f3c1a90-2e64-4b7d-8a51-6c0d9e2f4b83"
  },
  "message": "The requested Agent Knowledge Base resource was not found.",
  "status": 404
}

{
  "code": "not_found",
  "message": "The requested URL was not found on the server. If you entered the URL manually please check your spelling and try again.",
  "status": 404
}

{
  "code": "knowledge_fs_upstream_unavailable",
  "failure": {
    "action": "contact_admin",
    "category": "internal",
    "code": "KNOWLEDGE_FS_INTERNAL_ERROR",
    "message": "Agent Knowledge Base could not complete the operation. Try again, or contact an administrator with the error reference.",
    "retryPolicy": "manual",
    "traceId": "5e2a9c17-3b4d-4f60-8a1b-2c3d4e5f6a7b"
  },
  "message": "Agent Knowledge Base could not complete the operation. Try again, or contact an administrator with the error reference.",
  "status": 502
}

{
  "code": "knowledge_fs_upstream_unavailable",
  "message": "Agent Knowledge Base is unavailable.",
  "status": 502
}

{
  "code": "knowledge_fs_operation_unavailable",
  "message": "Agent Knowledge Base operation is not available.",
  "status": 503
}

{
  "code": "knowledge_fs_operation_unavailable",
  "failure": {
    "action": "retry",
    "category": "dependency",
    "code": "KNOWLEDGE_FS_UNAVAILABLE",
    "message": "A service required by Agent Knowledge Base is temporarily unavailable.",
    "retryPolicy": "manual",
    "traceId": "5e2a9c17-3b4d-4f60-8a1b-2c3d4e5f6a7b"
  },
  "message": "A service required by Agent Knowledge Base is temporarily unavailable.",
  "status": 503
}

get/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}/pages

Authorization

Authorizationstringheaderrequired#

Every request authenticates with an API key: Authorization: Bearer {API_KEY}. App endpoints take an app API key; knowledge endpoints take a knowledge base API key (Get Started).

Keep keys server-side; never embed them in client code. Requests with a missing or invalid key fail with HTTP 401 (unauthorized).

Path parameters

knowledge_base_idstringrequired#

Knowledge base ID: the last segment of the Service API endpoint shown in the knowledge base's API Access dialog (…/knowledge-fs/spaces/<knowledge base ID>), and the segment after /datasets/new/ in the address bar.

run_idstringrequired#

Run ID of a crawl preview: id from Preview Website Crawl, List Source Runs, or Get Source Run.

Query parameters

cursorstring#

Cursor from the previous page's next_cursor.

Length: 1–4096

limitinteger#

Pages per response.

Default: 50

Range: 1–200

Responses

application/json

One page of crawled pages.

dataobject[]#

Crawled pages, ordered by page_id.

Show child attributes

descriptionstring#

Page description. null when the page has none.

etagstring#

Always null for crawl previews.

page_idstring#

Page ID. Pass it in pageIds to Import Selected Pages.

source_urlstring#

URL the page was crawled from.

titlestring#

Page title. null when the page has none.

next_cursorstring#

Cursor for the next page, or null on the last page. Send it back as cursor.

Preview Website Crawl Import Selected Pages