Source Syncs and Imports

Get Source Run

Returns one source run. Use it to follow any run by ID, including crawl previews and imports from them, which List Sources does not show.

A run that ends completed has imported or refreshed every item, indexed it, and made it active. The run waits up to 10 minutes for each document’s indexing, and a document that takes longer fails it.

After failed, read failure, then call Retry Source Run or start a new run with a new Idempotency-Key.

For how to follow, retry, and cancel runs, see Follow Source Runs.

GET

knowledge-fs

spaces

{knowledge_base_id}

source-workflows

{run_id}

Get Source Run

curl --request GET \
  --url https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id} \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}', 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_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}"

	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))

}

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}")

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

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

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

{
  "canceled_at": null,
  "checkpoint": "source-committed",
  "completed_at": "2026-10-20T10:03:18Z",
  "created_at": "2026-10-20T10:00:00Z",
  "cursor": null,
  "execution_attempts": 1,
  "failure": null,
  "id": "e1f2a3b4-c5d6-4e7f-8a9b-0c1d2e3f4a5b",
  "kind": "crawl-import",
  "knowledge_space_id": "0a9d3c2e-5b6f-4e1a-8c7d-2f3e4a5b6c7d",
  "last_error_code": null,
  "max_execution_attempts": 5,
  "progress_completed": 2,
  "progress_failed": 0,
  "progress_skipped": 0,
  "progress_total": 2,
  "source_id": "6f1c2b0e-3d0b-4a5e-9f4c-1c0e6a7b8d90",
  "state": "completed",
  "updated_at": "2026-10-20T10:03:18Z"
}

Authorizations

Authorization

string

header

required

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_id

string<uuid>

required

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_id

string<uuid>

required

Run ID, from the response that started the run (id), from Update Source (sync_workflow.id), or from List Source Runs (id).

Response

The run.

canceled_at

string | null

When the run was canceled. null unless state is canceled.

checkpoint

string

Last step the run reached: queued, provider-read, preview-staged, selection-frozen, materialized, cleanup-staging, or source-committed. Retry Source Run starts the run over whatever its checkpoint.

completed_at

string | null

When the run ended (completed, zero_results, failed, or canceled), ISO 8601. null while it runs.

created_at

string

Creation time, ISO 8601.

cursor

string | null

Provider cursor the run resumes from. null when the run has not paged.

execution_attempts

integer

Times a worker has picked up the run, including after Retry Source Run, which does not reset it.

failure

object | null

Error details when state is failed. stage is the run's checkpoint at the failure, and traceId is the run ID. null otherwise.

Show child attributes

string

Run ID. Pass it to Get Source Run, Cancel Source Run, or Retry Source Run.

kind

string

What the run does:

sync: started by Sync Source, Update Source, a schedule, or Dify.
crawl-preview: started by Preview Website Crawl. It keeps this kind while Import Selected Pages imports from it.
crawl-import: started by Import Website Pages.
online-document-import, online-drive-import: started by Import Source Items.

Dify also starts previews and imports when a source is added or edited there.

knowledge_space_id

string

Internal ID of the knowledge base. Not the knowledge base ID in the path.

last_error_code

string | null

failure.code when state is failed. null otherwise.

max_execution_attempts

integer

Limit on execution_attempts. Once it is reached, Retry Source Run answers 409.

progress_completed

integer

Items finished, including unchanged items a sync checked.

progress_failed

integer

Always 0 for source runs: a failing item fails the whole run.

progress_skipped

integer

Always 0 for source runs.

progress_total

integer | null

Items the run expects to process: the pages or items an import requested, the pages a crawl preview has staged so far, or the source's items once a sync has listed them. null until known.

While an Import Website Pages run crawls its URLs, progress_completed and progress_total both count the pages crawled so far. Once every URL is crawled, they restart at 0 of the number of URLs.

source_id

string | null

Source the run belongs to.

state

string

Progress of the run.

Live states:

queued: waiting for a worker
crawling: a crawl preview is fetching pages
preview_ready: a crawl preview is waiting for Import Selected Pages or Cancel Source Run
importing: importing and indexing items
syncing: refreshing the source's documents

Terminal states:

completed: every item was imported or refreshed, indexed, and made active
zero_results: a crawl preview found no pages
failed: see failure
canceled

After failed or canceled, Retry Source Run runs it again, and Sync Source starts a new sync.

updated_at

string

Last change, ISO 8601.

Get Source Run

curl --request GET \
  --url https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id} \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}', 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_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "GET",
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

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

func main() {

	url := "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}"

	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))

}

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}")

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

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

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

{
  "canceled_at": null,
  "checkpoint": "source-committed",
  "completed_at": "2026-10-20T10:03:18Z",
  "created_at": "2026-10-20T10:00:00Z",
  "cursor": null,
  "execution_attempts": 1,
  "failure": null,
  "id": "e1f2a3b4-c5d6-4e7f-8a9b-0c1d2e3f4a5b",
  "kind": "crawl-import",
  "knowledge_space_id": "0a9d3c2e-5b6f-4e1a-8c7d-2f3e4a5b6c7d",
  "last_error_code": null,
  "max_execution_attempts": 5,
  "progress_completed": 2,
  "progress_failed": 0,
  "progress_skipped": 0,
  "progress_total": 2,
  "source_id": "6f1c2b0e-3d0b-4a5e-9f4c-1c0e6a7b8d90",
  "state": "completed",
  "updated_at": "2026-10-20T10:03:18Z"
}

Guides

App APIs

Knowledge APIs

Get Source Run

Authorizations

Path Parameters

Response