数据源同步与导入
获取数据源运行
GET
/
knowledge-fs
/
spaces
/
{knowledge_base_id}
/
source-workflows
/
{run_id}
获取数据源运行
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))
}HttpResponse<String> response = Unirest.get("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}")
.header("Authorization", "Bearer <token>")
.asString();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
每个请求都通过 API 密钥认证:Authorization: Bearer {API_KEY}。应用接口使用应用 API 密钥,知识库接口使用知识库 API 密钥(快速开始)。
API 密钥应保存在服务端,切勿嵌入客户端代码。缺失或无效的密钥会返回 HTTP 401(unauthorized)。
Path Parameters
Response
运行详情。
运行已到达的最后一步:queued、provider-read、preview-staged、selection-frozen、materialized、cleanup-staging 或 source-committed。无论运行停在哪个检查点,重试数据源运行 都会从头开始运行。
工作进程领取该运行的次数,包括 重试数据源运行 之后的领取,重试不会重置该值。
execution_attempts 的上限。达到上限后,重试数据源运行 返回 409。
运行预计处理的项数:导入请求的页面或条目数、抓取预览目前已暂存的页面数,或同步列出数据源条目后的条目数。确定之前为 null。
导入网站页面 的运行抓取 URL 期间,progress_completed 和 progress_total 都统计目前已抓取的页面数。所有 URL 抓取完成后,进度从 0 重新开始计,总数变为 URL 的数量。
Was this page helpful?
⌘I
获取数据源运行
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))
}HttpResponse<String> response = Unirest.get("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/source-workflows/{run_id}")
.header("Authorization", "Bearer <token>")
.asString();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"
}