获取文档嵌入状态(进度)
返回批次中每个文档的索引进度:当前阶段和分段完成计数。轮询直到每个
indexing_status 变为 completed 或 error。状态按 waiting → parsing → cleaning → splitting → indexing → completed 推进。1 min read
get/datasets/{dataset_id}/documents/{batch}/indexing-status
Request example
curl --request GET \
--url https://api.dify.ai/v1/datasets/{dataset_id}/documents/{batch}/indexing-status \
--header 'Authorization: Bearer <token>'import requests
url = "https://api.dify.ai/v1/datasets/{dataset_id}/documents/{batch}/indexing-status"
headers = {
"Authorization": "Bearer <token>",
}
response = requests.request("GET", url, headers=headers)
print(response.text)const response = await fetch('https://api.dify.ai/v1/datasets/{dataset_id}/documents/{batch}/indexing-status', {
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/datasets/{dataset_id}/documents/{batch}/indexing-status',
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/datasets/{dataset_id}/documents/{batch}/indexing-status"
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/datasets/{dataset_id}/documents/{batch}/indexing-status"))
.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/datasets/{dataset_id}/documents/{batch}/indexing-status')
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_bodyResponse
{
"data": [
{
"cleaning_completed_at": 1741267200,
"completed_at": 1741267200,
"completed_segments": 5,
"error": null,
"id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
"indexing_status": "completed",
"parsing_completed_at": 1741267200,
"paused_at": null,
"processing_started_at": 1741267200,
"splitting_completed_at": 1741267200,
"stopped_at": null,
"total_segments": 5
}
]
}{
"code": "forbidden",
"message": "Dataset api access is not enabled.",
"status": 403
}{
"code": "forbidden",
"message": "The API key is not authorized to access this knowledge base.",
"status": 403
}{
"code": "not_found",
"message": "Dataset not found.",
"status": 404
}{
"code": "not_found",
"message": "Documents not found.",
"status": 404
}get/datasets/{dataset_id}/documents/{batch}/indexing-status
Authorization
Path parameters
知识库 ID,通过 获取知识库列表 获取。使用限定范围的密钥时,从 Dify 页面 URL 复制 ID。
创建或更新文档时返回的批次 ID。
Responses
application/json
批次中文档的索引状态。
索引状态条目列表。
Show child attributesHide child attributes
清洗完成的 Unix 时间戳。
索引完成的 Unix 时间戳。
已索引的分段数。
索引失败时的错误信息。无错误时为
null。文档标识符。
当前索引状态:
waiting、parsing、cleaning、splitting、indexing、completed 或 error。解析完成的 Unix 时间戳。
索引暂停的时间戳。未暂停时为
null。处理开始的 Unix 时间戳。
拆分完成的 Unix 时间戳。
索引停止的时间戳。未停止时为
null。待索引的分段总数。