分段
从文档获取分段
返回文档内分段的分页列表。支持按关键词和状态筛选。
GET
/
datasets
/
{dataset_id}
/
documents
/
{document_id}
/
segments
从文档获取分段
curl --request GET \
--url https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments \
--header 'Authorization: Bearer <token>'import requests
url = "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments"
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}/datasets/{dataset_id}/documents/{document_id}/segments', 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}/datasets/{dataset_id}/documents/{document_id}/segments",
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}/datasets/{dataset_id}/documents/{document_id}/segments"
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}/datasets/{dataset_id}/documents/{document_id}/segments")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments")
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{
"data": [
{
"id": "f3d1c7be-9f3a-40d8-8eb8-3a1ef9c3f2c1",
"position": 1,
"document_id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
"content": "Dify is an open-source LLM app development platform.",
"sign_content": "",
"answer": "",
"word_count": 9,
"tokens": 12,
"keywords": [
"dify",
"platform",
"llm"
],
"index_node_id": "a1b2c3d4-e5f6-7890-abcd-000000000001",
"index_node_hash": "abc123def456",
"hit_count": 0,
"enabled": true,
"disabled_at": null,
"disabled_by": null,
"status": "completed",
"created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"created_at": 1741267200,
"updated_at": 1741267200,
"updated_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"indexing_at": 1741267200,
"completed_at": 1741267200,
"error": null,
"stopped_at": null,
"child_chunks": [],
"attachments": [],
"summary": null
}
],
"doc_form": "text_model",
"total": 1,
"has_more": false,
"limit": 20,
"page": 1
}Authorizations
API Key 认证。对于所有 API 请求,请在 Authorization HTTP 头中包含您的 API Key,并加上 Bearer 前缀。示例:Authorization: Bearer {API_KEY}。强烈建议将 API Key 存储在服务端,不要在客户端共享或存储,以避免 API Key 泄漏导致严重后果。缺少或无效的 API Key 会返回 HTTP 401,错误码为 unauthorized。
Query Parameters
要获取的页码。
每页的项目数量。服务器上限为 100。
按索引状态筛选分段,例如 completed、indexing、error。
搜索关键词。
Last modified on July 9, 2026
Was this page helpful?
⌘I
从文档获取分段
curl --request GET \
--url https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments \
--header 'Authorization: Bearer <token>'import requests
url = "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments"
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}/datasets/{dataset_id}/documents/{document_id}/segments', 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}/datasets/{dataset_id}/documents/{document_id}/segments",
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}/datasets/{dataset_id}/documents/{document_id}/segments"
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}/datasets/{dataset_id}/documents/{document_id}/segments")
.header("Authorization", "Bearer <token>")
.asString();require 'uri'
require 'net/http'
url = URI("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments")
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{
"data": [
{
"id": "f3d1c7be-9f3a-40d8-8eb8-3a1ef9c3f2c1",
"position": 1,
"document_id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
"content": "Dify is an open-source LLM app development platform.",
"sign_content": "",
"answer": "",
"word_count": 9,
"tokens": 12,
"keywords": [
"dify",
"platform",
"llm"
],
"index_node_id": "a1b2c3d4-e5f6-7890-abcd-000000000001",
"index_node_hash": "abc123def456",
"hit_count": 0,
"enabled": true,
"disabled_at": null,
"disabled_by": null,
"status": "completed",
"created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"created_at": 1741267200,
"updated_at": 1741267200,
"updated_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
"indexing_at": 1741267200,
"completed_at": 1741267200,
"error": null,
"stopped_at": null,
"child_chunks": [],
"attachments": [],
"summary": null
}
],
"doc_form": "text_model",
"total": 1,
"has_more": false,
"limit": 20,
"page": 1
}