从文档获取分段

返回文档内分段的分页列表，可按关键词或索引状态筛选。

GET /datasets/{dataset_id}/documents/{document_id}/segments

从文档获取分段

cURL

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

200

success

{
  "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

Authorization · string · header · required

每个请求都通过 API Key 认证：Authorization: Bearer {API_KEY}。应用接口使用应用 API Key，知识库接口使用知识库 API Key（快速开始）。

API Key 应保存在服务端，切勿嵌入客户端代码。缺失或无效的 Key 会返回 HTTP 401（unauthorized）。

Path Parameters

dataset_id · string<uuid> · required

知识库 ID。从 获取知识库列表 获取。

document_id · string<uuid> · required

文档 ID。从 获取知识库的文档列表 获取。

Query Parameters

page · integer · default: 1

页码。

Required range: x >= 1

limit · integer · default: 20

每页的项目数量。服务器上限为 100。

Required range: x >= 1

status · string[]

按索引状态筛选分段，例如 completed、indexing、error。

keyword · string

搜索关键词。

Response

200

application/json

分段列表。

data · object[]

分段列表。

Show child attributes

doc_form · string

该文档使用的分块模式。

total · integer

匹配的分段总数。

has_more · boolean

下一页是否还有更多项目。

limit · integer

每页条目数。

page · integer

当前页码。