获取分段列表

列出文档某个修订版本的分段，按分段 ID 排序，而非按在文档中的位置排序。接收获取文档列表返回的文档 ID（而不是文档文件 ID），以及修订版本号。

如需按文档顺序读取分段，获取所有页后按 ordinal 排序。

只要修订版本对应的文档文件版本仍然存在，任何修订版本都可以列出，包括已被取代的修订版本。

文档 ID 与文档文件 ID 的关系，详见浏览文档和分段。

1 min read

get/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks

Request example

curl --request GET \
  --url https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks"
headers = {
    "Authorization": "Bearer <token>",
}

response = requests.request("GET", url, headers=headers)

print(response.text)

const response = await fetch('https://api.dify.ai/v1/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks', {
  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/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks',
  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/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks"

	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/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks"))
    .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/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks')

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_body

Response

{
  "data": [
    {
      "created_at": "2026-09-03T10:04:30Z",
      "document_id": "3d2f1c0b-9a8e-4d7c-b6a5-4f3e2d1c0b9a",
      "document_revision": 2,
      "enabled": true,
      "end_offset": 5120,
      "id": "7a6b5c4d-3e2f-4a1b-9c8d-7e6f5a4b3c2d",
      "kind": "chunk",
      "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
      "ordinal": 14,
      "parent_chunk_id": null,
      "parse_element_ids": [
        "el-40",
        "el-41"
      ],
      "section_path": [
        "3 Employment",
        "3.4 Termination"
      ],
      "start_offset": 4600,
      "text": "Either party may terminate this agreement with thirty days' written notice.",
      "token_count": 131,
      "user_metadata": {}
    }
  ],
  "next_cursor": null
}

{
  "code": "knowledge_fs_invalid_request",
  "message": "Agent Knowledge Base request is invalid.",
  "status": 400,
  "violations": [
    {
      "field": [
        "query"
      ],
      "type": "string_too_long"
    }
  ]
}

{
  "code": "knowledge_fs_invalid_request",
  "message": "Agent Knowledge Base request is invalid.",
  "status": 400
}

{
  "code": "knowledge_fs_invalid_request",
  "failure": {
    "category": "validation",
    "code": "KNOWLEDGE_FS_INVALID_REQUEST",
    "message": "The Agent Knowledge Base request is invalid.",
    "retryPolicy": "never",
    "traceId": "7f3c1a90-2e64-4b7d-8a51-6c0d9e2f4b83"
  },
  "message": "The Agent Knowledge Base request is invalid.",
  "status": 400
}

{
  "code": "knowledge_fs_invalid_credential",
  "message": "Invalid Agent Knowledge Base service credential.",
  "status": 401
}

{
  "code": "unauthorized",
  "message": "Access token is invalid",
  "status": 401
}

{
  "code": "forbidden",
  "message": "Sorry, you have reached the knowledge base request rate limit of your subscription.",
  "status": 403
}

{
  "code": "knowledge_fs_access_denied",
  "message": "Agent Knowledge Base operation is not allowed.",
  "status": 403
}

{
  "code": "knowledge_fs_resource_not_found",
  "failure": {
    "category": "not_found",
    "code": "KNOWLEDGE_FS_NOT_FOUND",
    "message": "The requested Agent Knowledge Base resource was not found.",
    "retryPolicy": "never",
    "traceId": "7f3c1a90-2e64-4b7d-8a51-6c0d9e2f4b83"
  },
  "message": "The requested Agent Knowledge Base resource was not found.",
  "status": 404
}

{
  "code": "not_found",
  "message": "The requested URL was not found on the server. If you entered the URL manually please check your spelling and try again.",
  "status": 404
}

{
  "code": "knowledge_fs_upstream_unavailable",
  "failure": {
    "action": "contact_admin",
    "category": "internal",
    "code": "KNOWLEDGE_FS_INTERNAL_ERROR",
    "message": "Agent Knowledge Base could not complete the operation. Try again, or contact an administrator with the error reference.",
    "retryPolicy": "manual",
    "traceId": "5e2a9c17-3b4d-4f60-8a1b-2c3d4e5f6a7b"
  },
  "message": "Agent Knowledge Base could not complete the operation. Try again, or contact an administrator with the error reference.",
  "status": 502
}

{
  "code": "knowledge_fs_upstream_unavailable",
  "message": "Agent Knowledge Base is unavailable.",
  "status": 502
}

{
  "code": "knowledge_fs_operation_unavailable",
  "message": "Agent Knowledge Base operation is not available.",
  "status": 503
}

{
  "code": "knowledge_fs_operation_unavailable",
  "failure": {
    "action": "retry",
    "category": "dependency",
    "code": "KNOWLEDGE_FS_UNAVAILABLE",
    "message": "A service required by Agent Knowledge Base is temporarily unavailable.",
    "retryPolicy": "manual",
    "traceId": "5e2a9c17-3b4d-4f60-8a1b-2c3d4e5f6a7b"
  },
  "message": "A service required by Agent Knowledge Base is temporarily unavailable.",
  "status": 503
}

get/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks

Authorization

Authorizationstringheaderrequired#

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

knowledge_base_idstringrequired#

知识库 ID：即知识库 API 访问 对话框中所示服务 API 端点的最后一段（…/knowledge-fs/spaces/<knowledge base ID>），也是地址栏中 /datasets/new/ 之后的那一段。

document_idstringrequired#

文档 ID，从获取文档列表获取，或从已打开文档的地址栏中获取（/datasets/new/<knowledge base ID>/documents/<document ID>）。

revisionintegerrequired#

修订版本号。从获取文档修订版本列表获取。

Range: >= 1

Query parameters

cursorstring#

游标，取自上一页的 next_cursor。

Length: 1–1000

querystring#

与 text 匹配的子字符串，不区分大小写。不是语义检索。省略时列出所有分段。

Length: 1–512

limitinteger#

每页分段数。

Default: 50

Range: 1–100

Responses

application/json

一页分段。

dataobject[]#

一页分段，按分段 ID 排序。

Show child attributes

created_atstring#

分段创建时间，ISO 8601 格式。

document_idstring#

文档 ID，即获取文档中的 id。

document_revisioninteger#

分段所属的修订版本。每个修订版本有各自的分段，分段 ID 只能通过其所属的修订版本访问。

enabledboolean#

分段是否参与检索。此 API 中没有可修改该值的操作。

end_offsetinteger#

解析后文档文本中的 UTF-8 字节偏移量，从 0 开始计数，为结束位置（不包含）。未知时为 null。

idstring#

分段 ID，用作获取分段的路径参数 chunk_id。

kindstring#

分段的构建来源：chunk 表示一段正文（默认值），section 表示一个标题章节，table 表示表格，image 表示图片，summary 表示生成的摘要。

knowledge_space_idstring#

知识库的内部 ID，并非路径中的知识库 ID。

ordinalinteger#

分段在修订版本中的位置，从 0 开始。按此值排序即可按文档顺序读取分段。

parent_chunk_idstring#

父子分段模式下父分段的 ID。顶层分段为 null。

parse_element_idsstring[]#

构建该分段所用的解析元素 ID。

section_pathstring[]#

从文档根到该分段所在章节的各级标题。

start_offsetinteger#

解析后文档文本中的 UTF-8 字节偏移量，从 0 开始计数，为起始位置（包含）。未知时为 null。

textstring#

分段内容。

token_countinteger#

text 的 token 数。

user_metadataobject#

附加在分段上的元数据，为自由格式的对象。

next_cursorstring#

下一页的游标，最后一页时为 null。将其作为 cursor 传回。

获取文档修订版本列表获取分段