文档与分段

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。

GET

knowledge-fs

spaces

{knowledge_base_id}

documents

{document_id}

revisions

{revision}

chunks

获取分段列表

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

import requests

url = "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks"

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}/documents/{document_id}/revisions/{revision}/chunks', 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}/documents/{document_id}/revisions/{revision}/chunks",
  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}/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))

}

HttpResponse<String> response = Unirest.get("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks")

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": [
    {
      "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
}

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

knowledge_base_id

string<uuid>

required

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_id

string<uuid>

required

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>）。

revision

integer

required

修订版本号。从获取文档修订版本列表获取。

Required range: x >= 1

Query Parameters

cursor

string

游标，取自上一页的 next_cursor。

Required string length: 1 - 1000

query

string

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。

Required string length: 1 - 512

limit

integer

default:50

每页分段数。

Required range: 1 <= x <= 100

Response

一页分段。

data

object[]

一页分段，按分段 ID 排序。

Show child attributes

next_cursor

string | null

下一页的游标，最后一页时为 null。将其作为 cursor 传回。

获取分段列表

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

import requests

url = "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks"

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}/documents/{document_id}/revisions/{revision}/chunks', 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}/documents/{document_id}/revisions/{revision}/chunks",
  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}/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))

}

HttpResponse<String> response = Unirest.get("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/documents/{document_id}/revisions/{revision}/chunks")

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": [
    {
      "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
}