文档与分段

获取文档列表

列出知识库中的文档，最早的在前，包括每个文档的状态、自定义元数据、生效的修订版本和最近一次索引任务。

已禁用的文档也会列出，并带有 enabled: false。文件或数据源正在删除的文档不会列出。一页中的文档可能少于 limit 个，因此要沿 next_cursor 一直翻页，直到它为 null。

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}

logical-documents

获取文档列表

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

import requests

url = "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/logical-documents"

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}/logical-documents', 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}/logical-documents",
  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}/logical-documents"

	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))

}

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/logical-documents")

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": [
    {
      "active": {
        "activated_at": "2026-10-20T08:16:05Z",
        "content_hash": "4f7c2d9a1b3e5f60718293a4b5c6d7e8f9a0b1c2d3e4f5a6b7c8d9e0f1a2b3c4",
        "created_at": "2026-10-20T08:15:42Z",
        "document_asset_id": "6ec0bd7f-11c0-43da-975e-2a8ad9ebae0b",
        "document_asset_version": 1,
        "document_id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
        "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
        "mime_type": "application/pdf",
        "revision": 2,
        "size_bytes": 482113,
        "state": "active"
      },
      "active_revision": 2,
      "created_at": "2026-09-03T10:02:11Z",
      "disabled_at": null,
      "disabled_by_subject_id": null,
      "enabled": true,
      "id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
      "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
      "latest_task": {
        "can_cancel": false,
        "can_retry": false,
        "completed_at": "2026-10-20T08:16:05Z",
        "created_at": "2026-10-20T08:15:42Z",
        "document_id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
        "document_revision": 2,
        "document_title": null,
        "error_code": null,
        "error_message": null,
        "failure": null,
        "failures": null,
        "id": "c4e8a2f6-1b3d-4e5f-8a9b-0c1d2e3f4a5b",
        "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
        "operation": "document_processing",
        "progress_completed": 1,
        "progress_failed": 0,
        "progress_percent": 100,
        "progress_total": 1,
        "semantic_enrichment": {
          "error_code": null,
          "error_message": null,
          "failure": null,
          "nodes_completed": 18,
          "nodes_total": 18,
          "provider_calls": 12,
          "provider_calls_maximum": 200,
          "state": "ready",
          "updated_at": "2026-10-20T08:17:30Z"
        },
        "source_id": null,
        "source_title": null,
        "state": "completed",
        "task_kind": "document",
        "updated_at": "2026-10-20T08:17:30Z"
      },
      "provider_item_id": null,
      "row_version": 4,
      "source_id": null,
      "status": "ready",
      "title": "handbook.pdf",
      "updated_at": "2026-10-20T08:16:05Z",
      "user_metadata": {
        "owner": "support-team",
        "product_line": "billing",
        "review_date": "2026-12-01T00:00:00Z"
      }
    },
    {
      "active": {
        "activated_at": "2026-10-19T03:04:51Z",
        "content_hash": "9c1e5b7d3f2a4c6e8b0d1f3a5c7e9b2d4f6a8c0e1b3d5f7a9c2e4b6d8f0a1c3e",
        "created_at": "2026-10-19T03:04:12Z",
        "document_asset_id": "7d2e4f6a-8b0c-4d1e-9f3a-5b7c9d1e3f5a",
        "document_asset_version": 1,
        "document_id": "3a7e9c1b-5d2f-4e8a-9b0c-1d2e3f4a5b6c",
        "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
        "mime_type": "text/markdown",
        "revision": 1,
        "size_bytes": 18342,
        "state": "active"
      },
      "active_revision": 1,
      "created_at": "2026-10-19T03:04:12Z",
      "disabled_at": null,
      "disabled_by_subject_id": null,
      "enabled": true,
      "id": "3a7e9c1b-5d2f-4e8a-9b0c-1d2e3f4a5b6c",
      "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
      "latest_task": null,
      "provider_item_id": "5e0f9a6c2b8d4e1f7a3c9b5d1e7f3a9c5b1d7e3f9a5c1b7d3e9f5a1c7b3d9e5f",
      "row_version": 1,
      "source_id": "6f1c2b0e-3d0b-4a5e-9f4c-1c0e6a7b8d90",
      "status": "ready",
      "title": "Pricing | Docs site",
      "updated_at": "2026-10-19T03:04:51Z",
      "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。

Query Parameters

cursor

string

游标，取自上一页的 next_cursor。

Required string length: 1 - 1000

limit

integer

default:50

每页文档数。

Required range: 1 <= x <= 100

Response

一页文档。

data

object[]

一页文档，最早的在前。

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。

获取文档列表

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

import requests

url = "https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/logical-documents"

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}/logical-documents', 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}/logical-documents",
  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}/logical-documents"

	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))

}

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/knowledge-fs/spaces/{knowledge_base_id}/logical-documents")

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": [
    {
      "active": {
        "activated_at": "2026-10-20T08:16:05Z",
        "content_hash": "4f7c2d9a1b3e5f60718293a4b5c6d7e8f9a0b1c2d3e4f5a6b7c8d9e0f1a2b3c4",
        "created_at": "2026-10-20T08:15:42Z",
        "document_asset_id": "6ec0bd7f-11c0-43da-975e-2a8ad9ebae0b",
        "document_asset_version": 1,
        "document_id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
        "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
        "mime_type": "application/pdf",
        "revision": 2,
        "size_bytes": 482113,
        "state": "active"
      },
      "active_revision": 2,
      "created_at": "2026-09-03T10:02:11Z",
      "disabled_at": null,
      "disabled_by_subject_id": null,
      "enabled": true,
      "id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
      "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
      "latest_task": {
        "can_cancel": false,
        "can_retry": false,
        "completed_at": "2026-10-20T08:16:05Z",
        "created_at": "2026-10-20T08:15:42Z",
        "document_id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
        "document_revision": 2,
        "document_title": null,
        "error_code": null,
        "error_message": null,
        "failure": null,
        "failures": null,
        "id": "c4e8a2f6-1b3d-4e5f-8a9b-0c1d2e3f4a5b",
        "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
        "operation": "document_processing",
        "progress_completed": 1,
        "progress_failed": 0,
        "progress_percent": 100,
        "progress_total": 1,
        "semantic_enrichment": {
          "error_code": null,
          "error_message": null,
          "failure": null,
          "nodes_completed": 18,
          "nodes_total": 18,
          "provider_calls": 12,
          "provider_calls_maximum": 200,
          "state": "ready",
          "updated_at": "2026-10-20T08:17:30Z"
        },
        "source_id": null,
        "source_title": null,
        "state": "completed",
        "task_kind": "document",
        "updated_at": "2026-10-20T08:17:30Z"
      },
      "provider_item_id": null,
      "row_version": 4,
      "source_id": null,
      "status": "ready",
      "title": "handbook.pdf",
      "updated_at": "2026-10-20T08:16:05Z",
      "user_metadata": {
        "owner": "support-team",
        "product_line": "billing",
        "review_date": "2026-12-01T00:00:00Z"
      }
    },
    {
      "active": {
        "activated_at": "2026-10-19T03:04:51Z",
        "content_hash": "9c1e5b7d3f2a4c6e8b0d1f3a5c7e9b2d4f6a8c0e1b3d5f7a9c2e4b6d8f0a1c3e",
        "created_at": "2026-10-19T03:04:12Z",
        "document_asset_id": "7d2e4f6a-8b0c-4d1e-9f3a-5b7c9d1e3f5a",
        "document_asset_version": 1,
        "document_id": "3a7e9c1b-5d2f-4e8a-9b0c-1d2e3f4a5b6c",
        "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
        "mime_type": "text/markdown",
        "revision": 1,
        "size_bytes": 18342,
        "state": "active"
      },
      "active_revision": 1,
      "created_at": "2026-10-19T03:04:12Z",
      "disabled_at": null,
      "disabled_by_subject_id": null,
      "enabled": true,
      "id": "3a7e9c1b-5d2f-4e8a-9b0c-1d2e3f4a5b6c",
      "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
      "latest_task": null,
      "provider_item_id": "5e0f9a6c2b8d4e1f7a3c9b5d1e7f3a9c5b1d7e3f9a5c1b7d3e9f5a1c7b3d9e5f",
      "row_version": 1,
      "source_id": "6f1c2b0e-3d0b-4a5e-9f4c-1c0e6a7b8d90",
      "status": "ready",
      "title": "Pricing | Docs site",
      "updated_at": "2026-10-19T03:04:51Z",
      "user_metadata": {}
    }
  ],
  "next_cursor": null
}