获取文档的索引任务

GET

knowledge-fs

spaces

{knowledge_base_id}

logical-documents

{document_id}

processing-tasks

{task_id}

获取文档的索引任务

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

import requests

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

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/{document_id}/processing-tasks/{task_id}', 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/{document_id}/processing-tasks/{task_id}",
  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/{document_id}/processing-tasks/{task_id}"

	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}/logical-documents/{document_id}/processing-tasks/{task_id}")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

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

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

{
  "active_operations": [
    "chunk",
    "fts_index",
    "embedding"
  ],
  "completed_at": null,
  "created_at": "2026-10-20T08:15:42Z",
  "document_id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
  "document_revision": 2,
  "error_code": null,
  "error_message": null,
  "failure": null,
  "id": "c4e8a2f6-1b3d-4e5f-8a9b-0c1d2e3f4a5b",
  "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
  "phase": "chunking_indexing",
  "progress_percent": 35,
  "retry_at": null,
  "semantic_enrichment": {
    "error_code": null,
    "error_message": null,
    "failure": null,
    "nodes_completed": 0,
    "nodes_total": null,
    "provider_calls": null,
    "provider_calls_maximum": null,
    "state": "not_scheduled",
    "updated_at": null
  },
  "stage": "outline_built",
  "state": "running",
  "updated_at": "2026-10-20T08:15:58Z"
}

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。

task_id

string<uuid>

required

索引任务 ID：获取文档或获取文档列表返回的 latest_task.id，或获取文档的索引任务列表返回的 id。该任务必须属于此文档。

Response

索引任务。

active_operations

string[] | null

当前阶段正在进行的操作，例如 parse、chunk、embedding 或 publication。

completed_at

string | null

任务结束时间，ISO 8601 格式。运行期间为 null。

created_at

string

任务创建时间，ISO 8601 格式。获取索引任务以 Unix 纪元毫秒返回同一任务的时间。

document_id

string

文档 ID。

document_revision

integer

此任务构建的修订版本。

error_code

string | null

state 为 failed 时的错误码。

error_message

string | null

error_code 对应的错误消息，可能与 failure.message 不同。

failure

object | null

state 为 failed 时的错误详情。其中 stage 为任务失败时所处的 phase，traceId 为任务 ID。其他情况下为 null。

Show child attributes

string

索引任务 ID。同一 ID 可用于获取索引任务、取消索引任务和重试索引任务。

knowledge_space_id

string

知识库的内部 ID，并非路径中的知识库 ID。

phase

string | null

任务当前执行的环节：queued、parsing、outline_summary、chunking_indexing、graph_admission、publication 或 complete。

progress_percent

integer

进度，取值 0～100，由 stage 推算。

retry_at

string | null

自动重试的时间，ISO 8601 格式。state 为 retry_wait 时设置。

semantic_enrichment

object | null

已索引内容的知识图谱构建状态。深度检索和研究检索会沿知识图谱进行。未安排构建时，任务运行期间 state 为 not_scheduled，任务结束后为 disabled。

Show child attributes

stage

string

已到达的最后一个检查点，按推进顺序依次为：queued、parsed、outline_built、nodes_generated、projection_built、smoke_eval_passed、published。任务失败或取消时，该值停在最后到达的检查点，因此结果要看 state。

state

string

运行状态：

dispatch_pending、queued：等待工作进程处理。
retry_wait：已安排在 retry_at 自动重试。
running：工作进程正在索引。
succeeded：修订版本已发布，可响应查询。semantic_enrichment 可能仍在运行。
failed：详见 failure。可用重试索引任务重新启动。
canceled。
superseded：较新的一次尝试取代了本次尝试。

succeeded、failed、canceled 和 superseded 为终态。

updated_at

string

任务或其语义增强最后变更时间，ISO 8601 格式。

获取文档的索引任务

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

import requests

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

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/{document_id}/processing-tasks/{task_id}', 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/{document_id}/processing-tasks/{task_id}",
  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/{document_id}/processing-tasks/{task_id}"

	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}/logical-documents/{document_id}/processing-tasks/{task_id}")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

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

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

{
  "active_operations": [
    "chunk",
    "fts_index",
    "embedding"
  ],
  "completed_at": null,
  "created_at": "2026-10-20T08:15:42Z",
  "document_id": "2f6b8d1a-7c3e-4a5b-9d0e-1f2a3b4c5d6e",
  "document_revision": 2,
  "error_code": null,
  "error_message": null,
  "failure": null,
  "id": "c4e8a2f6-1b3d-4e5f-8a9b-0c1d2e3f4a5b",
  "knowledge_space_id": "9b2e5b7a-3c1d-4e2f-8a9b-1c2d3e4f5a6b",
  "phase": "chunking_indexing",
  "progress_percent": 35,
  "retry_at": null,
  "semantic_enrichment": {
    "error_code": null,
    "error_message": null,
    "failure": null,
    "nodes_completed": 0,
    "nodes_total": null,
    "provider_calls": null,
    "provider_calls_maximum": null,
    "state": "not_scheduled",
    "updated_at": null
  },
  "stage": "outline_built",
  "state": "running",
  "updated_at": "2026-10-20T08:15:58Z"
}