用文本更新文档

更新文档的文本内容、名称或处理配置。文本变更时会重新索引文档。

POST /datasets/{dataset_id}/documents/{document_id}/update-by-text

用文本更新文档

cURL

curl --request POST \
  --url https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "text": "<string>",
  "doc_form": "text_model",
  "doc_language": "English"
}
'

import requests

url = "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text"

payload = {
    "name": "<string>",
    "text": "<string>",
    "doc_form": "text_model",
    "doc_language": "English"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    text: '<string>',
    doc_form: 'text_model',
    doc_language: 'English'
  })
};

fetch('https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text', 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}/update-by-text",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>',
    'text' => '<string>',
    'doc_form' => 'text_model',
    'doc_language' => 'English'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"text\": \"<string>\",\n  \"doc_form\": \"text_model\",\n  \"doc_language\": \"English\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"text\": \"<string>\",\n  \"doc_form\": \"text_model\",\n  \"doc_language\": \"English\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/update-by-text")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"text\": \"<string>\",\n  \"doc_form\": \"text_model\",\n  \"doc_language\": \"English\"\n}"

response = http.request(request)
puts response.read_body

200

success

{
  "document": {
    "id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
    "position": 1,
    "data_source_type": "upload_file",
    "data_source_info": {
      "upload_file_id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890"
    },
    "data_source_detail_dict": {
      "upload_file": {
        "id": "a1b2c3d4-e5f6-7890-abcd-ef1234567890",
        "name": "guide.txt",
        "size": 2048,
        "extension": "txt",
        "mime_type": "text/plain",
        "created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
        "created_at": 1741267200
      }
    },
    "dataset_process_rule_id": "e1f2a3b4-c5d6-7890-ef12-345678901234",
    "name": "guide.txt",
    "created_from": "api",
    "created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
    "created_at": 1741267200,
    "tokens": 512,
    "indexing_status": "completed",
    "error": null,
    "enabled": true,
    "disabled_at": null,
    "disabled_by": null,
    "archived": false,
    "display_status": "available",
    "word_count": 350,
    "hit_count": 0,
    "doc_form": "text_model",
    "doc_metadata": [],
    "summary_index_status": null,
    "need_summary": false
  },
  "batch": "20250306150245647595"
}

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。

Body

application/json

name · string

文档名称。当提供 text 时必填。

text · string

文档文本内容。

process_rule · object

分块处理规则。

Show child attributes

doc_form · enum<string> · default: text_model

text_model 为标准文本分段，hierarchical_model 为父子分段结构，qa_model 为问答对提取。

Available options: text_model, hierarchical_model, qa_model

doc_language · string · default: English

用于处理优化的文档语言。

retrieval_model · object

控制查询此知识库时如何搜索和排序分段。

Show child attributes

Response

200

application/json

文档更新成功。

document · object

Show child attributes

batch · string

用于跟踪索引进度的批次 ID。