向文档添加分段

在文档中创建一个或多个分段。

POST /datasets/{dataset_id}/documents/{document_id}/segments

向文档添加分段

cURL

curl --request POST \
  --url https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "segments": [
    {
      "content": "<string>",
      "answer": "<string>",
      "keywords": [
        "<string>"
      ],
      "attachment_ids": [
        "<string>"
      ]
    }
  ]
}
'

import requests

url = "https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments"

payload = { "segments": [
        {
            "content": "<string>",
            "answer": "<string>",
            "keywords": ["<string>"],
            "attachment_ids": ["<string>"]
        }
    ] }
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({
    segments: [
      {
        content: '<string>',
        answer: '<string>',
        keywords: ['<string>'],
        attachment_ids: ['<string>']
      }
    ]
  })
};

fetch('https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments', 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}/segments",
  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([
    'segments' => [
        [
                'content' => '<string>',
                'answer' => '<string>',
                'keywords' => [
                                '<string>'
                ],
                'attachment_ids' => [
                                '<string>'
                ]
        ]
    ]
  ]),
  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}/segments"

	payload := strings.NewReader("{\n  \"segments\": [\n    {\n      \"content\": \"<string>\",\n      \"answer\": \"<string>\",\n      \"keywords\": [\n        \"<string>\"\n      ],\n      \"attachment_ids\": [\n        \"<string>\"\n      ]\n    }\n  ]\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}/segments")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"segments\": [\n    {\n      \"content\": \"<string>\",\n      \"answer\": \"<string>\",\n      \"keywords\": [\n        \"<string>\"\n      ],\n      \"attachment_ids\": [\n        \"<string>\"\n      ]\n    }\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/datasets/{dataset_id}/documents/{document_id}/segments")

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  \"segments\": [\n    {\n      \"content\": \"<string>\",\n      \"answer\": \"<string>\",\n      \"keywords\": [\n        \"<string>\"\n      ],\n      \"attachment_ids\": [\n        \"<string>\"\n      ]\n    }\n  ]\n}"

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

200

success

{
  "data": [
    {
      "id": "f3d1c7be-9f3a-40d8-8eb8-3a1ef9c3f2c1",
      "position": 1,
      "document_id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
      "content": "Dify is an open-source LLM app development platform.",
      "sign_content": "",
      "answer": "",
      "word_count": 9,
      "tokens": 12,
      "keywords": [
        "dify",
        "platform",
        "llm"
      ],
      "index_node_id": "a1b2c3d4-e5f6-7890-abcd-000000000001",
      "index_node_hash": "abc123def456",
      "hit_count": 0,
      "enabled": true,
      "disabled_at": null,
      "disabled_by": null,
      "status": "completed",
      "created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
      "created_at": 1741267200,
      "updated_at": 1741267200,
      "updated_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
      "indexing_at": 1741267200,
      "completed_at": 1741267200,
      "error": null,
      "stopped_at": null,
      "child_chunks": [],
      "attachments": [],
      "summary": null
    }
  ],
  "doc_form": "text_model"
}

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

segments · object[] · required

要创建的分段对象数组。

Minimum array length: 1

Show child attributes

Response

200

application/json

分段创建成功。

data · object[]

已创建的分段列表。

Show child attributes

doc_form · string

该文档使用的分块模式。