获取文档详情 - Dify Enterprise Docs

获取文档详情

curl --request GET \
  --url https://{api_base_url}/datasets/{dataset_id}/documents/{document_id} \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://{api_base_url}/datasets/{dataset_id}/documents/{document_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}/datasets/{dataset_id}/documents/{document_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}/datasets/{dataset_id}/documents/{document_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}/datasets/{dataset_id}/documents/{document_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}/datasets/{dataset_id}/documents/{document_id}")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/datasets/{dataset_id}/documents/{document_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

{
  "id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
  "position": 1,
  "data_source_type": "upload_file",
  "data_source_info": {
    "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",
  "dataset_process_rule": {
    "id": "e1f2a3b4-c5d6-7890-ef12-345678901234",
    "mode": "custom"
  },
  "document_process_rule": {
    "mode": "custom",
    "rules": {
      "pre_processing_rules": [],
      "segmentation": {
        "separator": "###",
        "max_tokens": 500,
        "chunk_overlap": 50
      }
    }
  },
  "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",
  "hit_count": 0,
  "doc_form": "text_model",
  "doc_language": "English",
  "doc_type": null,
  "doc_metadata": [],
  "completed_at": 1741267260,
  "updated_at": 1741267260,
  "indexing_latency": 60,
  "segment_count": 5,
  "average_segment_length": 70,
  "summary_index_status": null,
  "need_summary": false
}

GET

datasets

{dataset_id}

documents

{document_id}

获取文档详情

curl --request GET \
  --url https://{api_base_url}/datasets/{dataset_id}/documents/{document_id} \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://{api_base_url}/datasets/{dataset_id}/documents/{document_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}/datasets/{dataset_id}/documents/{document_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}/datasets/{dataset_id}/documents/{document_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}/datasets/{dataset_id}/documents/{document_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}/datasets/{dataset_id}/documents/{document_id}")
  .header("Authorization", "Bearer <token>")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://{api_base_url}/datasets/{dataset_id}/documents/{document_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

{
  "id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
  "position": 1,
  "data_source_type": "upload_file",
  "data_source_info": {
    "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",
  "dataset_process_rule": {
    "id": "e1f2a3b4-c5d6-7890-ef12-345678901234",
    "mode": "custom"
  },
  "document_process_rule": {
    "mode": "custom",
    "rules": {
      "pre_processing_rules": [],
      "segmentation": {
        "separator": "###",
        "max_tokens": 500,
        "chunk_overlap": 50
      }
    }
  },
  "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",
  "hit_count": 0,
  "doc_form": "text_model",
  "doc_language": "English",
  "doc_type": null,
  "doc_metadata": [],
  "completed_at": 1741267260,
  "updated_at": 1741267260,
  "indexing_latency": 60,
  "segment_count": 5,
  "average_segment_length": 70,
  "summary_index_status": null,
  "need_summary": false
}

授权

Authorization

string

header

必填

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）。

路径参数

dataset_id

string<uuid>

必填

知识库 ID。从获取知识库列表获取。

document_id

string<uuid>

必填

文档 ID。从获取知识库的文档列表获取。

查询参数

metadata

enum<string>

默认值:all

all 返回所有字段（包括元数据）。only 仅返回 id、doc_type 和 doc_metadata。without 返回除 doc_metadata 外的所有字段。

可用选项:

all,

only,

without

响应

文档详情。返回的字段取决于 metadata 查询参数。

string

文档标识符。

position

integer

在知识库中的位置索引。

data_source_type

string

文档的上传方式。文件上传为 upload_file，Notion 导入为 notion_import。

data_source_info

object

数据源详情。文件上传时，此详情接口在 upload_file 下返回完整的文件对象，而列表接口仅返回 upload_file_id。

Show child attributes

dataset_process_rule_id

string

应用于该文档的处理规则 ID。

dataset_process_rule

object

知识库级别的处理规则配置。

document_process_rule

object

文档级别的处理规则配置。

name

string

文档名称。

created_from

string

文档来源。通过 API 创建时为 api，通过 UI 创建时为 web。

created_by

string

创建该文档的用户 ID。

created_at

number

文档创建的 Unix 时间戳。

tokens

integer

文档中的令牌数。

indexing_status

string

当前索引状态，例如 waiting、parsing、cleaning、splitting、indexing、completed、error、paused。

error

string | null

索引失败时的错误消息，否则为 null。

enabled

boolean

该文档是否启用检索。

disabled_at

number | null

文档被禁用的 Unix 时间戳，启用时为 null。

disabled_by

string | null

禁用该文档的用户 ID，启用时为 null。

archived

boolean

文档是否已归档。

display_status

string

适合 UI 显示的索引状态。

hit_count

integer

该文档被检索的次数。

doc_form

string

文档分块模式。text_model 表示标准文本，hierarchical_model 表示父子结构，qa_model 表示问答对。

doc_language

string

文档内容的语言。

doc_type

string | null

文档类型分类，未设置时为 null。

doc_metadata

object[]

此文档的自定义元数据键值对。

Show child attributes

completed_at

number | null

处理完成的 Unix 时间戳，尚未完成时为 null。

updated_at

number | null

最后更新的 Unix 时间戳，从未更新时为 null。

indexing_latency

number | null

索引耗时（秒），未完成时为 null。

segment_count

integer

文档中的分段数。

average_segment_length

number

分段的平均字符长度。

summary_index_status

string | null

摘要索引的状态，未启用摘要索引时为 null。

need_summary

boolean

该文档是否需要生成摘要。

获取知识库的文档列表

删除文档