更新知识库 - Dify Enterprise Docs

更新知识库

curl --request PATCH \
  --url https://{api_base_url}/datasets/{dataset_id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "description": "<string>",
  "embedding_model": "<string>",
  "embedding_model_provider": "<string>",
  "partial_member_list": [
    {
      "user_id": "<string>"
    }
  ],
  "external_retrieval_model": {
    "top_k": 123,
    "score_threshold": 123,
    "score_threshold_enabled": true
  },
  "external_knowledge_id": "<string>",
  "external_knowledge_api_id": "<string>"
}
'

import requests

url = "https://{api_base_url}/datasets/{dataset_id}"

payload = {
    "name": "<string>",
    "description": "<string>",
    "embedding_model": "<string>",
    "embedding_model_provider": "<string>",
    "partial_member_list": [{ "user_id": "<string>" }],
    "external_retrieval_model": {
        "top_k": 123,
        "score_threshold": 123,
        "score_threshold_enabled": True
    },
    "external_knowledge_id": "<string>",
    "external_knowledge_api_id": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'PATCH',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    description: '<string>',
    embedding_model: '<string>',
    embedding_model_provider: '<string>',
    partial_member_list: [{user_id: '<string>'}],
    external_retrieval_model: {top_k: 123, score_threshold: 123, score_threshold_enabled: true},
    external_knowledge_id: '<string>',
    external_knowledge_api_id: '<string>'
  })
};

fetch('https://{api_base_url}/datasets/{dataset_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}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PATCH",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>',
    'description' => '<string>',
    'embedding_model' => '<string>',
    'embedding_model_provider' => '<string>',
    'partial_member_list' => [
        [
                'user_id' => '<string>'
        ]
    ],
    'external_retrieval_model' => [
        'top_k' => 123,
        'score_threshold' => 123,
        'score_threshold_enabled' => true
    ],
    'external_knowledge_id' => '<string>',
    'external_knowledge_api_id' => '<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}"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"partial_member_list\": [\n    {\n      \"user_id\": \"<string>\"\n    }\n  ],\n  \"external_retrieval_model\": {\n    \"top_k\": 123,\n    \"score_threshold\": 123,\n    \"score_threshold_enabled\": true\n  },\n  \"external_knowledge_id\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\"\n}")

	req, _ := http.NewRequest("PATCH", 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.patch("https://{api_base_url}/datasets/{dataset_id}")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"partial_member_list\": [\n    {\n      \"user_id\": \"<string>\"\n    }\n  ],\n  \"external_retrieval_model\": {\n    \"top_k\": 123,\n    \"score_threshold\": 123,\n    \"score_threshold_enabled\": true\n  },\n  \"external_knowledge_id\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"partial_member_list\": [\n    {\n      \"user_id\": \"<string>\"\n    }\n  ],\n  \"external_retrieval_model\": {\n    \"top_k\": 123,\n    \"score_threshold\": 123,\n    \"score_threshold_enabled\": true\n  },\n  \"external_knowledge_id\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\"\n}"

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

{
  "id": "c42e2a6e-40b3-4330-96f8-f1e4d768e8c9",
  "name": "Product Documentation",
  "description": "产品 API 技术文档",
  "provider": "vendor",
  "permission": "only_me",
  "data_source_type": null,
  "indexing_technique": "high_quality",
  "app_count": 0,
  "document_count": 0,
  "word_count": 0,
  "created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
  "author_name": "admin",
  "created_at": 1741267200,
  "updated_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
  "updated_at": 1741267200,
  "embedding_model": "text-embedding-3-small",
  "embedding_model_provider": "langgenius/openai/openai",
  "embedding_available": true,
  "retrieval_model_dict": {
    "search_method": "semantic_search",
    "reranking_enable": false,
    "reranking_mode": null,
    "reranking_model": {
      "reranking_provider_name": "",
      "reranking_model_name": ""
    },
    "weights": null,
    "top_k": 3,
    "score_threshold_enabled": false,
    "score_threshold": null
  },
  "tags": [],
  "doc_form": "text_model",
  "external_knowledge_info": null,
  "external_retrieval_model": null,
  "doc_metadata": [],
  "built_in_field_enabled": true,
  "pipeline_id": null,
  "runtime_mode": null,
  "chunk_structure": null,
  "icon_info": null,
  "summary_index_setting": null,
  "is_published": false,
  "total_documents": 0,
  "total_available_documents": 0,
  "enable_api": true,
  "is_multimodal": false,
  "maintainer": "admin",
  "partial_member_list": []
}

PATCH

datasets

{dataset_id}

更新知识库

curl --request PATCH \
  --url https://{api_base_url}/datasets/{dataset_id} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "name": "<string>",
  "description": "<string>",
  "embedding_model": "<string>",
  "embedding_model_provider": "<string>",
  "partial_member_list": [
    {
      "user_id": "<string>"
    }
  ],
  "external_retrieval_model": {
    "top_k": 123,
    "score_threshold": 123,
    "score_threshold_enabled": true
  },
  "external_knowledge_id": "<string>",
  "external_knowledge_api_id": "<string>"
}
'

import requests

url = "https://{api_base_url}/datasets/{dataset_id}"

payload = {
    "name": "<string>",
    "description": "<string>",
    "embedding_model": "<string>",
    "embedding_model_provider": "<string>",
    "partial_member_list": [{ "user_id": "<string>" }],
    "external_retrieval_model": {
        "top_k": 123,
        "score_threshold": 123,
        "score_threshold_enabled": True
    },
    "external_knowledge_id": "<string>",
    "external_knowledge_api_id": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'PATCH',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    name: '<string>',
    description: '<string>',
    embedding_model: '<string>',
    embedding_model_provider: '<string>',
    partial_member_list: [{user_id: '<string>'}],
    external_retrieval_model: {top_k: 123, score_threshold: 123, score_threshold_enabled: true},
    external_knowledge_id: '<string>',
    external_knowledge_api_id: '<string>'
  })
};

fetch('https://{api_base_url}/datasets/{dataset_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}",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "PATCH",
  CURLOPT_POSTFIELDS => json_encode([
    'name' => '<string>',
    'description' => '<string>',
    'embedding_model' => '<string>',
    'embedding_model_provider' => '<string>',
    'partial_member_list' => [
        [
                'user_id' => '<string>'
        ]
    ],
    'external_retrieval_model' => [
        'top_k' => 123,
        'score_threshold' => 123,
        'score_threshold_enabled' => true
    ],
    'external_knowledge_id' => '<string>',
    'external_knowledge_api_id' => '<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}"

	payload := strings.NewReader("{\n  \"name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"partial_member_list\": [\n    {\n      \"user_id\": \"<string>\"\n    }\n  ],\n  \"external_retrieval_model\": {\n    \"top_k\": 123,\n    \"score_threshold\": 123,\n    \"score_threshold_enabled\": true\n  },\n  \"external_knowledge_id\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\"\n}")

	req, _ := http.NewRequest("PATCH", 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.patch("https://{api_base_url}/datasets/{dataset_id}")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"partial_member_list\": [\n    {\n      \"user_id\": \"<string>\"\n    }\n  ],\n  \"external_retrieval_model\": {\n    \"top_k\": 123,\n    \"score_threshold\": 123,\n    \"score_threshold_enabled\": true\n  },\n  \"external_knowledge_id\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Patch.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"name\": \"<string>\",\n  \"description\": \"<string>\",\n  \"embedding_model\": \"<string>\",\n  \"embedding_model_provider\": \"<string>\",\n  \"partial_member_list\": [\n    {\n      \"user_id\": \"<string>\"\n    }\n  ],\n  \"external_retrieval_model\": {\n    \"top_k\": 123,\n    \"score_threshold\": 123,\n    \"score_threshold_enabled\": true\n  },\n  \"external_knowledge_id\": \"<string>\",\n  \"external_knowledge_api_id\": \"<string>\"\n}"

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

{
  "id": "c42e2a6e-40b3-4330-96f8-f1e4d768e8c9",
  "name": "Product Documentation",
  "description": "产品 API 技术文档",
  "provider": "vendor",
  "permission": "only_me",
  "data_source_type": null,
  "indexing_technique": "high_quality",
  "app_count": 0,
  "document_count": 0,
  "word_count": 0,
  "created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
  "author_name": "admin",
  "created_at": 1741267200,
  "updated_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
  "updated_at": 1741267200,
  "embedding_model": "text-embedding-3-small",
  "embedding_model_provider": "langgenius/openai/openai",
  "embedding_available": true,
  "retrieval_model_dict": {
    "search_method": "semantic_search",
    "reranking_enable": false,
    "reranking_mode": null,
    "reranking_model": {
      "reranking_provider_name": "",
      "reranking_model_name": ""
    },
    "weights": null,
    "top_k": 3,
    "score_threshold_enabled": false,
    "score_threshold": null
  },
  "tags": [],
  "doc_form": "text_model",
  "external_knowledge_info": null,
  "external_retrieval_model": null,
  "doc_metadata": [],
  "built_in_field_enabled": true,
  "pipeline_id": null,
  "runtime_mode": null,
  "chunk_structure": null,
  "icon_info": null,
  "summary_index_setting": null,
  "is_published": false,
  "total_documents": 0,
  "total_available_documents": 0,
  "enable_api": true,
  "is_multimodal": false,
  "maintainer": "admin",
  "partial_member_list": []
}

授权

Authorization

string

header

必填

每个请求都通过 API 密钥认证：Authorization: Bearer {API_KEY}。应用接口使用应用 API 密钥，知识库接口使用知识库 API 密钥（快速开始）。

API 密钥应保存在服务端，切勿嵌入客户端代码。缺失或无效的密钥会返回 HTTP 401（unauthorized）。

路径参数

dataset_id

string<uuid>

必填

知识库 ID，通过获取知识库列表获取。使用限定范围的密钥时，从 Dify 页面 URL 复制 ID。

请求体

application/json

name

string

知识库名称。

Required string length: 1 - 40

description

string

知识库描述。

Maximum string length: 400

indexing_technique

enum<string> | null

high_quality 使用嵌入模型进行精确搜索；economy 使用基于关键词的索引。

可用选项:

high_quality,

economy

permission

enum<string>

控制谁可以访问此知识库。only_me 仅限创建者，all_team_members 授权整个工作区访问，partial_members 授权指定成员访问。

可用选项:

only_me,

all_team_members,

partial_members

embedding_model

string

嵌入模型名称。使用获取可用模型中 model_type=text-embedding 返回的 model 字段值。

embedding_model_provider

string

嵌入模型供应商标识符，格式为 organization/plugin_name/provider_name（例如 langgenius/openai/openai）。openai 这类简写会展开为 langgenius/<name>/<name>，仅对 langgenius 发布的插件有效。

有效取值从获取可用模型中 model_type=text-embedding 返回的 provider 字段获取。

retrieval_model

object

检索模型配置。控制查询此知识库时如何搜索和排序分段。

Show child attributes

partial_member_list

object[]

当 permission 为 partial_members 时有访问权限的团队成员列表。

Show child attributes

external_retrieval_model

object

外部知识库的检索设置。

Show child attributes

external_knowledge_id

string

外部知识库的 ID。

external_knowledge_api_id

string

外部知识库 API 连接的 ID。

响应

知识库更新成功。

string

知识库的唯一标识符。

name

string

知识库的显示名称。在工作区内唯一。

description

string

描述知识库用途或内容的可选文本。

provider

string

供应商类型。内部管理为 vendor，外部知识库连接为 external。

permission

string

控制谁可以访问此知识库。可选值：only_me、all_team_members、partial_members。

data_source_type

string

文档的数据源类型，尚未配置时为 null。

indexing_technique

string

high_quality 使用嵌入模型进行精确搜索；economy 使用基于关键词的索引。

app_count

integer

当前使用该知识库的应用数量。

document_count

integer

知识库中的文档总数。

word_count

integer

所有文档的总字数。

created_by

string

创建该知识库的用户 ID。

author_name

string

创建者的显示名称。

created_at

number

创建时间戳（Unix 纪元，单位为秒）。

updated_by

string

最后更新该知识库的用户 ID。

updated_at

number

最后更新时间戳（Unix 纪元，单位为秒）。

embedding_model

string

用于索引的嵌入模型名称。

embedding_model_provider

string

嵌入模型供应商标识符，格式为 organization/plugin_name/provider_name（例如 langgenius/openai/openai）。旧版知识库可能返回简写形式（例如 openai）。

embedding_available

boolean

配置的嵌入模型当前是否可用。

retrieval_model_dict

object

知识库的检索配置。

Show child attributes

summary_index_setting

object | null

摘要索引配置。

Show child attributes