从知识库检索分段 / 测试检索

对知识库执行搜索查询，检索最相关的分段。此接口可用于生产环境检索和测试检索。

POST /datasets/{dataset_id}/retrieve

从知识库检索分段 / 测试检索

cURL

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

import requests

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

payload = {
    "query": "<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({query: '<string>', attachment_ids: ['<string>']})
};

fetch('https://{api_base_url}/datasets/{dataset_id}/retrieve', 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}/retrieve",
  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([
    'query' => '<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}/retrieve"

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

require 'uri'
require 'net/http'

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

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  \"query\": \"<string>\",\n  \"attachment_ids\": [\n    \"<string>\"\n  ]\n}"

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

200

success

{
  "query": {
    "content": "What is Dify?"
  },
  "records": [
    {
      "segment": {
        "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": 1,
        "enabled": true,
        "disabled_at": null,
        "disabled_by": null,
        "status": "completed",
        "created_by": "ad313dd6-ef04-4dd1-a5b0-c0f0b9e2e7e4",
        "created_at": 1741267200,
        "indexing_at": 1741267200,
        "completed_at": 1741267200,
        "error": null,
        "stopped_at": null,
        "document": {
          "id": "a8e0e5b5-78c6-4130-a5ce-25feb0e0b4ac",
          "data_source_type": "upload_file",
          "name": "guide.txt",
          "doc_type": null,
          "doc_metadata": null
        }
      },
      "child_chunks": [],
      "score": 0.92,
      "tsne_position": null,
      "files": [],
      "summary": null
    }
  ]
}

Authorizations

Authorization · string · header · required

API Key 认证。对于所有 API 请求，请在 Authorization HTTP 头中包含您的 API Key，并加上 Bearer 前缀。示例：Authorization: Bearer {API_KEY}。强烈建议将 API Key 存储在服务端，不要在客户端共享或存储，以避免 API Key 泄漏导致严重后果。缺少或无效的 API Key 会返回 HTTP 401，错误码为 unauthorized。

Path Parameters

dataset_id · string<uuid> · required

知识库 ID。

Body

application/json

query · string · required

搜索查询文本。

Maximum string length: 250

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

attachment_ids · string[] | null

要包含在检索上下文中的附件 ID 列表。

Response

200

application/json

检索结果。

query · object

原始查询对象。

Show child attributes

records · object[]

匹配的检索记录列表。

Show child attributes