基于DeepSeek-R1模型搭建RAG系统

Java

步骤 1：配置Java环境

java -version

<dependency>
    <groupId>com.aliyun.opensearch</groupId>
    <artifactId>aliyun-sdk-opensearch</artifactId>
    <version>6.0.0</version>
</dependency>

步骤 2：获取调用参数

SDK调用依赖以下关键参数：

• AppName：应用名称。

  

• host：应用的API访问地址。

  

步骤 3：调用接口

运行以下代码调用示例：

package com.aliyun.opensearch;

import com.aliyun.opensearch.OpenSearchClient;
import com.aliyun.opensearch.sdk.generated.OpenSearch;
import com.aliyun.opensearch.sdk.generated.commons.OpenSearchClientException;
import com.aliyun.opensearch.sdk.generated.commons.OpenSearchException;
import com.aliyun.opensearch.sdk.generated.commons.OpenSearchResult;

import java.util.HashMap;
import java.util.Map;

public class LLMSearch {

    private static String appName = "替换为应用名称";
    private static String host = "替换应用的API访问地址";
    private static String accesskey = "替换accesskey";
    private static String secret = "替换secret";
    private static String path = "/apps/%s/actions/knowledge-search";

    public static void main(String[] args) {
      
        String appPath = String.format(path, appName);

        //ApiReadTimeOut
        OpenSearch openSearch = new OpenSearch(accesskey, secret, host);
        openSearch.setTimeout(90000);

        OpenSearchClient openSearchClient = new OpenSearchClient(openSearch);

        Map<String, String> params = new HashMap<String, String>() {{
            put("format", "full_json");
            put("_POST_BODY", "{\"question\":{\"text\":\"怎么充电\",\"type\":\"TEXT\",\"session\":\"\"},\"options\":{\"retrieve\":{\"doc\":{\"filter\":\"\",\"top_n\":5,\"sf\":\"\",\"dense_weight\":\"0.7\",\"formula\":\"\",\"operator\":\"AND\"},\"entry\":{\"sf\":\"\"},\"image\":{\"sf\":\"\",\"dense_weight\":\"0.7\"},\"qp\":{\"query_extend\":false,\"query_extend_num\":5},\"return_hits\":false,\"rerank\":{\"enable\":true,\"model\":\"ops-bge-reranker-larger\"}},\"chat\":{\"stream\":true,\"prompt_config\":{\"attitude\":\"normal\",\"rule\":\"detailed\",\"noanswer\":\"sorry\",\"language\":\"Chinese\",\"role\":false,\"role_name\":\"AI小助手\",\"out_format\":\"text\"},\"agent\":{\"tools\":[]},\"csi_level\":\"strict\",\"history_max\":\"\",\"link\":\"false\",\"model\":\"deepseek-r1\",\"model_generation\":\"\"}}}");

        }};
          try {
            OpenSearchResult openSearchResult = openSearchClient
            .callAndDecodeResult(appPath, params, "POST");
            System.out.println("RequestID=" + openSearchResult.getTraceInfo().getRequestId());
            System.out.println(openSearchResult.getResult());
        } catch (
            OpenSearchException e) {
            System.out.println("RequestID=" + e.getRequestId());
            System.out.println("ErrorCode=" + e.getCode());
            System.out.println("ErrorMessage=" + e.getMessage());
        } catch (
            OpenSearchClientException e) {
            System.out.println("ErrorMessage=" + e.getMessage());
        }
    }
}

Python

步骤 1：配置 Python 环境

# 如果运行失败，您可以将python替换成python3再运行
python -V

pip install alibabacloud_tea_util 
pip install alibabacloud_opensearch_util
pip install alibabacloud_credentials

步骤 2：获取参数

SDK调用依赖以下关键参数：

• app_name：应用名称。

• endpoint：应用的API访问地址。

步骤 3：调用接口

BaseRequest参考：Python client 示例。

# -*- coding: utf-8 -*-

import time, os
from typing import Dict, Any

from Tea.exceptions import TeaException
from Tea.request import TeaRequest
from alibabacloud_tea_util import models as util_models
from BaseRequest import Config, Client


class LLMSearch:
    def __init__(self, config: Config):
        self.Clients = Client(config=config)
        self.runtime = util_models.RuntimeOptions(
            connect_timeout=10000,
            read_timeout=90000,
            autoretry=False,
            ignore_ssl=False,
            max_idle_conns=50,
            max_attempts=3
        )
        self.header = {}


    def searchDoc(self, app_name: str,body:Dict, query_params: dict={}) -> Dict[str, Any]:
        try:
            response = self.Clients._request(method="POST", pathname=f'/v3/openapi/apps/{app_name}/actions/knowledge-search',
                                             query=query_params, headers=self.header, body=body, runtime=self.runtime)
            return response
        except TeaException as e:
            print(e)


if __name__ == "__main__":
    # 配置统一的请求入口和  需要去掉http://
    endpoint = "<endpoint>"

    # 支持 protocol 配置 HTTPS/HTTP
    endpoint_protocol = "HTTP"

    # 用户识别信息
    # 从环境变量读取配置的AccessKey ID和AccessKey Secret，
    # 运行代码示例前必须先配置环境变量，参考文档上面“配置环境变量”步骤
    access_key_id = os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_ID")
    access_key_secret = os.environ.get("ALIBABA_CLOUD_ACCESS_KEY_SECRET")

    # 支持 type 配置 sts/access_key 鉴权. 其中 type 默认为 access_key 鉴权. 使用 sts 可配置 RAM-STS 鉴权.
    # 备选参数为:  sts 或者 access_key
    auth_type = "access_key"

    # 如果使用 RAM-STS 鉴权, 请配置 security_token, 可使用 阿里云 AssumeRole 获取 相关 STS 鉴权结构.
    security_token =  "<security_token>"

    # 配置请求使用的通用信息.
    # type和security_token 参数如果不是子账号，需要省略
    Configs = Config(endpoint=endpoint, access_key_id=access_key_id, access_key_secret=access_key_secret,
                     security_token=security_token, type=auth_type, protocol=endpoint_protocol)

    # 创建 opensearch 实例
    # 请将<应用名称>替换为您创建的智能问答版实例名称
    ops = LLMSearch(Configs)
    app_name = "<应用名称>"

    # --------------- 文档搜索 ---------------

    docQuery = {"question": {"text": "搜索", "type": "TEXT"}, "options": {"chat": {"model": "deepseek-r1"}}}

    res1 = ops.searchDoc(app_name=app_name, body=docQuery)
    print(res1)