十分钟手把手教学：用DeepSeek4j开发私有大模型知识库

# 下载推理模型 - 用于理解和生成回答
ollama run deepseek-r1:14b

# 下载向量模型 - 用于文本向量化
ollama run bge-m3:latest

# 1. 下载安装脚本
curl -sfL https://raw.githubusercontent.com/milvus-io/milvus/master/scripts/standalone_embed.sh -o standalone_embed.sh

# 2. 启动 Docker 容器
bash standalone_embed.sh start

<dependency>
    <groupId>io.github.pig-mesh.ai</groupId>
    <artifactId>deepseek-spring-boot-starter</artifactId>
    <version>1.4.0</version>
</dependency>
<!-- 链接 milvus SDK-->
<dependency>
    <groupId>io.milvus</groupId>
    <artifactId>milvus-sdk-java</artifactId>
    <version>2.5.3</version>
</dependency>

# 推理模型链接信息
deepseek:
  base-url: http://127.0.0.1:11434/v1
  model: deepseek-r1:14b
  api-key: ollama-local
# 向量模型链接信息
embedding:
  api-key: ${deepseek.api-key}
  base-url: ${deepseek.base-url}
  model: bge-m3:latest

// 1. Connect to Milvus server
ConnectConfig connectConfig = ConnectConfig.builder()
        .uri(CLUSTER_ENDPOINT) // 1.2 获取的 Milvus 链接端点
        .token(TOKEN)  // 1.2 获取的 Milvus 链接信息
        .build();

MilvusClientV2 milvusClientV2 = new MilvusClientV2(connectConfig);

@Autowired
EmbeddingClient embeddingClient;

{
    // 这里以 2025最新的我司保密条例演示，可以换成你自己的
    String law = FileUtil.readString("/Users/lengleng/Downloads/law.txt", Charset.defaultCharset());
    String[] lawSplits = StrUtil.split(law, 400);


    List<JsonObject> data = new ArrayList<>();
    for (String lawSplit : lawSplits) {
        List<Float> floatList = embeddingClient.embed(lawSplit);

        JsonObject jsonObject = new JsonObject();

        // 将 List<Float> 转换为 JsonArray
        JsonArray jsonArray = new JsonArray();
        for (Float value : floatList) {
            jsonArray.add(value);
        }
        jsonObject.add("vector", jsonArray);
        jsonObject.addProperty("text", lawSplit);

        data.add(jsonObject);
    }

    InsertReq insertReq = InsertReq.builder()
            .collectionName("deepseek4j_test")
            .data(data)
            .build();

    milvusClientV2.insert(insertReq);
}

@GetMapping(value = "/chat", produces = MediaType.TEXT_EVENT_STREAM_VALUE)
public Flux<ChatCompletionResponse> chat(String prompt) {
    MilvusClientV2 milvusClientV2 = new MilvusClientV2(connectConfig);

    List<Float> floatList = embeddingClientOptional.get().embed(prompt);

    SearchReq searchReq = SearchReq.builder()
            .collectionName("deepseek4j_test")
            .data(Collections.singletonList(new FloatVec(floatList)))
            .outputFields(Collections.singletonList("text"))
            .topK(3)
            .build();

    SearchResp searchResp = milvusClientV2.search(searchReq);

    List<String> resultList = new ArrayList<>();
    List<List<SearchResp.SearchResult>> searchResults = searchResp.getSearchResults();
    for (List<SearchResp.SearchResult> results : searchResults) {
        System.out.println("TopK results:");
        for (SearchResp.SearchResult result : results) {
            resultList.add(result.getEntity().get("text").toString());
        }
    }


    ChatCompletionRequest request = ChatCompletionRequest.builder()
            // 根据渠道模型名称动态修改这个参数
            .model("deepseek-r1:14b")
            .addUserMessage(String.format("你要根据用户输入的问题：%s \n \n 参考如下内容： %s  \n\n 整理处理最终结果", prompt, resultList)).build();

    return deepSeekClient.chatFluxCompletion(request);
}