SpringBoot 整合Redis Stack 构建本地向量数据库相似性查询的方法

docker run -d --name redis-stack -v /redis-data:/data -p 6379:6379 -p 8001:8001 redis/redis-stack:latest

version: '3'
services:
  redis-stack:
    image: redis/redis-stack
    ports:
      - 6379:6379
  redis-insight:
    image: redislabs/redisinsight:latest
    ports:
      - 5540:5540

<properties>
    <maven.compiler.source>17</maven.compiler.source>
    <maven.compiler.target>17</maven.compiler.target>
    <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
</properties>
<parent>
    <groupId>org.springframework.boot</groupId>
    <artifactId>spring-boot-starter-parent</artifactId>
    <version>3.2.4</version>
    <relativePath/>
</parent>
<dependencies>
    <dependency>
        <groupId>com.alibaba.cloud.ai</groupId>
        <artifactId>spring-ai-alibaba-starter</artifactId>
        <version>1.0.0-M2.1</version>
    </dependency>
    <dependency>
        <groupId>com.alibaba</groupId>
        <artifactId>fastjson</artifactId>
        <version>2.0.35</version>
    </dependency>
    <dependency>
        <groupId>com.squareup.okhttp3</groupId>
        <artifactId>okhttp</artifactId>
        <version>4.12.0</version>
    </dependency>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>
    <dependency>
        <groupId>org.projectlombok</groupId>
        <artifactId>lombok</artifactId>
        <scope>provided</scope>
    </dependency>
    <!-- https://mvnrepository.com/artifact/com.alibaba/dashscope-sdk-java -->
    <dependency>
        <groupId>com.alibaba</groupId>
        <artifactId>dashscope-sdk-java</artifactId>
        <version>2.16.9</version>
    </dependency>
    <dependency>
        <groupId>org.apache.httpcomponents</groupId>
        <artifactId>httpclient</artifactId>
        <version>4.5.13</version>
    </dependency>
    <!-- https://mvnrepository.com/artifact/io.milvus/milvus-sdk-java -->
    <dependency>
        <groupId>io.milvus</groupId>
        <artifactId>milvus-sdk-java</artifactId>
        <version>2.4.6</version>
    </dependency>
</dependencies>
<repositories>
    <repository>
        <id>spring-milestones</id>
        <name>Spring Milestones</name>
        <url>https://repo.spring.io/milestone</url>
        <snapshots>
            <enabled>false</enabled>
        </snapshots>
    </repository>
</repositories>

server:
  port: 8081
spring:
  ai:
    dashscope:
      api-key: 你的apikey
      embedding:
        options:
          model: text-embedding-v2

package com.congge.web;
import jakarta.annotation.Resource;
import lombok.extern.slf4j.Slf4j;
import org.springframework.ai.embedding.EmbeddingModel;
import org.springframework.ai.embedding.EmbeddingResponse;
import org.springframework.beans.factory.annotation.Autowired;
import org.springframework.web.bind.annotation.GetMapping;
import org.springframework.web.bind.annotation.RequestParam;
import org.springframework.web.bind.annotation.RestController;
import java.util.List;
import java.util.Map;
@RestController
@Slf4j
public class DocumentController {
    private final EmbeddingModel embeddingModel;
    @Autowired
    public DocumentController(EmbeddingModel embeddingModel) {
        this.embeddingModel = embeddingModel;
    }
    @GetMapping("/ai/embedding")
    public Map embed(@RequestParam(value = "message", defaultValue = "Tell me a joke") String message) {
        EmbeddingResponse embeddingResponse = this.embeddingModel.embedForResponse(List.of(message));
        return Map.of("embedding", embeddingResponse);
    }
    //localhost:8081/embedding
    @GetMapping("/embedding")
    public Object embeddingTest() {
        // 文本嵌入
        float[] embed = embeddingModel.embed("你好，我是小码农叔叔");
        log.info("文本转换得到的向量: {}", embed);
        return embed;
    }
}

        <dependency>
            <groupId>org.springframework.ai</groupId>
            <artifactId>spring-ai-tika-document-reader</artifactId>
        </dependency>

@SneakyThrows
@PostMapping("read/multipart-file")
public void readMultipartFile(@RequestParam MultipartFile file) {
    // 从IO流中读取文件
    Resource resource = new InputStreamResource(file.getInputStream());
    List<Document> documents = new TikaDocumentReader(resource)
            .read();
}

/**
 * 从本地文件读取
 * @return
 */
@GetMapping("/read/from-local-file")
public Object readLocalFile() {
    FileSystemResource resource = new FileSystemResource("E:\\工作空间\\wzlocal\\Java编码规范V1.0.pdf");
    List<Document> documents = new TikaDocumentReader(resource)
            .read();
    return documents;
}

/**
 * 分割后的文档列表  localhost:8081/doc/split
 * @param file
 * @return
 * @throws Exception
 */
@PostMapping("/doc/split")
public Object docSplit(@RequestParam MultipartFile file) throws Exception{
    InputStreamResource inputStreamResource = new InputStreamResource(file.getInputStream());
    List<Document> documentList = new TikaDocumentReader(inputStreamResource).read();
    // 分割后的文档列表
    List<Document> splitDocList = new TokenTextSplitter().split(documentList);
    List<String> contentList = splitDocList.stream().map(Document::getContent).collect(Collectors.toList());
    return contentList;
}

<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-tika-document-reader</artifactId>
    <version>1.0.0-M3</version>
</dependency>
<dependency>
    <groupId>org.springframework.ai</groupId>
    <artifactId>spring-ai-redis-store</artifactId>
    <version>1.0.0-M3</version>
</dependency>
<dependency>
    <groupId>redis.clients</groupId>
    <artifactId>jedis</artifactId>
</dependency>

spring:
  ai:
    dashscope:
      api-key: 你的apikey
      embedding:
        options:
          model: text-embedding-v2
    vectorstore:
      redis:
        uri: redis://IP:6379
  data:
    redis:
      database: 0
      timeout: 10s
      lettuce:
        pool:
          # 连接池最大连接数
          max-active: 200
          # 连接池最大阻塞等待时间（使用负值表示没有限制）
          max-wait: -1ms
          # 连接池中的最大空闲连接
          max-idle: 10
          # 连接池中的最小空闲连接
          min-idle: 0
      repositories:
        enabled: false
      host: redis地址

package com.congge.config;
import lombok.AllArgsConstructor;
import org.springframework.ai.autoconfigure.vectorstore.redis.RedisVectorStoreAutoConfiguration;
import org.springframework.ai.autoconfigure.vectorstore.redis.RedisVectorStoreProperties;
import org.springframework.ai.embedding.EmbeddingModel;
import org.springframework.ai.vectorstore.RedisVectorStore;
import org.springframework.ai.vectorstore.VectorStore;
import org.springframework.boot.autoconfigure.EnableAutoConfiguration;
import org.springframework.boot.autoconfigure.data.redis.RedisConnectionDetails;
import org.springframework.boot.context.properties.EnableConfigurationProperties;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;
import redis.clients.jedis.JedisPooled;
@Configuration
// 禁用SpringAI提供的RedisStack向量数据库的自动配置，会和Redis的配置冲突。
@EnableAutoConfiguration(exclude = {RedisVectorStoreAutoConfiguration.class})
// 读取RedisStack的配置信息
@EnableConfigurationProperties({RedisVectorStoreProperties.class})
@AllArgsConstructor
public class RedisVectorConfig {
    /**
     * 创建RedisStack向量数据库
     *
     * @param embeddingModel 嵌入模型
     * @param properties     redis-stack的配置信息
     * @return vectorStore 向量数据库
     */
    @Bean
    public VectorStore vectorStore(EmbeddingModel embeddingModel,
                                   RedisVectorStoreProperties properties,
                                   RedisConnectionDetails redisConnectionDetails) {
        RedisVectorStore.RedisVectorStoreConfig config = RedisVectorStore.RedisVectorStoreConfig.builder().withIndexName(properties.getIndex()).withPrefix(properties.getPrefix()).build();
        return new RedisVectorStore(config, embeddingModel,
                new JedisPooled(redisConnectionDetails.getStandalone().getHost(),
                        redisConnectionDetails.getStandalone().getPort()
                        , redisConnectionDetails.getUsername(),
                        redisConnectionDetails.getPassword()),
                properties.isInitializeSchema());
    }
}

/**
 * 文档保存到向量数据库   localhost:8081/doc/embedding
 * @param file
 * @return
 * @throws Exception
 */
@PostMapping("/doc/embedding")
public Object docEmbedding(@RequestParam MultipartFile file) throws Exception{
    TikaDocumentReader tikaDocumentReader = new TikaDocumentReader(new InputStreamResource(file.getInputStream()));
    List<Document> splitDocuments = new TokenTextSplitter().apply(tikaDocumentReader.read());
    // 存入向量数据库，这个过程会自动调用embeddingModel,将文本变成向量存入
    vectorStore.add(splitDocuments);
    return true;
}

/**
 * 关键字检索文档  localhost:8081/doc/query?keyword=面向对象
 * @param keyword
 * @return
 */
@GetMapping("/doc/query")
public List<Document> query(@RequestParam String keyword) {
    List<Document> documentList = vectorStore.similaritySearch(keyword);
    return documentList;
}