ElasticSearch的向量存储和搜索

引入依赖

<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0"
         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
    <modelVersion>4.0.0</modelVersion>

    <parent>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-parent</artifactId>
        <version>3.0.5</version>
    </parent>

    <groupId>org.example</groupId>
    <artifactId>langchain4j-demo</artifactId>
    <version>1.0-SNAPSHOT</version>

    <properties>
        <maven.compiler.source>17</maven.compiler.source>
        <maven.compiler.target>17</maven.compiler.target>
        <project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
    </properties>

    <dependencies>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-web</artifactId>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-data-elasticsearch</artifactId>
        </dependency>


        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j</artifactId>
            <version>0.29.1</version>
        </dependency>

        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-qianfan</artifactId>
            <version>0.30.0</version>
        </dependency>

        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-open-ai</artifactId>
            <version>0.29.1</version>
        </dependency>

        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-zhipu-ai</artifactId>
            <version>0.29.1</version>
        </dependency>

        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-dashscope</artifactId>
            <version>0.29.1</version>
        </dependency>

        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-ollama</artifactId>
            <version>0.29.1</version>
        </dependency>

        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-embeddings-all-minilm-l6-v2</artifactId>
            <version>0.29.1</version>
        </dependency>

        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-pgvector</artifactId>
            <version>0.29.0</version>
        </dependency>

        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-elasticsearch</artifactId>
            <version>0.29.0</version>
        </dependency>

        <dependency>
            <groupId>dev.langchain4j</groupId>
            <artifactId>langchain4j-redis</artifactId>
            <version>0.29.0</version>
        </dependency>

        <dependency>
            <groupId>org.projectlombok</groupId>
            <artifactId>lombok</artifactId>
        </dependency>

        <dependency>
            <groupId>org.springframework.boot</groupId>
            <artifactId>spring-boot-starter-test</artifactId>
            <scope>test</scope>
        </dependency>
    </dependencies>
</project>

示例代码

package org.example;

import dev.langchain4j.data.embedding.Embedding;
import dev.langchain4j.data.segment.TextSegment;
import dev.langchain4j.model.embedding.AllMiniLmL6V2EmbeddingModel;
import dev.langchain4j.model.embedding.EmbeddingModel;
import dev.langchain4j.model.output.Response;
import dev.langchain4j.store.embedding.EmbeddingMatch;
import dev.langchain4j.store.embedding.EmbeddingSearchRequest;
import dev.langchain4j.store.embedding.EmbeddingSearchResult;
import dev.langchain4j.store.embedding.EmbeddingStore;
import dev.langchain4j.store.embedding.elasticsearch.ElasticsearchEmbeddingStore;

public class EsMain {

    public static void main(String[] args) {

        TextSegment textSegment = TextSegment.from("我爱吃苹果");

        EmbeddingModel embeddingModel = new AllMiniLmL6V2EmbeddingModel();
        Response<Embedding> embed = embeddingModel.embed(textSegment);

        ElasticsearchEmbeddingStore embeddingStore = ElasticsearchEmbeddingStore
        .builder()
        .serverUrl("http://192.11.2.1:29201")
        .indexName("vector_index")
        .dimension(embed.content().dimension())
        .userName("elastic")
        .password("1231230")
        .build();

        embeddingStore.add(embed.content(), textSegment);


        TextSegment queryTextSegment = TextSegment.from("我喜欢吃苹果");
        Embedding queryEmbedding = embeddingModel.embed(queryTextSegment).content();
        EmbeddingSearchRequest request = EmbeddingSearchRequest.builder().queryEmbedding(queryEmbedding).maxResults(3).minScore(0.1).build();
        EmbeddingSearchResult<TextSegment> result = embeddingStore.search(request);

        for (EmbeddingMatch<TextSegment> match : result.matches()) {
            System.out.println(match.embedded().text());
            System.out.println(match.score());
        }
    }
}