.Net使用Elastic.Clients.Elasticsearch在Elasticsearch8中实现向量存储和相似度检索

server/2024/9/23 3:52:32/

文章目录

- - 一、测试环境
  - 二、代码
  - - 1、创建包含DenseVector的索引
    - 2、索引文档
    - 3、对向量字段进行近似knn检索
  - 三、参考

一、测试环境

Elastic.Clients.Elasticsearch版本：8.13.0
Elasticsearch版本：8.13.0

二、代码

1、创建包含DenseVector的索引

public static bool InitIndex()
{// 定义索引配置var faceVectorproperties = new Properties{{ "Id" ,new KeywordProperty()},{ "FileID" ,new KeywordProperty()},{ "FileGUID" ,new KeywordProperty()},{ "ResourceID" ,new KeywordProperty()},{ "FileName" ,new TextProperty()},{ "Embedding" ,new DenseVectorProperty{Dims = 3 } }};// 定义索引配置var indexConfig = new IndexState{Settings = new IndexSettings{NumberOfShards = 1, // 设置分片数NumberOfReplicas = 1 // 设置副本数},Mappings = new TypeMapping{Properties = faceVectorproperties}};//判断是否已经存在该索引var existFaceVectorIndexResponse = _client.Indices.ExistsAsync("FaceVector").Result;if (!existFaceVectorIndexResponse.IsValidResponse){// 创建索引请求var createIndexRequest = new CreateIndexRequest("FaceVector"){Settings = indexConfig.Settings,Mappings = indexConfig.Mappings};var createFaceVectorIndexResponse = _client.Indices.CreateAsync(createIndexRequest).Result;if (createFaceVectorIndexResponse.Acknowledged){//添加一条测试数据ES_FaceVector temp = new ES_FaceVector{FileID = 0,FileGUID = Guid.NewGuid(),ResourceID = 0,FileName = "测试",Embedding = new float[] {1.2f,1.1f,1.3f }};var addDocResult = AddDoc<ES_FaceVector>(temp, ElasticIndexEnum.FaceVector);}else{return false;}}return true;
}

2、索引文档

//批量索引文档
public static bool AddDocs<T>(List<T> data, string indexName) where T : class
{var bulkIndexResponse = _client.BulkAsync(b => b.Index(indexName).IndexMany(data)).Result;return bulkIndexResponse.IsValidResponse;
}
//单个索引文档
public static bool AddDoc<T>(T data, string indexName) where T : class
{var response = _client.IndexAsync(data, indexName).Result;return response.IsValidResponse;
}

3、对向量字段进行近似knn检索

public static void SearchKnn()
{// 构建KNN查询var doubleArr = new[] { -0.04604065, 0.054946236, 0.057453074};var arrLen = doubleArr.Length;var knnQuery = new KnnQuery(){k = 2,NumCandidates = 1000,Field = "embedding",QueryVector= doubleArr.Select(s=>(float)s).ToArray()};// 构建Elasticsearch查询var searchRequest = new SearchRequest<ES_FaceVector>(ElasticIndexEnum.FaceVector){Knn = new KnnQuery[] { knnQuery },MinScore = 0.90,SourceIncludes = new [] { "fileName", "embedding" }};var searchResponse = _client.Search<ES_FaceVector>(searchRequest);if (searchResponse.IsValidResponse){foreach (var hit in searchResponse.Hits){// 处理每个文档的结果var fileNameTemp = hit.Source.FileName;var embeddingTemp = hit.Source.Embedding;}}else{Console.WriteLine($"Error: {searchResponse.DebugInformation}");}
}