C#使用Qdrant实现向量存储及检索

1、背景

C#通过Semantic Kernel可以实现向量存储和检索，向量的存储方式有很多（InMemory、各种专门的向量数据库之类），本次实现以Qdrant向量数据库实现，其他的向量数据库都是一样的。

2、步骤

2.1、下载Qdrant数据库

可以参考如下的文章，进行下载：2025年Windows 11系统下Qdrant向量数据库安装与使用全指南
本机的环境是安装的1.14.1

2.2、下载Ollama并下载模型

Ollama的安装教程网上很多，不在此赘述。
本地环境为：ollama的版本是：ollama version is 0.9.3
本地中模型有：

2.3、下载package

因为需要使用到Ollama和Qdrant向量数据库，所以需要安装相应的package

2.4、代码实现

安装完软件后，创建一个控制台程序，然后引入上面的包后，全部代码如下：

using Microsoft.Extensions.AI;
using Microsoft.Extensions.VectorData;
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.Connectors.Qdrant;
using OllamaSharp;
using Qdrant.Client;

var kernelBuilder = Kernel.CreateBuilder();

//1、设置嵌入的模型
IEmbeddingGenerator<string, Embedding<float>> embeddingGenerator = new OllamaApiClient(new Uri("http://localhost:11434"),
    "all-minilm");
//2、QdrantClient默认使用的gRPC方式联系，因此端口只能是6334,。
//6333那个http的端口，无法使用
var vectorStore = new QdrantVectorStore(new QdrantClient("localhost",6334,false), ownsClient: true, new QdrantVectorStoreOptions
{
    EmbeddingGenerator = embeddingGenerator
});

//3、创建一个collection，并进行初始化
var collection = vectorStore.GetCollection<ulong, Movie>("movies");
await collection.EnsureCollectionExistsAsync();

//4、把数据进行初始化
//其中，我们是讲描述进行了向量化，并保存到向量数据库中
var movieData = new List<Movie>()
{
    new Movie
        {
            Key=0,
            Title="Lion King",
            Description="The Lion King is a classic Disney animated film that tells the story of a young lion named Simba who embarks on a journey to reclaim his throne as the king of the Pride Lands after the tragic death of his father."
        },
    new Movie
        {
            Key=1,
            Title="Inception",
            Description="Inception is a science fiction film directed by Christopher Nolan that follows a group of thieves who enter the dreams of their targets to steal information."
        },
    new Movie
        {
            Key=2,
            Title="The Matrix",
            Description="The Matrix is a science fiction film directed by the Wachowskis that follows a computer hacker named Neo who discovers that the world he lives in is a simulated reality created by machines."
        },
    new Movie
        {
            Key=3,
            Title="Shrek",
            Description="Shrek is an animated film that tells the story of an ogre named Shrek who embarks on a quest to rescue Princess Fiona from a dragon and bring her back to the kingdom of Duloc."
        }
};

//5、将描述向量化，并保存到数据库中
foreach (var movie in movieData)
{
    movie.Vector = await embeddingGenerator.GenerateVectorAsync(movie.Description);
    await collection.UpsertAsync(movie);
}

//6、以上，完成了数据的保存
//从本布开始，进行数据检索。先将查询条件进行向量化
var query = "A family friendly movie";
var queryEmbedding = await embeddingGenerator.GenerateVectorAsync(query);

//7、在向量中查询数据
//SearchAsync方法的第二个参数是，希望能获取几个结果。现在是2个结果
var results = collection.SearchAsync<ReadOnlyMemory<float>>(queryEmbedding, 2);

//8、将结果展示出来
await foreach (var result in results)
{
    Console.WriteLine($"Key: {result.Record.Key}, Text: {result.Record.Title}");
}

Console.ReadLine();


//定义数据类型
public class Movie
{
    [VectorStoreKey]
    public ulong Key { get; set; }
		
		//title和Description是payload
    [VectorStoreData]
    public string? Title { get; set; }

    [VectorStoreData]
    public string? Description { get; set; }

    [VectorStoreVector(384, DistanceFunction = DistanceFunction.CosineSimilarity, IndexKind = IndexKind.Hnsw)]
    public ReadOnlyMemory<float> Vector { get; set; }
}

2.5、实现效果

3、总结

这里面的版本不太稳定，方法变化挺多。调试费劲。