实施者的RAG:使用 ONNX 和 Qdrant 进行 CPU 友好语义搜索

Tuesday, 25 November 2025

一. 导言导言导言导言导言导言一,导言导言导言导言导言导言

部分RAG系列: 这是第4a部分----核心执行:

第1部分:RAG起源和基本要点 - 什么是嵌入,为什么它们重要
第2部分:RAG建筑和内部 - 启动、象征化、矢量数据库
第3部分:在实务中协助通知书 - 建立完整的ARAG系统
第4a部分:ONNX和Qdrant执行 (本条) - CPU友好语义搜索基金会
第4b部分:语义搜索行动 - 头型、混合搜索和UI组件
第5部分:混合搜索和自动插入 - 生产一体化模式
第6部分:图表 - 用于了解人身知识的知识图

第1至3部分解释 为什么 语义搜索工作。此文章显示 如何如何 建立基础 -- -- a 零成本、有利于CPU的执行 使用 ONNX 运行时间和 Qdrant 。第4部分b 包括搜索界面和混合搜索执行,以及第5部分第五部分包括自动索引制作。

挑战: 多数语义搜索解决方案都需要昂贵的 GPU 基础设施或高成本的管理服务。如果您是独立开发商,

解决方案: 一个功能齐全的语义搜索系统, 完全在 CPU 上运行, 使用免费的开放源码工具。这是这个博客上正在运行的精确设置 — — 超过现有主机的零额外成本。

核心概念核心概念

这些概念在《公约》中得到了深入的阐述。 RAG系列,但以下是您需要知道的。

嵌入式:文本为数字

嵌入器是捕捉到这些物体的矢量(数组数) 意思。类似的含义产生相似的矢量, 这就是魔力。

graph TD
    A["Text: 'The cat sat on the mat'"] --> B[Embedding Model]
    B --> C["Vector: [0.25, -0.18, 0.91, ... 384 more numbers]"]
    D["Text: 'A feline rested on the carpet'"] --> B
    B --> E["Vector: [0.27, -0.16, 0.89, ... similar numbers!]"]

    C -.Similar vectors = similar meaning.-> E

    style A stroke:#10b981,stroke-width:2px
    style D stroke:#10b981,stroke-width:2px
    style B stroke:#6366f1,stroke-width:3px
    style C stroke:#f59e0b,stroke-width:2px
    style E stroke:#f59e0b,stroke-width:2px

关键洞察力: 具有类似含义的文字将具有相似的矢量( 组合 ) 。这就是我们如何找到“ 相关” 内容- 我们实际上是在测量含义之间的距离 !

理解余心相似性

余余相相似性测量两个矢量之间的角 - 如果他们指向相似的方向, 它们在语义上是相似的 :

flowchart LR
    subgraph "Vector Space (simplified to 2D)"
        direction TB
        A["'Docker tutorial'"] -.-> B((0.85))
        C["'Container deployment'"] -.-> B
        D["'Cooking recipes'"] -.-> E((0.12))
        A -.-> E
    end

    B --> F["High Similarity<br/>Related content!"]
    E --> G["Low Similarity<br/>Different topics"]

    style A stroke:#10b981,stroke-width:2px
    style C stroke:#10b981,stroke-width:2px
    style D stroke:#f59e0b,stroke-width:2px
    style B stroke:#22c55e,stroke-width:3px
    style E stroke:#ef4444,stroke-width:3px
    style F stroke:#22c55e,stroke-width:2px
    style G stroke:#ef4444,stroke-width:2px

公式 : similarity = (A · B) / (||A|| × ||B||) - 但是既然我们L2实现了向量的正常化, 它就简化成了仅仅的点产品!

什么是ONNX?

ONNX(开放神经网络交换) 是一个用于机器学习模型的开放标准格式, 使其能够在不同平台上高效运行。把它想象成一个通用的 AI 模型翻译器。 ONNX 运行时间是微软的高性能推断引擎执行这些模型

为何使用ONNX案例:

CPU 运行( 不需要 GPU ! ) - 见 ONNX 运行时 CPU 执行提供方 docs
比在 Python 运行模型快得多
较小的记忆足迹
以.NET 和.NET 通过微软.ML. OnnnxRuntime Nuget 软件包
支助支助图形优化快速推断

flowchart LR
    subgraph "ONNX Inference Pipeline"
        A[Raw Text] --> B[Tokenizer]
        B --> C["Tokens: [CLS] the cat sat [SEP]"]
        C --> D[Token IDs: 101 1996 4937 2068 102]
        D --> E[ONNX Runtime]
        E --> F[384-dim Vector]
        F --> G[L2 Normalize]
        G --> H[Final Embedding]
    end

    style A stroke:#10b981,stroke-width:2px
    style B stroke:#f59e0b,stroke-width:2px
    style C stroke:#f59e0b,stroke-width:2px
    style D stroke:#f59e0b,stroke-width:2px
    style E stroke:#6366f1,stroke-width:3px
    style F stroke:#8b5cf6,stroke-width:2px
    style G stroke:#8b5cf6,stroke-width:2px
    style H stroke:#ef4444,stroke-width:2px

什么是 Qdrant ?

解冻是一个开放源源矢量数据库 - 基本上是储存和搜索这些嵌入矢量的最佳数据库。要深入潜入 Qdrant 的概念、配置和 C# 集成,请查看带有 Qdrant 的自住矢量数据库。而当你能够 PostgreSQL中的存储矢量, Qdrant是为此专门建造的, 提供:

使用闪电-快速近效搜索 HNSW 算法
元数据过滤过滤 - 有效载荷场的过滤结果
向成百万个矢量的部署部署
低资源使用率 -- -- 使用少量硬件可舒适地使用
与多克自负自负看 Qdrant Docker 快速启动
g/RPC和REST APPs 和融合的融合
通过下列方式支持土著.NET Qdrant. Client Nuget 软件包

flowchart TB
    subgraph "Qdrant Vector Storage"
        direction TB
        A[Collection: blog_posts] --> B[Point 1]
        A --> C[Point 2]
        A --> D[Point N...]

        B --> B1["Vector: [0.12, -0.08, ...]"]
        B --> B2["Payload: {slug, title, language}"]

        C --> C1["Vector: [0.25, 0.14, ...]"]
        C --> C2["Payload: {slug, title, language}"]
    end

    subgraph "Vector Search"
        E[Query Vector] --> F[HNSW Index]
        F --> G[Cosine Similarity]
        G --> H[Top K Results]
    end

    style A stroke:#ef4444,stroke-width:3px
    style B stroke:#8b5cf6,stroke-width:2px
    style C stroke:#8b5cf6,stroke-width:2px
    style D stroke:#8b5cf6,stroke-width:2px
    style B1 stroke:#f59e0b,stroke-width:2px
    style B2 stroke:#10b981,stroke-width:2px
    style C1 stroke:#f59e0b,stroke-width:2px
    style C2 stroke:#10b981,stroke-width:2px
    style E stroke:#6366f1,stroke-width:2px
    style F stroke:#ec4899,stroke-width:3px
    style G stroke:#ec4899,stroke-width:2px
    style H stroke:#10b981,stroke-width:2px

建筑结构概览

我们的语义搜索系统是如何搭配在一起的:

flowchart TB
    subgraph "Content Ingestion"
        A[Blog Post Markdown] --> B[Extract Plain Text]
        B --> C[ONNX Embedding Service]
        C --> D[Generate 384-dim Vector]
        D --> E[Qdrant Vector Store]
    end

    subgraph "Search Flow"
        F[User Query] --> G[ONNX Embedding Service]
        G --> H[Generate Query Vector]
        H --> I[Qdrant Search]
        E -.Vector Similarity.-> I
        I --> J[Ranked Results]
    end

    subgraph "Related Posts"
        K[Current Blog Post] --> L[Get Post Vector from Qdrant]
        L --> M[Find Similar Vectors]
        E -.->M
        M --> N[Top 5 Related Posts]
    end

    style A stroke:#10b981,stroke-width:2px
    style B stroke:#10b981,stroke-width:2px
    style C stroke:#6366f1,stroke-width:3px
    style D stroke:#f59e0b,stroke-width:2px
    style E stroke:#ef4444,stroke-width:3px
    style F stroke:#10b981,stroke-width:2px
    style G stroke:#6366f1,stroke-width:3px
    style H stroke:#f59e0b,stroke-width:2px
    style I stroke:#ef4444,stroke-width:2px
    style J stroke:#8b5cf6,stroke-width:2px
    style K stroke:#10b981,stroke-width:2px
    style L stroke:#ef4444,stroke-width:2px
    style M stroke:#ef4444,stroke-width:2px
    style N stroke:#8b5cf6,stroke-width:2px

以普通英语流出:

编制索引索引: 当你写博客文章时, 我们将其转换为矢量, 并存储在 Qdrant 中。
搜索:当某人搜索时,我们将其查询转换为矢量,并在 Qdrant 中找到类似的矢量。
相关员额: 对于任何博客文章, 我们可以找到其它带有类似矢量的日志。

项目结构

我们创造了一个干净的模块结构:

Mostlylucid.SemanticSearch/
├── Config/
│   └── SemanticSearchConfig.cs      # Configuration settings
├── Models/
│   ├── BlogPostDocument.cs          # Document model for indexing
│   └── SearchResult.cs               # Search result model
├── Services/
│   ├── IEmbeddingService.cs         # Embedding interface
│   ├── OnnxEmbeddingService.cs      # ONNX-based embeddings
│   ├── IVectorStoreService.cs       # Vector store interface
│   ├── QdrantVectorStoreService.cs  # Qdrant implementation
│   ├── ISemanticSearchService.cs    # High-level search interface
│   └── SemanticSearchService.cs     # Orchestration service
├── Extensions/
│   └── ServiceCollectionExtensions.cs  # DI registration
├── download-models.sh               # Model download script
└── README.md

执行执行情况执行

第1步:建立项目

首先,创建新的类库:

dotnet new classlib -n Mostlylucid.SemanticSearch -f net9.0
dotnet sln add Mostlylucid.SemanticSearch

添加必需的 Nuget 软件包 :

cd Mostlylucid.SemanticSearch
dotnet add package Microsoft.Extensions.Logging.Abstractions
dotnet add package Microsoft.ML.OnnxRuntime --version 1.21.1
dotnet add package Qdrant.Client --version 1.14.0
dotnet add reference ../Mostlylucid.Shared/Mostlylucid.Shared.csproj

第2步:配置

我们来安排我们的配置课我们用的是 IConfigSection 整个Mostlylucid使用的模式 :

using Mostlylucid.Shared.Config;

namespace Mostlylucid.SemanticSearch.Config;

/// <summary>
/// Configuration for semantic search functionality
/// </summary>

public class SemanticSearchConfig : IConfigSection
{
    public static string Section => "SemanticSearch";

    /// <summary>
    /// Enable or disable semantic search
    /// </summary>

    public bool Enabled { get; set; } = true;

    /// <summary>
    /// Qdrant server URL (e.g., http://localhost:6333)
    /// </summary>

    public string QdrantUrl { get; set; } = "http://localhost:6333";

    /// <summary>
    /// Optional read-only API key for Qdrant (used for search operations)
    /// </summary>

    public string? ReadApiKey { get; set; }

    /// <summary>
    /// Optional read-write API key for Qdrant (used for indexing operations)
    /// </summary>

    public string? WriteApiKey { get; set; }

    /// <summary>
    /// Collection name in Qdrant for blog posts
    /// </summary>

    public string CollectionName { get; set; } = "blog_posts";

    /// <summary>
    /// Path to the ONNX embedding model file
    /// </summary>

    public string EmbeddingModelPath { get; set; } = "models/all-MiniLM-L6-v2.onnx";

    /// <summary>
    /// Path to the tokenizer vocabulary file
    /// </summary>

    public string VocabPath { get; set; } = "models/vocab.txt";

    /// <summary>
    /// Embedding vector size (384 for all-MiniLM-L6-v2)
    /// </summary>

    public int VectorSize { get; set; } = 384;

    /// <summary>
    /// Number of related posts to return
    /// </summary>

    public int RelatedPostsCount { get; set; } = 5;

    /// <summary>
    /// Minimum similarity score (0-1) for related posts
    /// </summary>

    public float MinimumSimilarityScore { get; set; } = 0.5f;

    /// <summary>
    /// Number of search results to return
    /// </summary>

    public int SearchResultsCount { get; set; } = 10;
}

为何单独使用API钥匙? 安全性 ! 您的读取密钥可以用于公共搜索端点, 而您写的密钥只用于管理操作, 只能用于服务器端。

添加此添加到您的 appsettings.json:

{
  "SemanticSearch": {
    "Enabled": false,
    "QdrantUrl": "http://localhost:6333",
    "ReadApiKey": "",
    "WriteApiKey": "",
    "CollectionName": "blog_posts",
    "EmbeddingModelPath": "models/all-MiniLM-L6-v2.onnx",
    "VocabPath": "models/vocab.txt",
    "VectorSize": 384,
    "RelatedPostsCount": 5,
    "MinimumSimilarityScore": 0.5,
    "SearchResultsCount": 10
  }
}

步骤3:ONNX嵌入服务

这就是魔法发生的地方。我们正在使用全米尼LM-L6-V2模型, 它专门设计用于语义相似的任务, 并高效运行于 CPU 。

为什么是这个模型?

小型 (~ 90MB)
CPU 快速推断( 每嵌入到 $~ 50- 100 ms)
优质嵌入(384个维度)
培训了10亿对一对以上的判刑

以下是完整的执行 :

using Microsoft.Extensions.Logging;
using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
using Mostlylucid.SemanticSearch.Config;
using System.Text.RegularExpressions;

namespace Mostlylucid.SemanticSearch.Services;

public class OnnxEmbeddingService : IEmbeddingService, IDisposable
{
    private readonly ILogger<OnnxEmbeddingService> _logger;
    private readonly SemanticSearchConfig _config;
    private readonly InferenceSession? _session;
    private readonly Dictionary<string, int> _vocabulary;
    private readonly SemaphoreSlim _semaphore = new(1, 1);
    private bool _disposed;

    private const int MaxSequenceLength = 256;
    private const string PadToken = "[PAD]";
    private const string UnkToken = "[UNK]";
    private const string ClsToken = "[CLS]";
    private const string SepToken = "[SEP]";

    public OnnxEmbeddingService(
        ILogger<OnnxEmbeddingService> logger,
        SemanticSearchConfig config)
    {
        _logger = logger;
        _config = config;
        _vocabulary = new Dictionary<string, int>();

        if (!_config.Enabled)
        {
            _logger.LogInformation("Semantic search is disabled");
            return;
        }

        try
        {
            // Check if model file exists
            if (!File.Exists(_config.EmbeddingModelPath))
            {
                _logger.LogWarning("Embedding model not found at {Path}. Semantic search will be disabled.",
                    _config.EmbeddingModelPath);
                return;
            }

            // Load vocabulary if it exists
            if (File.Exists(_config.VocabPath))
            {
                LoadVocabulary(_config.VocabPath);
            }

            // Create ONNX session with CPU execution provider
            var sessionOptions = new SessionOptions
            {
                ExecutionMode = ExecutionMode.ORT_SEQUENTIAL,
                GraphOptimizationLevel = GraphOptimizationLevel.ORT_ENABLE_ALL
            };

            _session = new InferenceSession(_config.EmbeddingModelPath, sessionOptions);
            _logger.LogInformation("ONNX embedding model loaded successfully from {Path}",
                _config.EmbeddingModelPath);
        }
        catch (Exception ex)
        {
            _logger.LogError(ex, "Failed to initialize ONNX embedding service");
        }
    }

    private void LoadVocabulary(string vocabPath)
    {
        var lines = File.ReadAllLines(vocabPath);
        for (int i = 0; i < lines.Length; i++)
        {
            var token = lines[i].Trim();
            if (!string.IsNullOrEmpty(token))
            {
                _vocabulary[token] = i;
            }
        }
        _logger.LogInformation("Loaded vocabulary with {Count} tokens", _vocabulary.Count);
    }

    public async Task<float[]> GenerateEmbeddingAsync(string text, CancellationToken cancellationToken = default)
    {
        if (_session == null || !_config.Enabled)
        {
            return new float[_config.VectorSize];
        }

        if (string.IsNullOrWhiteSpace(text))
        {
            return new float[_config.VectorSize];
        }

        // Use semaphore to prevent concurrent ONNX inference (not thread-safe)
        await _semaphore.WaitAsync(cancellationToken);
        try
        {
            return await Task.Run(() => GenerateEmbedding(text), cancellationToken);
        }
        finally
        {
            _semaphore.Release();
        }
    }

    private float[] GenerateEmbedding(string text)
    {
        try
        {
            // Tokenize the input text
            var tokens = Tokenize(text);

            // Create input tensors for ONNX model
            var inputIds = CreateInputTensor(tokens, "input_ids");
            var attentionMask = CreateAttentionMaskTensor(tokens.Length);
            var tokenTypeIds = CreateTokenTypeIdsTensor(tokens.Length);

            // Run inference
            var inputs = new List<NamedOnnxValue>
            {
                NamedOnnxValue.CreateFromTensor("input_ids", inputIds),
                NamedOnnxValue.CreateFromTensor("attention_mask", attentionMask),
                NamedOnnxValue.CreateFromTensor("token_type_ids", tokenTypeIds)
            };

            using var results = _session!.Run(inputs);

            // Extract the output tensor (sentence embedding)
            var output = results.First().AsTensor<float>();
            var embedding = output.ToArray();

            // Normalize the vector (L2 normalization)
            return NormalizeVector(embedding);
        }
        catch (Exception ex)
        {
            _logger.LogError(ex, "Error generating embedding for text: {Text}",
                text[..Math.Min(100, text.Length)]);
            return new float[_config.VectorSize];
        }
    }

    private List<int> Tokenize(string text)
    {
        // Simple whitespace + punctuation tokenization
        var tokens = new List<int>();

        // Add [CLS] token at the start
        if (_vocabulary.TryGetValue(ClsToken, out var clsId))
            tokens.Add(clsId);

        // Tokenize the text
        var words = Regex.Split(text.ToLowerInvariant(), @"(\W+)")
            .Where(w => !string.IsNullOrWhiteSpace(w))
            .Take(MaxSequenceLength - 2); // Leave room for [CLS] and [SEP]

        foreach (var word in words)
        {
            if (_vocabulary.Count > 0)
            {
                if (_vocabulary.TryGetValue(word, out var tokenId))
                    tokens.Add(tokenId);
                else if (_vocabulary.TryGetValue(UnkToken, out var unkId))
                    tokens.Add(unkId);
            }
            else
            {
                // Fallback: use hash code as token ID
                tokens.Add(Math.Abs(word.GetHashCode()) % 30000);
            }
        }

        // Add [SEP] token at the end
        if (_vocabulary.TryGetValue(SepToken, out var sepId))
            tokens.Add(sepId);

        return tokens;
    }

    private Tensor<long> CreateInputTensor(List<int> tokens, string name)
    {
        var length = Math.Min(tokens.Count, MaxSequenceLength);
        var tensorData = new long[1, MaxSequenceLength];

        for (int i = 0; i < length; i++)
        {
            tensorData[0, i] = tokens[i];
        }

        // Pad the rest
        var padId = _vocabulary.TryGetValue(PadToken, out var id) ? id : 0;
        for (int i = length; i < MaxSequenceLength; i++)
        {
            tensorData[0, i] = padId;
        }

        return new DenseTensor<long>(tensorData, new[] { 1, MaxSequenceLength });
    }

    private Tensor<long> CreateAttentionMaskTensor(int actualLength)
    {
        var length = Math.Min(actualLength, MaxSequenceLength);
        var tensorData = new long[1, MaxSequenceLength];

        for (int i = 0; i < length; i++)
        {
            tensorData[0, i] = 1; // Attend to actual tokens
        }

        return new DenseTensor<long>(tensorData, new[] { 1, MaxSequenceLength });
    }

    private Tensor<long> CreateTokenTypeIdsTensor(int actualLength)
    {
        var tensorData = new long[1, MaxSequenceLength];
        // All zeros for single sentence
        return new DenseTensor<long>(tensorData, new[] { 1, MaxSequenceLength });
    }

    private float[] NormalizeVector(float[] vector)
    {
        // L2 normalization
        var sumOfSquares = vector.Sum(v => v * v);
        var magnitude = MathF.Sqrt(sumOfSquares);

        if (magnitude > 0)
        {
            for (int i = 0; i < vector.Length; i++)
            {
                vector[i] /= magnitude;
            }
        }

        return vector;
    }

    public void Dispose()
    {
        if (_disposed) return;

        _session?.Dispose();
        _semaphore?.Dispose();
        _disposed = true;

        GC.SuppressFinalize(this);
    }
}

初级学位的要点 :

当当当化:我们正在将文字破解成小块( 缩写) 模型可以理解
代数:这些是多维阵列,ONNX模型与这些阵列一起工作
注意掩码:告诉模型输入的哪个部分是实际内容相对于粘贴
L2 正常化:使所有矢量都有相同的“长度”,以便我们可以公平地比较它们。
塞马磷: 确保线条安全( ONNX 默认情况下不安全线条)

第4步: Qdrant 矢量存储

现在让我们执行矢量存储和搜索:

using Microsoft.Extensions.Logging;
using Mostlylucid.SemanticSearch.Config;
using Mostlylucid.SemanticSearch.Models;
using Qdrant.Client;
using Qdrant.Client.Grpc;

namespace Mostlylucid.SemanticSearch.Services;

public class QdrantVectorStoreService : IVectorStoreService
{
    private readonly ILogger<QdrantVectorStoreService> _logger;
    private readonly SemanticSearchConfig _config;
    private readonly QdrantClient? _client;
    private bool _collectionInitialized;

    public QdrantVectorStoreService(
        ILogger<QdrantVectorStoreService> logger,
        SemanticSearchConfig config)
    {
        _logger = logger;
        _config = config;

        if (!_config.Enabled)
        {
            _logger.LogInformation("Semantic search is disabled");
            return;
        }

        try
        {
            var uri = new Uri(_config.QdrantUrl);
            var host = uri.Host;
            var port = uri.Port > 0 ? uri.Port : 6334; // Default gRPC port

            _client = new QdrantClient(host, port, https: uri.Scheme == "https");
            _logger.LogInformation("Connected to Qdrant at {Host}:{Port}", host, port);
        }
        catch (Exception ex)
        {
            _logger.LogError(ex, "Failed to connect to Qdrant at {Url}", _config.QdrantUrl);
        }
    }

    public async Task InitializeCollectionAsync(CancellationToken cancellationToken = default)
    {
        if (_client == null || !_config.Enabled || _collectionInitialized)
            return;

        try
        {
            var collections = await _client.ListCollectionsAsync(cancellationToken);
            var collectionExists = collections.Any(c => c.Name == _config.CollectionName);

            if (!collectionExists)
            {
                _logger.LogInformation("Creating collection {CollectionName}", _config.CollectionName);

                await _client.CreateCollectionAsync(
                    collectionName: _config.CollectionName,
                    vectorsConfig: new VectorParams
                    {
                        Size = (ulong)_config.VectorSize,
                        Distance = Distance.Cosine // Cosine similarity for semantic search
                    },
                    cancellationToken: cancellationToken
                );

                _logger.LogInformation("Collection {CollectionName} created successfully", _config.CollectionName);
            }

            _collectionInitialized = true;
        }
        catch (Exception ex)
        {
            _logger.LogError(ex, "Failed to initialize collection {CollectionName}", _config.CollectionName);
            throw;
        }
    }

    public async Task<List<SearchResult>> FindRelatedPostsAsync(
        string slug,
        string language,
        int limit = 5,
        CancellationToken cancellationToken = default)
    {
        if (_client == null || !_config.Enabled)
            return new List<SearchResult>();

        try
        {
            // Find the document by slug and language
            var scrollResults = await _client.ScrollAsync(
                collectionName: _config.CollectionName,
                filter: new Filter
                {
                    Must =
                    {
                        new Condition
                        {
                            Field = new FieldCondition
                            {
                                Key = "slug",
                                Match = new Match { Keyword = slug }
                            }
                        },
                        new Condition
                        {
                            Field = new FieldCondition
                            {
                                Key = "language",
                                Match = new Match { Keyword = language }
                            }
                        }
                    }
                },
                limit: 1,
                cancellationToken: cancellationToken
            );

            var point = scrollResults.FirstOrDefault();
            if (point == null)
            {
                _logger.LogWarning("Post {Slug} ({Language}) not found in vector store", slug, language);
                return new List<SearchResult>();
            }

            // Use the document's vector to find similar posts
            var searchResults = await _client.SearchAsync(
                collectionName: _config.CollectionName,
                vector: point.Vectors.Vector.Data.ToArray(),
                limit: (ulong)(limit + 1), // +1 because the first result will be the post itself
                scoreThreshold: _config.MinimumSimilarityScore,
                cancellationToken: cancellationToken
            );

            // Filter out the original post and return top N similar posts
            return searchResults
                .Where(r => r.Payload["slug"].StringValue != slug || r.Payload["language"].StringValue != language)
                .Take(limit)
                .Select(result => new SearchResult
                {
                    Slug = result.Payload["slug"].StringValue,
                    Title = result.Payload["title"].StringValue,
                    Language = result.Payload["language"].StringValue,
                    Categories = result.Payload.TryGetValue("categories", out var cats)
                        ? cats.ListValue.Values.Select(v => v.StringValue).ToList()
                        : new List<string>(),
                    Score = result.Score,
                    PublishedDate = DateTime.Parse(result.Payload["published_date"].StringValue)
                })
                .ToList();
        }
        catch (Exception ex)
        {
            _logger.LogError(ex, "Failed to find related posts for {Slug} ({Language})", slug, language);
            return new List<SearchResult>();
        }
    }

    // ... Additional methods for IndexDocument, Search, Delete, etc.
}

这里发生了什么:

余弦距离:我们正在使用 cosine 相似性, 这对于比较正常的矢量来说是完美的。
元中元数据存储: Qdrant 允许我们在矢量的同时存储额外数据( 有效载荷) 。
过滤过滤:在比较矢量之前,我们可以通过元数据过滤结果
最低分数:只有返回结果超过某些相似得分

步骤5:管弦服务

这种高层次的服务将一切联系在一起:

using Microsoft.Extensions.Logging;
using Mostlylucid.SemanticSearch.Config;
using Mostlylucid.SemanticSearch.Models;
using System.Security.Cryptography;
using System.Text;

namespace Mostlylucid.SemanticSearch.Services;

public class SemanticSearchService : ISemanticSearchService
{
    private readonly ILogger<SemanticSearchService> _logger;
    private readonly SemanticSearchConfig _config;
    private readonly IEmbeddingService _embeddingService;
    private readonly IVectorStoreService _vectorStoreService;

    public SemanticSearchService(
        ILogger<SemanticSearchService> logger,
        SemanticSearchConfig config,
        IEmbeddingService embeddingService,
        IVectorStoreService vectorStoreService)
    {
        _logger = logger;
        _config = config;
        _embeddingService = embeddingService;
        _vectorStoreService = vectorStoreService;
    }

    public async Task IndexPostAsync(BlogPostDocument document, CancellationToken cancellationToken = default)
    {
        if (!_config.Enabled)
            return;

        try
        {
            // Prepare text for embedding: combine title and content
            // We give more weight to the title by including it twice
            var textToEmbed = $"{document.Title}. {document.Title}. {document.Content}";

            // Truncate to reasonable length (embedding models have token limits)
            const int maxLength = 2000;
            if (textToEmbed.Length > maxLength)
            {
                textToEmbed = textToEmbed[..maxLength];
            }

            // Generate embedding
            var embedding = await _embeddingService.GenerateEmbeddingAsync(textToEmbed, cancellationToken);

            // Compute content hash if not provided
            if (string.IsNullOrEmpty(document.ContentHash))
            {
                document.ContentHash = ComputeContentHash(document.Content);
            }

            // Store in vector database
            await _vectorStoreService.IndexDocumentAsync(document, embedding, cancellationToken);

            _logger.LogInformation("Indexed post {Slug} ({Language})", document.Slug, document.Language);
        }
        catch (Exception ex)
        {
            _logger.LogError(ex, "Failed to index post {Slug} ({Language})", document.Slug, document.Language);
        }
    }

    public async Task<List<SearchResult>> SearchAsync(
        string query,
        int limit = 10,
        CancellationToken cancellationToken = default)
    {
        if (!_config.Enabled || string.IsNullOrWhiteSpace(query))
            return new List<SearchResult>();

        try
        {
            // Generate embedding for the search query
            var queryEmbedding = await _embeddingService.GenerateEmbeddingAsync(query, cancellationToken);

            // Search in vector store
            var results = await _vectorStoreService.SearchAsync(
                queryEmbedding,
                Math.Min(limit, _conken);

            _logger.LogDebug("Search for '{Query}' returned {Count} results", query, results.Count);

            return results;
        }
        catch (Exception ex)
        {
            _logger.LogError(ex, "Search failed for query '{Query}'", query);
            return new List<SearchResult>();
        }
    }

    public async Task<List<SearchResult>> GetRelatedPostsAsync(
        string slug,
        string language,
        int limit = 5,
        CancellationToken cancellationToken = default)
    {
        if (!_config.Enabled)
            return new List<SearchResult>();

        try
        {
            var results = await _vectorStoreService.FindRelatedPostsAsync(
                slug,
                language,
                Math.Min(limit, _config.RelatedPostsCount),
                cancellationToken);

            _logger.LogDebug("Found {Count} related posts for {Slug} ({Language})",
                results.Count, slug, language);

            return results;
        }
        catch (Exception ex)
        {
            _logger.LogError(ex, "Failed to get related posts for {Slug} ({Language})", slug, language);
            return new List<SearchResult>();
        }
    }

    private string ComputeContentHash(string content)
    {
        using var sha256 = SHA256.Create();
        var bytes = Encoding.UTF8.GetBytes(content);
        var hashBytes = sha256.ComputeHash(bytes);
        return Convert.ToBase64String(hashBytes);
    }
}

步骤6:依赖注射设置

登记在DI容器中的一切:

using Microsoft.Extensions.Configuration;
using Microsoft.Extensions.DependencyInjection;
using Mostlylucid.SemanticSearch.Config;
using Mostlylucid.SemanticSearch.Services;
using Mostlylucid.Shared.Config;

namespace Mostlylucid.SemanticSearch.Extensions;

public static class ServiceCollectionExtensions
{
    public static void AddSemanticSearch(
        this IServiceCollection services,
        IConfiguration configuration)
    {
        // Bind configuration using POCO pattern
        services.ConfigurePOCO<SemanticSearchConfig>(
            configuration.GetSection(SemanticSearchConfig.Section));

        // Register services as singletons for efficiency
        services.AddSingleton<IEmbeddingService, OnnxEmbeddingService>();
        services.AddSingleton<IVectorStoreService, QdrantVectorStoreService>();
        services.AddSingleton<ISemanticSearchService, SemanticSearchService>();
    }
}

在你的 Program.cs:

using Mostlylucid.SemanticSearch.Extensions;
using Mostlylucid.SemanticSearch.Services;

// Add services
services.AddSemanticSearch(config);

// Initialize after building the app
using (var scope = app.Services.CreateScope())
{
    var semanticSearch = scope.ServiceProvider.GetRequiredService<ISemanticSearchService>();
    await semanticSearch.InitializeAsync();
}

建立基础设施

Qdrant 的 docker 混音

为语义搜索服务创建单独的 docker 合成文件 :

version: '3.8'

services:
  qdrant:
    image: qdrant/qdrant:latest
    container_name: mostlylucid-qdrant
    restart: unless-stopped
    ports:
      - "6333:6333"  # HTTP API
      - "6334:6334"  # gRPC API
    volumes:
      - qdrant_storage:/qdrant/storage
    environment:
      - QDRANT__SERVICE__HTTP_PORT=6333
      - QDRANT__SERVICE__GRPC_PORT=6334
    networks:
      - mostlylucid_network
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:6333/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

volumes:
  qdrant_storage:
    driver: local

networks:
  mostlylucid_network:
    name: mostlylucidweb_app_network
    external: true

以下列方式开始:

docker-compose -f semantic-search-docker-compose.yml up -d

下载嵌入模型

我们在用全部米尼LM-L6-v2 来自 Huggging Face 的模型句子变换器该模式在语义相似性任务方面接受专门培训,并制作384维嵌入材料。

自动下载( 推荐)

如果不存在, 此服务会自动从 Hugging Face 自动下载模型 :

// In OnnxEmbeddingService.cs
private const string ModelUrl = "https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/resolve/main/onnx/model.onnx";
private const string VocabUrl = "https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/resolve/main/vocab.txt";

public async Task EnsureInitializedAsync(CancellationToken cancellationToken = default)
{
    if (_initialized || !_config.Enabled) return;

    // Download model if not exists
    if (!File.Exists(_config.EmbeddingModelPath))
    {
        _logger.LogInformation("Downloading ONNX embedding model to {Path}...", _config.EmbeddingModelPath);
        await DownloadFileAsync(ModelUrl, _config.EmbeddingModelPath, cancellationToken);
    }

    // Download vocab if not exists
    if (!File.Exists(_config.VocabPath))
    {
        _logger.LogInformation("Downloading vocabulary file to {Path}...", _config.VocabPath);
        await DownloadFileAsync(VocabUrl, _config.VocabPath, cancellationToken);
    }

    // Initialize ONNX session...
}

这在与 Docker 一起部署时特别有用 - 您可以为模型目录绘制一个音量 :

volumes:
  - ./mlmodels:/app/mlmodels  # Model persists across container restarts

手工手工下载下载

也可以手动下载:

chmod +x Mostlylucid.SemanticSearch/download-models.sh
./Mostlylucid.SemanticSearch/download-models.sh

或直接来自Huggging Face:

mkdir -p mlmodels
curl -L https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/resolve/main/onnx/model.onnx -o mlmodels/all-MiniLM-L6-v2.onnx
curl -L https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2/resolve/main/vocab.txt -o mlmodels/vocab.txt

此下载次数 :

all-MiniLM-L6-v2.onnx - (~900MB) - (~900MB) ONNX出口嵌入模型
vocab.txt - (~230KB) WordPiece 表示器词典

绩效考量

内嵌生成

CPU 性能: ~ 50- 100米/每嵌入现代 CPU
优化:我们用血肿来防止 ONNX 的同时推断
条纹:在批量指数化方面,分10-20批处理员额

矢量搜索

搜索速度: 收藏量最多为 100K 矢量的 < 10ms
内存使用: ~ 1KB 每个矢量(有元数据)
缩缩: Qdrant能够用微小的硬件处理数以百万计的矢量。

缓结战略

我们使用 ASP. NET 核心输出缓存:

[OutputCache(Duration = 7200, VaryByRouteValueNames = new[] {"slug", "language"})]

这些暗藏站长达两个小时,大大减少了负荷。

我们所建造的

您目前有一个完整的、正在使用的语义搜索基础 :

✅ ONNX 嵌入 - CPU方便,自动下载,从抱抱面
✅ Qdrant 矢量存储 - 与元数据过滤的快速相似搜索
✅ 相关员额 - 查找与语言内容相似的内容
✅ API 搜索 API - 自然语言查询
✅ 内容索引编制 - 将博客文章作为矢量存储

这是这个博客上正在运行的精确设置 - 零GPU,零额外费用。

下一步: 语义搜索在动作中

内第4b部分:语义搜索行动,我们覆盖:

类型标题搜索 阿尔卑斯山的搜索工作方式
混合搜索 - 将语义语义 + PostgreSQL 全文与相互列队融合相结合
API 搜索 API - 带有过滤器的完整API文件
相关员额 - 带有HTMX懒货装载的DaisaUI组件
高级过滤器 - 语言和日期范围的筛选

继续第4部分b 搜索界面和混合搜索执行。

然后第5部分:混合搜索和自动插入包括生产一体化模式。

资源资源资源资源资源资源资源资源资源资源

ONNX 文件

ONNX 官方网站 - ML模型的开放标准
ONNX 运行时间 - 微软高性能推断引擎
ONNX 运行时间 .NET API - C# API docs
ONNX 运行时性能 - 优化指南

Qdrant 文档文档

带有 Qdrant 的自住矢量数据库 - 深入潜入 Qdrant 概念和 C# 客户端
解冻官方文件 - 主要文件中心
快速启动 Qdrant - 开始
Qdrant 矢量索引 - HNSW 算法
Qdrant.net 客户端 - 官方的. NETSDK

嵌嵌模型

全部米尼LM-L6-v2 - 我们使用的模型
句子变换器 - 语义嵌入图书馆

完整代码

所有代码可用于: com/scottgal/ mostlylylucidweb 缩略图/ com/ scottgal/ mostlylylucidweb 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图/ 缩略图

Mostlylucid.SemanticSearch/ - 核心语义搜索库