一. 导言导言导言导言导言

📖+RAG系列的一部分 本部分为“4a -核心执行”

RAG 起源和基本要点 “-”什么嵌入是“,”,为什么它们重要?
RAG 建筑和内部 @ -_ Chunking,}代号@,}矢量数据库
内容:3: 建立完整的RAG系统
“4a :ONNX”“& Qdrant 履行” MPK0 @ this article\ _ _ MS K2} CPU% -}友好的语义搜索基金会
操作中的语义搜索 -typeahead,混合搜索@,和UI组件
@ 5:_ 混合搜索@ MS K1\ 自动 @ MASK2 @ Indexing 生产一体化模式
6: 图表集 - 用于 proposal_- 水平理解的知识图表

1-3 @ 解释为什么语义搜索工作@. @% 此文章显示如何建立基金会 CPU=-}便利执行使用 ONNX 运行时间和 Qdrant @ . 第一部分#4b 包括搜索 UI 和混合搜索执行@,}及部分#5 覆盖自动生产@-_indexing @.

《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#: 功能齐全的语义搜索系统, 它完全运行在 CPU@ MSKK0}使用 Free Open @ MS K1 source makings . {这是这个博客上正在运行的确切设置 {-} 零额外成本超过现有主机 < MSC4 > =%

核心概念

这些概念在《公约》中得到了深入阐述。 RAG系列@, @% 但在此 @ '_%s 您需要知道什么来实施此执行@:

内嵌嵌入@ :文本为数字

嵌入式是捕捉到该天体的矢量 (数数数中的矢量\ ) 意思类似的含义产生相似的矢量 -\ \ ,\ MOSK2\ + 魔法= MSC3\ {

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会有相似矢量 {(} embeddings).这样我们才能找到 \ "}\ 相关{MS K3 内容 {-}\ we}'re 字面上测量意义之间的距离=!}

理解余心相似性

余心相似性测量两个矢量之间的角@-,如果它们指向类似的方向 @, 它们#'re 语义相似:

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||) @-,但自从我们L2- 调整我们的向量#, 它简化到仅仅点产物@!

什么是ONNX ??

开放神经网络交流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。 “.” 把它想象成是AI 模式的通用翻译器“.” NONX 运行时间是执行这些模型的微软'+Qs high-}性能推断引擎=.}

为什么我们需要ONNX?

CPU 上的运行@( @no GPU 需要 !)}\ MPK2看到 ONNX 运行时 CPU 执行供应商 docs
比在 Python 运行模型快得多
较小的记忆足迹
通过 & . @NET Microsoft .ML.OnnxRuntime 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 OpenQ-源矢量数据库 @ - 基本上是一个存储和搜索这些嵌入矢量的优化数据库@ MS K2 要深潜到 Qdrant'}{概念\ , 配置@,和 Cç#}整合 , 见带有 Qdrant 的自定义“-” 矢量数据库# 和你在一起的时候# 能够 PostgreSQL, Qdrant 中的存储矢量是为此而建造的,并且提供\ :

使用 Lightning+-#fast 类似搜索 HNSW 算法
元数据过滤 - 有效载荷字段的过滤结果
向成百万个矢量的已分配部署
低资源使用量 - 轻巧的硬件可舒适地运行
以 Docker 为主的自定义@- @ access Qdrant Docker 快速启动
g/RPC和REST APPs 融合的融入
@.NET 本地支持 Qdrant.Cclient 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如何搭配 : *

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

以纯英语的流 :

索引编制: 写博客 post @,时, 我们将其转换为矢量并存储在 Qdrant
搜索@ : @ {当有人搜索 MS K1} 我们将其查询转换为矢量, 在 Qdrant 中找到相似的矢量
相关员额@:_ 任何博客的possible post@,}我们能找到类似矢量的其他文章

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

设置工程

创建新类库@: @

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

添加必需的 Nuget 软件包@: @% 1

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

步骤 @ 2:_ 配置

让' @%s 设置我们的配置类@ . @ we'}使用 IConfigSection Mostlylucid@ : NAME OF TRANSLATORS 中所使用的值

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;
}

为何分隔 API 键“?” 安全@! 您的读密钥可以用于公共场合 @ - afacing search endpoints@ MS K2}而您写入的密钥只用于管理操作 @ MPK4}

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
  }
}

ONNX嵌入服务

在此出现魔法发生的地方 @.We're 使用全部@-MiniLM}-L6-vMS K5model_,。该模型是专门为语义相似性任务设计的,并高效运行于 CPU+.

为何这个模型?

大小小@(~90MB)
每个嵌入中的 CPU @ (~50-100 @ ms
优质嵌入@(384 @ 维度 @ )#
培训了超过10亿对的刑期

这里的'%s 完整执行@: @%

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 Devs: 的要点

声当化:We' 正在将文字破解成小块 @ MS K2tokens@)该模型能够理解
代数: 这些是MONX模型使用的多维数组
注意掩码: 告诉了输入中哪些部分是实际内容的模型 vs.padding
L2 正常化: 使所有向量都具有相同的 MS K1 长 ", 这样我们就可以公平地比较它们
塞马磷@ :_ 确保线条安全 % 1@ ONNX is MS K2} t线索@ -# 默认安全 * _

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.
}

这里发生什么了?

余弦距离:We're使用相近的余弦@,,这非常适合比较正常向量
元数据存储: Qdrant 让我们在矢量的同时存储额外数据@ MS K1 payload)
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种相似得分

指挥服务处

高端服务将一切连结在一起

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, _config.SearchResultsCount),
                _config.MinimumSimilarityScore,
                cancellationToken);

            _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);
    }
}

\ 6:\ 依赖注射设置

在 DI 容器中登记所有内容@: @%

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 的嵌入器合成

为语义搜索服务创建单独的 docker @ -}composte 文件@ MS K1

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

从:开始

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

下载嵌入模型

我们正在使用 {\fn黑体\fs22\bord1\shad0\3aHBE\4aH00\fscx67\fscy66\2款来自 Huggging Face 的模型@' @%s 句子变换器该模型专门就语义相似性任务进行了培训,并制作了“384-”-维嵌入.}

自动下载@( @ 推荐@ )}

如果该服务确实存在 @ ' @ title@ MS K1} , 它会自动从 Hugging Face 下载模型的首运行模式。

// 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...
}

这在使用 Docker {-} 部署时特别有用, 您可以绘制模型目录的音量@ :} @

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

手动下载

option, 您可以手动下载手动@ :

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@ : @

all-MiniLM-L6-v2.onnx (~90MB) NSK2 ONNX- 出口嵌入模型
vocab.txt (~230KB)- WordPiece 表示器词典

业绩考量

内嵌生成

CPU 性能: ~50-100 mms 每嵌入现代CPU
优化: 我们用血压来防止同时发生ONNX的推理
条纹用于批量索引的: , 分批处理 process points

矢量搜索

搜索速度:{<10}%s 收藏至 @100K矢量
内存使用: MS K1KB 每个矢量( 元数据)
缩缩:Qdrant可以用微小的硬件处理数百万个矢量。

缓结战略

我们使用 ASP.NET 核心输出缓存\ :

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

@2@ hours ,}大大降低负载=.

我们所建造的

您目前有一个完整的 ,工作语义搜索基础@:

✅ ONNX 嵌入器 - CPU- 友好} MS K2 自动 - 下載自 Hugging face
✅ Qdrant 矢量存储 - 具有元数据过滤功能的快速相似搜索
✅ 相关员额 @- 找到相似的语义内容
✅ APIP 搜索 -自然语言查询
✅ 内容索引编制 @-_ 存储博客文章作为矢量

这是在这个博客上运行的精确设置 零GPU+,+0 零额外费用

下次:语义搜索动作Name

内操作中的语义搜索我们负责:

类型标题搜索 “-”搜索如何与阿尔卑斯山合作?
混合搜索 - 结合语义语义 + PostgreSQL full}- text 和对等合唱
APIP 搜索 - 带有过滤器的完整 API 文件
相关员额 -DisaiUI组件,带有HTMX懒惰装载
高级过滤器 - 语言和日期范围过滤

继续第一部分#4b 搜索 UI 和混合搜索执行@. @%

然后 @ 5:_ 混合搜索@ MS K1\ 自动 @ MASK2 @ Indexing 生产一体化模式*.

资源资源资源资源和资源资源资源

ONNX 文件

ONNX 官方网站 -ML模型的开放标准
NONX 运行时间 - 微软' 高端- 性能发酵引擎
ONNX 运行时间 @ .+NET API -C#API docs
ONNX 运行时性能 -优化指南

Qdrant 文档

带有 Qdrant 的自定义“-” 矢量数据库深潜到 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 正在启动
Qdrant 矢量索引 -+HNSW 算法
Qdrant @ .@NET 客户端 -=YTET -伊甸园字幕组=- 翻译:

嵌入模型

{\fn黑体\fs22\bord1\shad0\3aHBE\4aH00\fscx67\fscy66\2款 - 我们使用的模型
句子变换器 -语义嵌入库

完整代码

所有代码都可用于 @: @% 多数为平质网,

Mostlylucid.SemanticSearch/ -核心语义搜索库

用 ONNX 和 Qdrant 友好语义搜索

一. 导言导言 导言 导言 导言

1-3 @ 解释 为什么 语义搜索工作@. @% 此文章显示 如何 建立基金会 CPU=-}便利执行 使用 ONNX 运行时间和 Qdrant @ . 第一部分#4b 包括搜索 UI 和混合搜索执行@,}及 部分#5 覆盖自动生产@-_indexing @.

核心概念

内嵌嵌入@ :文本为数字

理解余心相似性

什么是ONNX ??

什么是 Qdrant?

建筑结构概览

项目结构

执行 执行情况

设置工程

步骤 @ 2:_ 配置

ONNX嵌入服务

Qdrant 矢量存储

指挥服务处

\ 6:\ 依赖注射设置

建立基础设施

Qdrant 的嵌入器合成

下载嵌入模型

自动下载@( @ 推荐@ )}

手动下载

业绩考量

内嵌生成

矢量搜索

缓结战略

我们所建造的

下次:语义搜索动作Name

资源资源资源 资源和资源资源资源

ONNX 文件

Qdrant 文档

嵌入模型

完整代码

一. 导言导言导言导言导言

1-3 @ 解释为什么语义搜索工作@. @% 此文章显示如何建立基金会 CPU=-}便利执行使用 ONNX 运行时间和 Qdrant @ . 第一部分#4b 包括搜索 UI 和混合搜索执行@,}及部分#5 覆盖自动生产@-_indexing @.

执行执行情况

资源资源资源资源和资源资源资源