为您的博客建设“律师GPT” - 第三部分:了解嵌入和矢量数据库

Wednesday, 12 November 2025

警告:这些是“加入”的草稿。

可能很多下面的东西是行不通的; 我制作了这些作为给ME的操作方法, 然后做所有步骤,让样本应用起作用...你一直偷偷摸摸地看到它们!它们很可能在12月中旬就绪。

## 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

欢迎来到第三部分我们已经得到了我们的GPU堆叠工作(GPU) (GPU) (GPU) 第二部分第二部分),我们理解这个结构(第一部分第一部分**现在该是潜入魔法的时候了让语义搜索成为可能嵌入**.

和

矢量数据库

注:这是我对人工智能(协助起草)和我自己编辑的实验的一部分。

同一个声音,同样的务实;只是更快的手指。

这就是事情变得有趣的地方。

我们将理解如何用数字而不是关键词来表达文本的含义。

graph TD
    subgraph "2D Embedding Space (simplified)"
        A[cat: 0.8, 0.2]
        B[kitten: 0.7, 0.3]
        C[dog: 0.6, 0.1]
        D[puppy: 0.5, 0.2]
        E[car: -0.5, 0.8]
        F[vehicle: -0.6, 0.7]
        G[database: 0.1, -0.7]
        H[SQL: 0.2, -0.8]
    end

    class A,B cats
    class C,D dogs
    class E,F vehicles
    class G,H tech

    classDef cats stroke:#333
    classDef dogs stroke:#333
    classDef vehicles stroke:#333
    classDef tech stroke:#333

区别在于找到含有“docker”字眼的文章与找到关于集装箱化概念的语义化文章。

什么是嵌入?
嵌入是作为矢量的文字(或图像、音频等)的数值表示----基本上是数字列表。
直觉
试想在二维空域内基于其含义的文字图示 :

**类似概念组群组合在一起:**宠物(红/绿)彼此相近

车辆(蓝色)分类

技术术语(黄)群集

无关联的概念相去甚远,相距甚远
实际嵌入

graph LR
    A[Text: 'Docker container'] --> B[Embedding Model]
    B --> C[Vector: 384 floats]

    D[Text: 'containerization'] --> B
    B --> E[Vector: 384 floats]

    C -.Similar.-> E

    F[Text: 'chocolate cake'] --> B
    B --> G[Vector: 384 floats]

    C -.Very Different.-> G

    class B model
    class C,E similar
    class G different

    classDef model stroke:#333,stroke-width:4px
    classDef similar stroke:#333
    classDef different stroke:#333

使用384 至 1536 维(不只是 2! ) , 细微得多。

如何运作**嵌入模型是一个神经网络,受过培训,可以将文字映射到矢量上,例如:**类似的意思关闭矢量

public static float CosineSimilarity(float[] vectorA, float[] vectorB)
{
    if (vectorA.Length != vectorB.Length)
        throw new ArgumentException("Vectors must have same length");

    // Dot product: sum of element-wise multiplication
    float dotProduct = 0;
    for (int i = 0; i < vectorA.Length; i++)
    {
        dotProduct += vectorA[i] * vectorB[i];
    }

    // Magnitude of each vector: sqrt(sum of squares)
    float magnitudeA = 0;
    float magnitudeB = 0;
    for (int i = 0; i < vectorA.Length; i++)
    {
        magnitudeA += vectorA[i] * vectorA[i];
        magnitudeB += vectorB[i] * vectorB[i];
    }
    magnitudeA = MathF.Sqrt(magnitudeA);
    magnitudeB = MathF.Sqrt(magnitudeB);

    // Cosine similarity: dot product / (magnitude_a * magnitude_b)
    return dotProduct / (magnitudeA * magnitudeB);
}

不同的意思 `远端矢量':

1.0测量相似性
0.0我们用
-1.0余弦相似性

测量两个矢量之间的距离::

var dockerEmbed = new float[] { 0.5f, 0.3f, -0.2f, 0.8f };  // "Docker container"
var containerEmbed = new float[] { 0.45f, 0.35f, -0.18f, 0.75f };  // "containerization"
var cakeEmbed = new float[] { -0.7f, 0.1f, 0.9f, -0.3f };  // "chocolate cake"

Console.WriteLine(CosineSimilarity(dockerEmbed, containerEmbed));  // ~0.95 (very similar!)
Console.WriteLine(CosineSimilarity(dockerEmbed, cakeEmbed));  // ~0.15 (unrelated)

共生相近性介于-1至1之间

= 相同含义

= 无关

=相反的含义(实践中少见)

示例示例示例示例
为何嵌入为适合我们使用的案例
记住,我们正在建一个写作助理
当我开始写:

**"在这篇文章中,我将展示如何使用实体框架..."**系统应发现过去的职位有:

实体框架

graph TB
    subgraph "Traditional Keyword Search"
        A1[Query: 'Docker setup'] --> B1[Find: 'Docker' OR 'setup']
        B1 --> C1[❌ Misses: 'containerization guide']
        B1 --> D1[❌ Misses: 'running containers']
        B1 --> E1[✅ Finds: 'Docker setup tutorial']
    end

    subgraph "Embedding-Based Semantic Search"
        A2[Query: 'Docker setup'] --> B2[Generate embedding]
        B2 --> C2[Find similar embeddings]
        C2 --> D2[✅ Finds: 'containerization guide']
        C2 --> E2[✅ Finds: 'running containers']
        C2 --> F2[✅ Finds: 'Docker setup tutorial']
    end

    class B2,C2 semantic

    classDef semantic stroke:#333,stroke-width:2px

数据库使用模式

ORM 配置

相关ASP.NET核心专题不只是关键字匹配!
**它应该明白,“EF核心移民”是相关的, 即使它不说“实体框架”。**嵌入式对传统搜索
选择嵌入模型有许多嵌入模型。
**我们需要一个:**本地运行

(隐私+速度)

使用 ONNX 使用 ONNX 工作 |-------|------------|------|---------|-------| | (所以我们可以使用我们的GPU) | 384 | 80MB | Good | Very Fast ⚡⚡⚡ | | 良好质量 | 768 | 420MB | Better | Fast ⚡⚡ | | (准确的语义理解) | 384 | 133MB | Better | Very Fast ⚡⚡⚡ | | 右右侧大小 | 768 | 436MB | Best | Fast ⚡⚡ | | (384-768维是良好的平衡) | 1536 | N/A (API) | Excellent | Slow (network) ⚡ |

人民选择: 模范尺寸大小质量速度速度

全部米尼LM-L6-v2
全mpnet- base-v2
b- 小至小v1.5
b- 基底- en- v1.5

OpenAI 文本编组- ad- 002

我的建议建议

b- 基底- en- v1.5:

pip install optimum[exporters]

最先进的开放源码模式:

optimum-cli export onnx --model BAAI/bge-base-en-v1.5 --task feature-extraction bge-base-en-onnx/

768维(良好平衡)

bge-base-en-onnx/
    model.onnx           # The neural network
    tokenizer.json       # Text → tokens converter
    tokenizer_config.json
    special_tokens_map.json
    config.json

与 ONNX 合作很好运行时间: 本地自由运行

转换为 ONNX 格式

大多数模型都采用PyTorrch格式。

我们需要ONNX为C##。

mkdir EmbeddingTest
cd EmbeddingTest
dotnet new console
dotnet add package Microsoft.ML.OnnxRuntime.Gpu --version 1.16.3
dotnet add package Microsoft.ML.Tokenizers --version 0.1.0-preview.23511.1

安裝最佳( Python 库用于转换)

OnnxRuntime.Gpu转换 BGE 模式
Microsoft.ML.Tokenizers创建 :

如果您不想转换, 下载

许多模型都是预先变换的,

using Microsoft.ML.Tokenizers;
using System;
using System.Linq;

public class SimpleTokenizer
{
    private readonly Tokenizer _tokenizer;

    public SimpleTokenizer(string tokenizerPath)
    {
        // Load the tokenizer.json file
        _tokenizer = Tokenizer.CreateTokenizer(tokenizerPath);
    }

    public (long[] InputIds, long[] AttentionMask) Tokenize(string text, int maxLength = 512)
    {
        // Tokenize the text
        var encoding = _tokenizer.Encode(text);

        // Get token IDs
        var ids = encoding.Ids.Select(i => (long)i).ToArray();

        // Pad or truncate to maxLength
        var inputIds = new long[maxLength];
        var attentionMask = new long[maxLength];

        int length = Math.Min(ids.Length, maxLength);

        // Copy actual tokens
        Array.Copy(ids, inputIds, length);

        // Set attention mask (1 = real token, 0 = padding)
        for (int i = 0; i < length; i++)
        {
            attentionMask[i] = 1;
        }

        return (inputIds, attentionMask);
    }
}

使用 C # 中的嵌入字

让我们用ONNX运行时间建立一个实用的嵌入发电机项目设置[101, 8667, 2088, 102]
- 为什么这些包裹?
- - 在 GPU 上运行模型[- 将文本转换为符号 ID( 模型输入格式)[名化第一
**在嵌入前, 我们必须象征性化( 将文本转换为数字) :**这是怎么回事?
- 编码编码
- - "哈罗世界"
每个数字都是来自模型词汇表的代号 ID特殊标记:101=
- 1CLS],102=
- 0[中

graph LR
    A["Text: 'Docker setup'"] --> B[Tokenizer]
    B --> C[Token IDs:<br/>101, 12849, 12229, 102]
    C --> D[Pad to 512]
    D --> E[Input IDs:<br/>101, 12849, 12229, 102, 0, 0,...]
    D --> F[Attention Mask:<br/>1, 1, 1, 1, 0, 0,...]

    E --> G[Feed to Model]
    F --> G

    class B,G process

    classDef process stroke:#333,stroke-width:2px

贴贴

模型预期有固定长度的投入

using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
using System;
using System.Collections.Generic;
using System.Linq;

public class EmbeddingGenerator : IDisposable
{
    private readonly InferenceSession _session;
    private readonly SimpleTokenizer _tokenizer;
    private readonly int _embeddingDimension;

    public EmbeddingGenerator(string modelPath, string tokenizerPath, bool useGpu = true)
    {
        // Setup session options
        var options = new SessionOptions();
        if (useGpu)
        {
            options.AppendExecutionProvider_CUDA(0);
        }

        // Load model
        _session = new InferenceSession(modelPath, options);

        // Load tokenizer
        _tokenizer = new SimpleTokenizer(tokenizerPath);

        // Get embedding dimension from model output shape
        var outputMetadata = _session.OutputMetadata["last_hidden_state"];
        _embeddingDimension = outputMetadata.Dimensions[2]; // Usually 768 for base models
    }

    public float[] GenerateEmbedding(string text)
    {
        // Step 1: Tokenize
        var (inputIds, attentionMask) = _tokenizer.Tokenize(text);

        // Step 2: Create input tensors
        var inputIdsTensor = new DenseTensor<long>(inputIds, new[] { 1, inputIds.Length });
        var attentionMaskTensor = new DenseTensor<long>(attentionMask, new[] { 1, attentionMask.Length });

        var inputs = new List<NamedOnnxValue>
        {
            NamedOnnxValue.CreateFromTensor("input_ids", inputIdsTensor),
            NamedOnnxValue.CreateFromTensor("attention_mask", attentionMaskTensor)
        };

        // Step 3: Run inference
        using var results = _session.Run(inputs);

        // Step 4: Extract embeddings from output
        var outputTensor = results.First().AsTensor<float>();

        // Output shape is [batch_size, sequence_length, embedding_dim]
        // We want [batch_size, embedding_dim] by mean pooling

        return MeanPooling(outputTensor, attentionMask);
    }

    private float[] MeanPooling(Tensor<float> outputTensor, long[] attentionMask)
    {
        int seqLength = outputTensor.Dimensions[1];
        int embeddingDim = outputTensor.Dimensions[2];

        var embedding = new float[embeddingDim];
        int tokenCount = 0;

        // Average across all non-padded tokens
        for (int seq = 0; seq < seqLength; seq++)
        {
            if (attentionMask[seq] == 0) continue; // Skip padding

            tokenCount++;
            for (int dim = 0; dim < embeddingDim; dim++)
            {
                embedding[dim] += outputTensor[0, seq, dim];
            }
        }

        // Divide by count to get mean
        for (int dim = 0; dim < embeddingDim; dim++)
        {
            embedding[dim] /= tokenCount;
        }

        // Normalize to unit length (common practice)
        return Normalize(embedding);
    }

    private float[] Normalize(float[] vector)
    {
        float magnitude = 0;
        foreach (var val in vector)
        {
            magnitude += val * val;
        }
        magnitude = MathF.Sqrt(magnitude);

        var normalized = new float[vector.Length];
        for (int i = 0; i < vector.Length; i++)
        {
            normalized[i] = vector[i] / magnitude;
        }

        return normalized;
    }

    public void Dispose()
    {
        _session?.Dispose();
    }
}

如果文本短: 零的页面:

如果文本长: 短短注意遮罩
- 告诉模型哪个符号是真实的= 处理此标识符
**忽略( 它的垫) :**嵌入式发电机类
**现在,整个嵌入管道:**代码分类明细
模型装货- 在 GPU 支持下创建 ONNX 会话
当当当化- 将文本转换为代号 ID

开开台艺艺艺艺艺艺艺艺艺艺艺造艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺艺创艺艺艺艺艺艺艺

graph TB
    A[Model Output:<br/>Token Embeddings] --> B["Token 0 (CLS):<br/>(0.1, 0.5, -0.3, ...)"]
    A --> C["Token 1 (Docker):<br/>(0.4, 0.2, -0.1, ...)"]
    A --> D["Token 2 (setup):<br/>(0.3, 0.6, -0.2, ...)"]
    A --> E["Token 3 (SEP):<br/>(0.2, 0.3, -0.4, ...)"]

    B --> F[Average]
    C --> F
    D --> F
    E --> F

    F --> G["Sentence Embedding:<br/>(0.25, 0.4, -0.25, ...)"]

    class A input
    class F process
    class G output

    classDef input stroke:#333
    classDef process stroke:#333,stroke-width:2px
    classDef output stroke:#333,stroke-width:2px

模型输入的形状数据
推断
- 运行神经网络
平均共用

- 平均象征性嵌入单句嵌入

using System;

class Program
{
    static void Main(string[] args)
    {
        using var embedder = new EmbeddingGenerator(
            modelPath: "bge-base-en-onnx/model.onnx",
            tokenizerPath: "bge-base-en-onnx/tokenizer.json",
            useGpu: true
        );

        // Generate embeddings
        var embedding1 = embedder.GenerateEmbedding("Docker containerization tutorial");
        var embedding2 = embedder.GenerateEmbedding("Setting up containers with Docker");
        var embedding3 = embedder.GenerateEmbedding("Baking a chocolate cake");

        Console.WriteLine($"Embedding dimension: {embedding1.Length}");
        Console.WriteLine($"First 5 values: {string.Join(", ", embedding1.Take(5).Select(f => f.ToString("F4")))}");

        // Calculate similarities
        float sim12 = CosineSimilarity(embedding1, embedding2);
        float sim13 = CosineSimilarity(embedding1, embedding3);

        Console.WriteLine($"\nSimilarity (Docker vs Containers): {sim12:F4}");  // ~0.85
        Console.WriteLine($"Similarity (Docker vs Cake): {sim13:F4}");  // ~0.10
    }

    static float CosineSimilarity(float[] a, float[] b)
    {
        // Since vectors are normalized, dot product = cosine similarity
        float dot = 0;
        for (int i = 0; i < a.Length; i++)
        {
            dot += a[i] * b[i];
        }
        return dot;
    }
}

正常化:

Embedding dimension: 768
First 5 values: 0.0123, -0.0456, 0.0789, -0.0234, 0.0567

Similarity (Docker vs Containers): 0.8542
Similarity (Docker vs Cake): 0.1023

使矢量长度1(简化相似性计算)

平均合用资金

我们平均是因为:

每件信物都有自己的嵌入

整个句子需要一个嵌入

A. 动动动:

float bestSimilarity = -1;
int bestIndex = -1;

for (int i = 0; i < 10000; i++)
{
    float sim = CosineSimilarity(queryEmbedding, storedEmbeddings[i]);
    if (sim > bestSimilarity)
    {
        bestSimilarity = sim;
        bestIndex = i;
    }
}

使用率示例产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出

美丽!

历史相似的内容非常相似,不相干的内容很少。
矢量数据库

现在我们有嵌入。

我们需要储存数以百万计的地雷,并有效地搜索。

问题

graph TB
    A[Query Embedding] --> B[Vector Database]
    B --> C{HNSW Index}

    C --> D[Layer 2:<br/>Coarse Search]
    D --> E[Layer 1:<br/>Refined Search]
    E --> F[Layer 0:<br/>Exact Search]

    F --> G[Top K Results]

    H[10,000 vectors] -.Indexed.-> C

    class B db
    class C index
    class G results

    classDef db stroke:#333,stroke-width:4px
    classDef index stroke:#333,stroke-width:2px
    classDef results stroke:#333,stroke-width:2px

假设我们有1000个博客文章,:

原始搜索
问题
这是O(n) - 我们检查每一个嵌入。

慢点!

10 000个嵌入层x768个维度各:

~3 000万浮动点行动

即使在快速CPU上也~50-100米
我们需要更快的东西。
矢量数据库解决方案
矢量数据库使用智能数据结构(如 HNSW - 高层次可控小型世界图表)在 O( log n) 时间找到最近的邻居。

速度比较 |----------|------------|------------|-------------|---------| | 小型搜索:10K矢量为50-100米 | ✅ Excellent | Docker | Very Fast | Apache 2.0 | | 矢量 DB (HNSW): 1,0K 矢量为 1,5米 | ✅ (via Npgsql) | Postgres extension | Fast | PostgreSQL License | | 10 -50x更快! 10 -50x更快! | ✅ Good | Docker | Very Fast | BSD-3 | | 它的大小是: 百万矢量仍然只需要~10 -20米。 | ⚠️ Limited | Docker/K8s | Very Fast | Apache 2.0 | | 选择矢量数据库 | ❌ Python-first | Docker | Fast | Apache 2.0 |

对于我们的C#项目,我们需要:

良好的 C# 客户库Qdrant.Client)
易部署 (多克)
良好业绩
Free/ 开源
数据库 C# 支持部署性能许可证 = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = = =

解冻

pgvictor 变量
断断
米尔伏人

色谱我的选择:Qdrant优秀的 C # 客户(

简单嵌入部署

专为矢量搜索而建造(未粘贴)

docker run -p 6333:6333 -p 6334:6334 \
    -v $(pwd)/qdrant_storage:/qdrant/storage \
    qdrant/qdrant

特大文件文件:

6333积极发展
6334替代物:插件

**我们已经在使用 PostgreSQL 博客!**能把所有东西都保存在一个数据库里./qdrant_storage性能稍差但较简单的建筑

这个系列,我用

dotnet add package Qdrant.Client --version 1.7.0

解冻

因为它是有目的的,更容易理解这些概念。

using Qdrant.Client;
using Qdrant.Client.Grpc;

public class QdrantSetup
{
    private readonly QdrantClient _client;

    public QdrantSetup(string host = "localhost", int port = 6334)
    {
        _client = new QdrantClient(host, port);
    }

    public async Task CreateCollectionAsync(string collectionName, ulong vectorSize)
    {
        // Check if collection exists
        var collections = await _client.ListCollectionsAsync();
        if (collections.Any(c => c.Name == collectionName))
        {
            Console.WriteLine($"Collection '{collectionName}' already exists");
            return;
        }

        // Create collection
        await _client.CreateCollectionAsync(
            collectionName: collectionName,
            vectorsConfig: new VectorParams
            {
                Size = vectorSize,  // 768 for bge-base
                Distance = Distance.Cosine  // Cosine similarity
            }
        );

        Console.WriteLine($"Created collection '{collectionName}' with {vectorSize} dimensions");
    }
}

但我会让Pgvictor做个选择:

Size设置 Qdrant 设置
DistanceDoccker 部署
- Distance.Cosine港口港口
- Distance.Euclid- STEST API - STAP - STAST - STAP - STAP - STAST - STAP - STAP - STAST - STAST - STAST - STAP - STAST - STSTAP - STAP - STAP - STSTAST STAP
- Distance.Dot- GRPC API(越快,我们用这个)

储存储存

using Qdrant.Client.Grpc;
using System.Collections.Generic;

public class QdrantInserter
{
    private readonly QdrantClient _client;

    public QdrantInserter(QdrantClient client)
    {
        _client = client;
    }

    public async Task InsertBlogChunkAsync(
        string collectionName,
        ulong id,
        float[] embedding,
        string blogPostSlug,
        string chunkText,
        int chunkIndex)
    {
        var point = new PointStruct
        {
            Id = id,
            Vectors = embedding,
            Payload =
            {
                ["blog_post_slug"] = blogPostSlug,
                ["chunk_text"] = chunkText,
                ["chunk_index"] = chunkIndex,
                ["timestamp"] = DateTimeOffset.UtcNow.ToUnixTimeSeconds()
            }
        };

        await _client.UpsertAsync(collectionName, new[] { point });
    }

    public async Task InsertBatchAsync(
        string collectionName,
        List<(ulong id, float[] embedding, Dictionary<string, object> payload)> points)
    {
        var qdrantPoints = points.Select(p => new PointStruct
        {
            Id = p.id,
            Vectors = p.embedding,
            Payload = { p.payload }
        }).ToList();

        // Batch insert for efficiency
        await _client.UpsertAsync(collectionName, qdrantPoints);

        Console.WriteLine($"Inserted {points.Count} points");
    }
}

: 永久数据到:

主机
C# C# 客户端设置
创建收藏

一个收藏就像一个表格 - 它持有特定维度的矢量。:

关键参数
- 必须匹配您的嵌入模型( 768 用于 bge- base )

- 如何衡量相似性:

public class QdrantSearcher
{
    private readonly QdrantClient _client;

    public QdrantSearcher(QdrantClient client)
    {
        _client = client;
    }

    public async Task<List<SearchResult>> SearchAsync(
        string collectionName,
        float[] queryEmbedding,
        int topK = 10)
    {
        var searchResult = await _client.SearchAsync(
            collectionName: collectionName,
            vector: queryEmbedding,
            limit: (ulong)topK,
            scoreThreshold: 0.7f  // Only return if similarity > 0.7
        );

        return searchResult.Select(r => new SearchResult
        {
            Id = r.Id.Num,
            Score = r.Score,
            BlogPostSlug = r.Payload["blog_post_slug"].StringValue,
            ChunkText = r.Payload["chunk_text"].StringValue,
            ChunkIndex = (int)r.Payload["chunk_index"].IntegerValue
        }).ToList();
    }

    public async Task<List<SearchResult>> SearchWithFilterAsync(
        string collectionName,
        float[] queryEmbedding,
        string blogPostSlug,  // Only search within this post
        int topK = 5)
    {
        var filter = new Filter
        {
            Must =
            {
                new Condition
                {
                    Field = new FieldCondition
                    {
                        Key = "blog_post_slug",
                        Match = new Match { Keyword = blogPostSlug }
                    }
                }
            }
        };

        var searchResult = await _client.SearchAsync(
            collectionName: collectionName,
            vector: queryEmbedding,
            filter: filter,
            limit: (ulong)topK
        );

        return searchResult.Select(r => new SearchResult
        {
            Id = r.Id.Num,
            Score = r.Score,
            BlogPostSlug = r.Payload["blog_post_slug"].StringValue,
            ChunkText = r.Payload["chunk_text"].StringValue,
            ChunkIndex = (int)r.Payload["chunk_index"].IntegerValue
        }).ToList();
    }
}

public class SearchResult
{
    public ulong Id { get; set; }
    public float Score { get; set; }
    public string BlogPostSlug { get; set; }
    public string ChunkText { get; set; }
    public int ChunkIndex { get; set; }
}

- 共生相似性(最常见):

limit- 大陆距离
scoreThreshold- 点产品
filter插入矢量

有效载荷解释

using System;
using System.Threading.Tasks;

class Program
{
    static async Task Main(string[] args)
    {
        // Setup
        var embedder = new EmbeddingGenerator(
            "bge-base-en-onnx/model.onnx",
            "bge-base-en-onnx/tokenizer.json",
            useGpu: true
        );

        var client = new QdrantClient("localhost", 6334);
        var searcher = new QdrantSearcher(client);

        // User query
        string query = "How do I set up Docker with ASP.NET Core?";

        // Generate query embedding
        Console.WriteLine($"Searching for: {query}");
        var queryEmbedding = embedder.GenerateEmbedding(query);

        // Search
        var results = await searcher.SearchAsync(
            collectionName: "blog_embeddings",
            queryEmbedding: queryEmbedding,
            topK: 5
        );

        // Display results
        Console.WriteLine($"\nFound {results.Count} results:\n");

        foreach (var result in results)
        {
            Console.WriteLine($"Score: {result.Score:F4}");
            Console.WriteLine($"Post: {result.BlogPostSlug}");
            Console.WriteLine($"Chunk: {result.ChunkText.Substring(0, Math.Min(100, result.ChunkText.Length))}...");
            Console.WriteLine();
        }
    }
}

类似附于每个矢量的元数据:

Searching for: How do I set up Docker with ASP.NET Core?

Found 5 results:

Score: 0.8923
Post: dockercomposedevdeps
Chunk: In this post, I'll show you how to set up a development environment using Docker Compose. This is p...

Score: 0.8654
Post: dockercompose
Chunk: Docker Compose is a tool for defining and running multi-container Docker applications. With Compose...

Score: 0.8102
Post: addingentityframeworkforblogpostspt1
Chunk: You can set it up either as a windows service or using Docker as I presented in a previous post on...

Score: 0.7891
Post: imagesharpwithdocker
Chunk: When running ASP.NET Core applications in Docker containers, you may encounter issues with ImageSha...

Score: 0.7654
Post: selfhostingseq
Chunk: I use Docker Compose to run all my services. Here's the relevant part of my docker-compose.yml file...

能够存储任何东西: 邮戳标题、块文本、日期、分类

可搜索和过滤!

批次插入

比一比一快得多

public class BatchEmbeddingGenerator
{
    private readonly EmbeddingGenerator _embedder;

    public BatchEmbeddingGenerator(EmbeddingGenerator embedder)
    {
        _embedder = embedder;
    }

    public List<float[]> GenerateBatch(List<string> texts, int batchSize = 32)
    {
        var embeddings = new List<float[]>();

        for (int i = 0; i < texts.Count; i += batchSize)
        {
            var batch = texts.Skip(i).Take(batchSize).ToList();

            foreach (var text in batch)
            {
                embeddings.Add(_embedder.GenerateEmbedding(text));
            }

            Console.WriteLine($"Processed {Math.Min(i + batchSize, texts.Count)} / {texts.Count}");
        }

        return embeddings;
    }
}

Qdrant 高效率地处理100-1 000的批次

搜索矢量
搜索功能
- 返回最相似的上K

- 只有在相似性超过门槛值时才返回

通过元数据过滤(例如,仅搜索特定员额)

using System.Security.Cryptography;
using System.Text;

public class EmbeddingCache
{
    private readonly Dictionary<string, float[]> _cache = new();

    public float[] GetOrGenerate(string text, Func<string, float[]> generator)
    {
        string hash = ComputeHash(text);

        if (_cache.TryGetValue(hash, out var cached))
        {
            return cached;
        }

        var embedding = generator(text);
        _cache[hash] = embedding;

        return embedding;
    }

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

完整示例:搜索管道

产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出产出

完美! 完美!

CREATE EXTENSION vector;

它发现了有关Docker和ASP.NET核心的相关文章,

CREATE TABLE blog_embeddings (
    id SERIAL PRIMARY KEY,
    blog_post_slug VARCHAR(255),
    chunk_text TEXT,
    chunk_index INT,
    embedding VECTOR(768)  -- 768 dimensions
);

-- Create HNSW index for fast search
CREATE INDEX ON blog_embeddings USING hnsw (embedding vector_cosine_ops);

业绩优化

using Npgsql;
using Pgvector;

public async Task InsertEmbeddingAsync(
    string slug,
    string chunkText,
    int chunkIndex,
    float[] embedding)
{
    await using var conn = new NpgsqlConnection(connectionString);
    await conn.OpenAsync();

    await using var cmd = new NpgsqlCommand(
        "INSERT INTO blog_embeddings (blog_post_slug, chunk_text, chunk_index, embedding) VALUES ($1, $2, $3, $4)",
        conn
    )
    {
        Parameters =
        {
            new() { Value = slug },
            new() { Value = chunkText },
            new() { Value = chunkIndex },
            new() { Value = new Vector(embedding) }
        }
    };

    await cmd.ExecuteNonQueryAsync();
}

批量嵌入生成

public async Task<List<SearchResult>> SearchAsync(float[] queryEmbedding, int topK = 10)
{
    await using var conn = new NpgsqlConnection(connectionString);
    await conn.OpenAsync();

    await using var cmd = new NpgsqlCommand(
        @"SELECT blog_post_slug, chunk_text, chunk_index,
                 1 - (embedding <=> $1) as similarity
          FROM blog_embeddings
          ORDER BY embedding <=> $1
          LIMIT $2",
        conn
    )
    {
        Parameters =
        {
            new() { Value = new Vector(queryEmbedding) },
            new() { Value = topK }
        }
    };

    var results = new List<SearchResult>();

    await using var reader = await cmd.ExecuteReaderAsync();
    while (await reader.ReadAsync())
    {
        results.Add(new SearchResult
        {
            BlogPostSlug = reader.GetString(0),
            ChunkText = reader.GetString(1),
            ChunkIndex = reader.GetInt32(2),
            Score = reader.GetFloat(3)
        });
    }

    return results;
}

**<=>不要产生一个一个一个的嵌入。**批发他们! **1 - distance**为什么要批发?

GPU 利用率: 保持 GPU 忙碌

内存效率:再利用缓冲

✅ What embeddings are and why they enable semantic search
✅ How to choose and convert an embedding model to ONNX
✅ Generating embeddings in C# with ONNX Runtime
✅ Vector database concepts (HNSW, similarity search)
✅ Using Qdrant for vector storage and search
✅ Alternative: pgvector in PostgreSQL
✅ Performance optimization (batching, caching)

进展情况跟踪:用户反馈

缓缓的嵌套

不要为内容不变而再生嵌入!**pgvictor 替代品**如果您想将一切保留在 PostgreSQL :

安裝 pgvictor 扩展
创建表格
从C#插入
使用 pgvictor 搜索操作员
: 余弦距离( 较低更相似) 。
: 转换为相似得分(越高越好)

摘要摘要摘要

我们已经覆盖了:

解冻

第2部分:C#中的GPU设置和CUDA CUDA第三部分:了解嵌入和矢量数据库!