Deel van de RAG-serie: Dit is deel 4a - kernimplementatie:
Delen 1-3 verklaren waarom semantische zoekopdrachten. Dit artikel toont hoe om de stichting te bouwen - a zero-cost, CPU-vriendelijke implementatie gebruik van ONNX Runtime en Qdrant. Deel 4b de search-UI en hybride zoekimplementatie omvat, en Deel 5 omvat de auto-indexering van de productie.
De uitdaging: De meeste semantische zoekoplossingen vereisen dure GPU-infrastructuur of dure beheerde diensten. Wat als je een indie-ontwikkelaar bent die een blog draait op een bescheiden VPS?
De oplossing: Een volledig functioneel semantisch zoeksysteem dat volledig draait op CPU, met behulp van gratis open-source tools. Dit is de exacte setup die draait op deze blog - nul extra kosten voorbij bestaande hosting.
Deze begrippen worden uitvoerig behandeld in de RAG-reeks, maar dit is wat je moet weten voor deze implementatie:
Inbeddingen zijn vectoren (arrays van getallen) die de Betekenis Vergelijkbare betekenissen produceren vergelijkbare vectoren - dat is de magie.
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
Belangrijkste inzicht: Teksten met vergelijkbare betekenissen zullen vergelijkbare vectoren hebben (inbeddingen). Zo kunnen we "gerelateerde" inhoud vinden - we meten letterlijk de afstand tussen betekenissen!
Cosinus-vergelijkbaarheid meet de hoek tussen twee vectoren - als ze in vergelijkbare richtingen wijzen, zijn ze semantisch vergelijkbaar:
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
De formule: similarity = (A · B) / (||A|| × ||B||) - maar omdat we L2-normaliseren onze vectoren, het vereenvoudigt naar alleen de punt product!
ONNX (Open Neural Network Exchange) is een open standaardformaat voor machine learning modellen die hen in staat stelt om efficiënt te lopen over verschillende platformen. Denk aan het als een universele vertaler voor AI modellen. ONNX-runtime is Microsoft's high-performance gevolgtrekking motor die deze modellen uitvoert.
Waarom ONNX voor onze use case:
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
Qdrant is een open-source vector database - in principe een database geoptimaliseerd voor het opslaan en zoeken van deze inbedden vectoren. Voor een diepe duik in Qdrant's concepten, configuratie, en C# integratie, zie Self-Hosted Vector Databanken met Qdrant- Terwijl jij... kan Store vectoren in PostgreSQL, Qdrant is speciaal hiervoor gebouwd en biedt:
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
Zo past ons semantische zoeksysteem in elkaar:
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
De stroom in het gewone Engels:
We hebben een schone, modulaire structuur gecreëerd:
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
Maak eerst de nieuwe klassebibliotheek:
dotnet new classlib -n Mostlylucid.SemanticSearch -f net9.0
dotnet sln add Mostlylucid.SemanticSearch
Voeg de nodige NuGet pakketten toe:
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
Laten we onze configuratieklas opzetten. IConfigSection patroon dat wordt gebruikt in de meeste lucid:
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;
}
Waarom API-sleutels scheiden? Beveiliging! Uw leessleutel kan worden gebruikt in publieke zoekeindpunten, terwijl uw schrijfsleutel server-side blijft voor admin operaties.
Voeg dit toe aan uw 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
}
}
Dit is waar de magie gebeurt. We gebruiken het all-MiniLM-L6-v2 model, dat speciaal is ontworpen voor semantische gelijkenis taken en efficiënt draait op CPU.
Waarom dit model?
Hier is de volledige implementatie:
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);
}
}
Belangrijkste punten voor junior devs:
Laten we nu de vectoropslag implementeren en zoeken:
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.
}
Wat gebeurt hier?
Deze dienst op hoog niveau verbindt alles:
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);
}
}
Registreer alles in de DI container:
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>();
}
}
In uw 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();
}
Maak een apart docker-compose bestand aan voor semantische zoekdiensten:
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
Begin met:
docker-compose -f semantic-search-docker-compose.yml up -d
We gebruiken de all-MiniLM-L6-v2 model van Hugging Face's Zintransformatoren bibliotheek. Dit model is speciaal getraind op semantische gelijkenis taken en produceert 384-dimensionale inbeddingen.
De service downloadt automatisch het model van Hugging Face op eerste run als het niet bestaat:
// 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...
}
Dit is vooral handig bij het implementeren met Docker - u kunt een volume in kaart brengen voor de map modellen:
volumes:
- ./mlmodels:/app/mlmodels # Model persists across container restarts
Als alternatief kunt u handmatig downloaden:
chmod +x Mostlylucid.SemanticSearch/download-models.sh
./Mostlylucid.SemanticSearch/download-models.sh
Of rechtstreeks vanuit Hugging 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
Deze downloads:
all-MiniLM-L6-v2.onnx (~90MB) ONNX-uitgevoerd inbeddingsmodelvocab.txt (~230KB) - De Woordenschat van WordPiece tokenizerWe gebruiken ASP.NET Core output caching:
[OutputCache(Duration = 7200, VaryByRouteValueNames = new[] {"slug", "language"})]
Deze caches gerelateerde posten gedurende 2 uur, aanzienlijk verminderen belasting.
Op dit moment heb je een complete, werkende semantische zoekstichting:
Dit is de exacte setup die draait op deze blog - nul GPU, nul extra kosten.
In Deel 4b: Semantisch zoeken in actie, we behandelen:
Doorgaan naar Deel 4b voor de zoekopdracht UI en hybride zoekimplementatie.
Daarna Deel 5: Hybrid Search & Auto-Indexing omvat productie-integratiepatronen.
Alle code beschikbaar op: github.com/scottgal/meestallucidweb
Mostlylucid.SemanticSearch/ - Semantische zoekbibliotheek
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.