Parte della serie RAG: Questa è la parte 4a - attuazione fondamentale:
Le parti 1-3 spiegano perché La ricerca semantica funziona. Questo articolo mostra come per costruire la fondazione - un zero-cost, CPU-friendly implementazione usando ONNX Runtime e Qdrant. Parte 4b copre l'implementazione dell'interfaccia utente e della ricerca ibrida, e Parte 5 copre l'indicizzazione automatica della produzione.
La sfida: La maggior parte delle soluzioni di ricerca semantiche richiedono costose infrastrutture GPU o costosi servizi gestiti. E se sei uno sviluppatore indie che esegue un blog su un VPS modesto?
La soluzione: Un sistema di ricerca semantico completamente funzionale che viene eseguito interamente sulla CPU, utilizzando strumenti open-source gratuiti. Questa è l'esatta configurazione in esecuzione su questo blog - zero costi aggiuntivi oltre l'hosting esistente.
Questi concetti sono trattati in modo approfondito nel Serie RAG, ma ecco cosa dovete sapere per questa implementazione:
I montaggi sono vettori (argomenti di numeri) che catturano il significato di testo. Significati simili producono vettori simili - questa è la magia.
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
Intuizione chiave: Testi con significati simili avranno vettori simili (embeddings). Questo è il modo in cui possiamo trovare contenuti "relativi" - stiamo letteralmente misurando la distanza tra i significati!
Similità del coseno misura l'angolo tra due vettori - se puntano in direzioni simili, sono semanticamente simili:
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
La formula: similarity = (A · B) / (||A|| × ||B||) - ma siccome noi L2-normalizzare i nostri vettori, si semplifica solo al prodotto punto!
ONNX (Open Neural Network Exchange) è un formato standard aperto per i modelli di apprendimento automatico che consente loro di funzionare in modo efficiente attraverso diverse piattaforme. Pensateci come un traduttore universale per i modelli AI. ONNX Runtime è il motore di inferenza ad alte prestazioni di Microsoft che esegue questi modelli.
Perché ONNX per il nostro caso d'uso:
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
QdrantCity name (optional, probably does not need a translation) è un database vettoriale open-source - fondamentalmente un database ottimizzato per la memorizzazione e la ricerca di questi vettori incorporanti. Per un'immersione profonda nei concetti, nella configurazione e nell'integrazione di Qdrant, vedere Database vettoriali self-hosted con Qdrant. mentre tu potrebbe vettori di store in PostgreSQL, Qdrant è appositamente costruito per questo e offre:
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
Ecco come si inserisce il nostro sistema di ricerca semantica:
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
Il flusso in inglese semplice:
Abbiamo creato una struttura modulare e pulita:
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
In primo luogo, creare la nuova libreria di classe:
dotnet new classlib -n Mostlylucid.SemanticSearch -f net9.0
dotnet sln add Mostlylucid.SemanticSearch
Aggiungere i pacchetti NuGet necessari:
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
Organizziamo la nostra classe di configurazione. IConfigSection modello che viene utilizzato in tutta la maggior parte dei Lucidi:
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;
}
Perché separare le chiavi API? Sicurezza! La tua chiave di lettura può essere utilizzata negli endpoint di ricerca rivolti al pubblico, mentre la tua chiave di scrittura rimane server-side solo per le operazioni di amministrazione.
Aggiungi questo al tuo 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
}
}
Qui è dove avviene la magia. Stiamo usando il modello all-MiniLM-L6-v2, che è specificamente progettato per attività di somiglianza semantica e funziona in modo efficiente sulla CPU.
Perché questo modello?
Ecco l'implementazione completa:
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);
}
}
Punti chiave per gli sviluppatori junior:
Ora implementiamo lo storage vettoriale e la ricerca:
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.
}
Cosa sta succedendo qui:
Questo servizio di alto livello unisce tutto:
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);
}
}
Registrare tutto nel contenitore DI:
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>();
}
}
Nella tua 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();
}
Crea un file docker-compose separato per i servizi di ricerca semantica:
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
Inizia con:
docker-compose -f semantic-search-docker-compose.yml up -d
Stiamo usando il all-MiniLM-L6-v2 modello da Hugging Face's Trasformatori di sentenza biblioteca. Questo modello è specificamente addestrato su compiti di somiglianza semantica e produce 384-inserzioni dimensionali.
Il servizio scarica automaticamente il modello da Hugging Face al primo avvio se non esiste:
// 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...
}
Questo è particolarmente utile quando si utilizza Docker: è possibile mappare un volume per la directory dei modelli:
volumes:
- ./mlmodels:/app/mlmodels # Model persists across container restarts
In alternativa, è possibile scaricare manualmente:
chmod +x Mostlylucid.SemanticSearch/download-models.sh
./Mostlylucid.SemanticSearch/download-models.sh
O direttamente da 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
Questi downloads:
all-MiniLM-L6-v2.onnx (~90MB) Modello di imbottitura ONNX-exportvocab.txt (~230KB) Lessico tokenizer di WordPieceUtilizziamo ASP.NET Core output cacheing:
[OutputCache(Duration = 7200, VaryByRouteValueNames = new[] {"slug", "language"})]
Questo cache relativi posti per 2 ore, riducendo significativamente il carico.
A questo punto hai una fondazione di ricerca semantica completa e funzionante:
Questo è il setup esatto in esecuzione su questo blog - GPU zero, costo aggiuntivo zero.
Dentro Parte 4b: Ricerca semantica in azione, copriamo:
Continua a Parte 4b per l'interfaccia utente di ricerca e l'implementazione di ricerca ibrida.
Poi Parte 5: Ricerca ibrida e integrazione automatica riguarda i modelli di integrazione della produzione.
Tutti i codici disponibili al seguente indirizzo: github.com/scottgal/mostlylucidweb
Mostlylucid.SemanticSearch/ - Core libreria di ricerca semantica
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.