This is a viewer only at the moment see the article on how this works.
To update the preview hit Ctrl-Alt-R (or ⌘-Alt-R on Mac) or Enter to refresh. The Save icon lets you save the markdown file to disk
This is a preview from the server running through my markdig pipeline
Tuesday, 25 November 2025
Parte de la serie RAG: Esta es la parte 4a - aplicación básica:
Las partes 1 a 3 explican ¿Por qué? trabajos de búsqueda semántica. Este artículo muestra ¿Cómo? para construir los cimientos - un de costo cero, aplicación fácil de CPU utilizando ONNX Runtime y Qdrant. Parte 4b cubre la búsqueda de interfaz de usuario y la implementación de búsqueda híbrida, y Parte 5 cubre la producción de auto-indexación.
El desafío: La mayoría de las soluciones de búsqueda semánticas requieren costosas infraestructuras GPU o costosos servicios gestionados. ¿Qué pasa si eres un desarrollador independiente que ejecuta un blog en un VPS modesto?
La solución: Un sistema de búsqueda semántica totalmente funcional que funciona completamente en la CPU, utilizando herramientas de código abierto gratuitas. Esta es la configuración exacta que se ejecuta en este blog - cero costo adicional más allá del alojamiento existente.
Estos conceptos se tratan en profundidad en el Serie RAG, pero esto es lo que necesitas saber para esta implementación:
Los empotrados son vectores (arrays de números) que capturan el significado significados similares producen vectores similares - que es 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
Perspicacia clave: Textos con significados similares tendrán vectores similares (embeddings). Así es como podemos encontrar contenido "relacionado" - estamos midiendo literalmente la distancia entre significados!
Similitud de coseno mide el ángulo entre dos vectores - si apuntan en direcciones similares, son semánticamente similares:
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 fórmula: similarity = (A · B) / (||A|| × ||B||) - pero ya que L2-normalizamos nuestros vectores, se simplifica a sólo el producto punto!
ONNX (Intercambio de redes neuronales abiertas) es un formato estándar abierto para los modelos de aprendizaje automático que les permite funcionar eficientemente en diferentes plataformas. Piense en ello como un traductor universal para los modelos de IA. ONNX Runtime es el motor de inferencia de alto rendimiento de Microsoft que ejecuta estos modelos.
Por qué ONNX para nuestro caso de 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
Qdrant es una base de datos de vectores de código abierto - básicamente una base de datos optimizada para almacenar y buscar estos vectores de integración. Para una inmersión profunda en los conceptos de Qdrant, configuración e integración C#, vea Bases de datos Vectores Auto-Hosted con Qdrant. Mientras tú podría store vectors in PostgreSQL, Qdrant está diseñado especialmente para esto y ofrece:
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
Así es como nuestro sistema de búsqueda semántica encaja:
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
El flujo en inglés sencillo:
Hemos creado una estructura limpia y modular:
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
Primero, crear la nueva biblioteca de clases:
dotnet new classlib -n Mostlylucid.SemanticSearch -f net9.0
dotnet sln add Mostlylucid.SemanticSearch
Añadir los paquetes necesarios de NuGet:
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
Configuremos nuestra clase de configuración. IConfigSection patrón que se utiliza a lo largo de la mayoría de lúcido:
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;
}
¿Por qué las claves de API separadas? ¡Seguridad! Su clave de lectura se puede utilizar en los endpoints de búsqueda orientados al público, mientras que su clave de escritura permanece en el lado del servidor únicamente para operaciones de administración.
Añadir esto a su 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
}
}
Aquí es donde ocurre la magia. Estamos usando el modelo all-MiniLM-L6-v2, que está diseñado específicamente para tareas de similitud semántica y se ejecuta de manera eficiente en la CPU.
¿Por qué este modelo?
Aquí está la implementación 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);
}
}
Puntos clave para los devs junior:
Ahora vamos a implementar el almacenamiento vectorial y la búsqueda:
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.
}
Lo que está pasando aquí:
Este servicio de alto nivel lo une todo:
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);
}
}
Registrar todo en el contenedor 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>();
}
}
En tu 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();
}
Crear un archivo docker-compose separado para los servicios de búsqueda semántica:
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
Empieza con:
docker-compose -f semantic-search-docker-compose.yml up -d
Estamos usando el all-MiniLM-L6-v2 modelo de Hugging Face Transformadores de sentencias biblioteca. Este modelo está específicamente capacitado en tareas de similitud semántica y produce 384 incrustaciones dimensionales.
El servicio descarga automáticamente el modelo de Hugging Face en la primera ejecución si no existe:
// 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...
}
Esto es particularmente útil cuando se implementa con Docker - puede mapear un volumen para el directorio de modelos:
volumes:
- ./mlmodels:/app/mlmodels # Model persists across container restarts
Alternativamente, se puede descargar manualmente:
chmod +x Mostlylucid.SemanticSearch/download-models.sh
./Mostlylucid.SemanticSearch/download-models.sh
O directamente de 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
Esta descarga:
all-MiniLM-L6-v2.onnx (~90MB) - El Modelo de incrustación exportado por ONNXvocab.txt (~230KB) - El Vocabulario de WordPiece tokenizerUtilizamos caché de salida ASP.NET Core:
[OutputCache(Duration = 7200, VaryByRouteValueNames = new[] {"slug", "language"})]
Esta cachea puestos relacionados durante 2 horas, reduciendo significativamente la carga.
En este punto usted tiene una base de búsqueda semántica completa, que funciona:
Esta es la configuración exacta que se ejecuta en este blog - Cero GPU, cero costo adicional.
In Parte 4b: Búsqueda Semántica en Acción, cubrimos:
Continuar a Parte 4b para la búsqueda de la interfaz de usuario y la implementación de búsqueda híbrida.
Entonces Parte 5: Búsqueda híbrida y auto-indexación cubre los patrones de integración de la producción.
Todo el código disponible en: github.com/scottgal/mostlylucidweb
Mostlylucid.SemanticSearch/ - Biblioteca de búsqueda semántica básica
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.