Deel van de RAG-serie: Dit is deel 5 - productie-integratiepatronen:
In Deel 4 bis, bouwden we de stichting: ONNX inbeddingen en Qdrant opslag. Deel 4b, we hebben de zoekopdracht UI en hybride zoekimplementatie. Nu maken we het productie-klaar met automatische indexering (nul-touch content updates) via FileSystemWatcher.
Semantische zoekopdracht is krachtig maar traditionele full-text zoekopdracht blinkt nog steeds uit in exacte zinnen en technische termen. De oplossing? Gebruik beide.
Waarom Hybrid? Verschillende benaderingen hebben verschillende sterke punten:
We gebruiken Wederzijdse fusie van rangen om resultaten van meerdere zoekbronnen te combineren:
flowchart TB
A[User Query: 'docker containers'] --> B[PostgreSQL Full-Text Search]
A --> C[Semantic Vector Search]
B --> D["Results:<br/>1. 'Docker Basics' (rank 1)<br/>2. 'Containerizing Apps' (rank 2)<br/>3. 'Docker Compose' (rank 3)"]
C --> E["Results:<br/>1. 'Containerizing Apps' (rank 1)<br/>2. 'Kubernetes Guide' (rank 2)<br/>3. 'Docker Basics' (rank 3)"]
D --> F[RRF Algorithm]
E --> F
F --> G["Combined Results:<br/>1. 'Containerizing Apps'<br/> (1/61 + 1/62 = 0.0328)<br/>2. 'Docker Basics'<br/> (1/61 + 1/63 = 0.0322)<br/>3. 'Docker Compose'<br/> (1/63 = 0.0159)"]
style A stroke:#10b981,stroke-width:2px
style B stroke:#3b82f6,stroke-width:2px
style C stroke:#6366f1,stroke-width:2px
style D stroke:#3b82f6,stroke-width:2px
style E stroke:#6366f1,stroke-width:2px
style F stroke:#ec4899,stroke-width:4px
style G stroke:#8b5cf6,stroke-width:2px
De RRF-formule: score = Σ(1 / (k + rank))
k = 60 (constant om te voorkomen dat vroege rangen domineren)rank = positie in de resultaten van die zoekmethodeWaarom RRF werkt:
public class HybridSearchService : IHybridSearchService
{
private readonly ISemanticSearchService _semanticSearchService;
private const int RrfConstant = 60;
public async Task<List<SearchResult>> SearchAsync(
string query,
string language = "en",
int limit = 10,
CancellationToken cancellationToken = default)
{
// Execute both searches in parallel
var semanticResults = await _semanticSearchService.SearchAsync(
query, limit * 2, cancellationToken);
// Filter by language and apply RRF
var filteredResults = semanticResults
.Where(r => r.Language == language)
.ToList();
return ApplyReciprocalRankFusion(filteredResults)
.Take(limit)
.ToList();
}
private List<SearchResult> ApplyReciprocalRankFusion(List<SearchResult> results)
{
var rrfScores = new Dictionary<string, RrfScore>();
for (int i = 0; i < results.Count; i++)
{
var result = results[i];
var key = $"{result.Slug}_{result.Language}";
if (!rrfScores.ContainsKey(key))
rrfScores[key] = new RrfScore { Result = result };
// RRF formula: 1 / (k + rank)
rrfScores[key].Score += 1.0 / (RrfConstant + i + 1);
}
return rrfScores.Values
.OrderByDescending(x => x.Score)
.Select(x => x.Result)
.ToList();
}
}
Opmerking: Dit toont semantische zoekopdracht alleen. Voer in productie PostgreSQL full-text search parallel uit en neem deze resultaten in de RRF berekening op.
Als je PostgreSQL full-text search al hebt geïmplementeerd (zoals hier behandeld), het toevoegen van semantische zoekopdracht is eenvoudig:
// Program.cs
services.AddSemanticSearch(configuration);
services.AddSingleton<IHybridSearchService, HybridSearchService>();
[HttpGet("search/hybrid")]
public async Task<IActionResult> HybridSearch(string query, string language = "en")
{
var results = await _hybridSearchService.SearchAsync(query, language);
return PartialView("_SearchResults", results);
}
De meest krachtige eigenschap: automatische indexering. Sla een blogpost op, het is direct doorzoekbaar - geen handmatige interventie.
flowchart TB
A[Save Markdown File] --> B[FileSystemWatcher Detects Change]
B --> C{File in Main Directory?}
C -->|Yes| D[Save to Database]
C -->|No| E[Save to Database Only]
D --> F[Create BlogPostDocument]
F --> G[Generate Embedding via ONNX]
G --> H[Store in Qdrant]
H --> I[Post Searchable Immediately]
style A stroke:#10b981,stroke-width:2px
style B stroke:#f59e0b,stroke-width:2px
style C stroke:#ec4899,stroke-width:3px
style D stroke:#3b82f6,stroke-width:2px
style E stroke:#6b7280,stroke-width:2px
style F stroke:#8b5cf6,stroke-width:2px
style G stroke:#6366f1,stroke-width:3px
style H stroke:#ef4444,stroke-width:2px
style I stroke:#10b981,stroke-width:2px
Belangrijkste ontwerpbeschikking: Alleen indexbestanden in de hoofdmap markdown, niet subdirectories (translated/, drafts/, comments/Dit houdt de zoekindex schoon.
De blog heeft al een MarkdownDirectoryWatcherServiceWe breiden het uit om semantische indexering te activeren:
// In MarkdownDirectoryWatcherService.cs
private async Task OnChangedAsync(WaitForChangedResult e)
{
if (e.Name == null) return;
await retryPolicy.ExecuteAsync(async () =>
{
var savedModel = await blogService.SavePost(slug, language, markdown);
// Index ONLY if file is in main directory (no path separators in name)
if (!e.Name.Contains(Path.DirectorySeparatorChar) &&
!e.Name.Contains(Path.AltDirectorySeparatorChar))
{
await IndexPostForSemanticSearchAsync(scope, savedModel, language);
}
});
}
private async Task IndexPostForSemanticSearchAsync(
IServiceScope scope,
BlogPostDto post,
string language)
{
var semanticSearchService = scope.ServiceProvider.GetService<ISemanticSearchService>();
if (semanticSearchService == null) return; // Not configured
var document = new BlogPostDocument
{
Id = $"{post.Slug}_{language}",
Slug = post.Slug,
Title = post.Title,
Content = post.PlainTextContent,
Language = language,
Categories = post.Categories?.ToList() ?? new List<string>(),
PublishedDate = post.PublishedDate
};
await semanticSearchService.IndexPostAsync(document);
_logger.LogInformation("Indexed {Slug} ({Language}) in semantic search", post.Slug, language);
}
Als een bericht wordt verwijderd, verwijder het dan uit de semantische index:
private async Task OnDeletedAsync(WaitForChangedResult e)
{
await blogService.Delete(slug, language);
// Delete from semantic search ONLY if file was in main directory
if (!e.Name.Contains(Path.DirectorySeparatorChar) &&
!e.Name.Contains(Path.AltDirectorySeparatorChar))
{
var semanticSearchService = scope.ServiceProvider.GetService<ISemanticSearchService>();
await semanticSearchService?.DeletePostAsync(slug, language);
}
}
Bij het opstarten, een background service indexeert bestaande berichten nog niet in Qdrant:
flowchart TB
A[Application Starts] --> B[Wait 10 seconds]
B --> C[Initialize Semantic Search]
C --> D{Model Exists?}
D -->|No| E[Download from Hugging Face]
D -->|Yes| F[Load ONNX Model]
E --> F
F --> G[Scan Main Markdown Directory]
G --> H{For Each .md File}
H --> I[Compute Content Hash]
I --> J{Hash Changed?}
J -->|Yes| K[Generate Embedding]
J -->|No| L[Skip - Already Indexed]
K --> M[Store in Qdrant]
M --> H
L --> H
H -->|Done| N[Indexing Complete]
style A stroke:#10b981,stroke-width:2px
style C stroke:#6366f1,stroke-width:2px
style E stroke:#f59e0b,stroke-width:2px
style F stroke:#6366f1,stroke-width:3px
style G stroke:#8b5cf6,stroke-width:2px
style J stroke:#ec4899,stroke-width:3px
style K stroke:#6366f1,stroke-width:2px
style M stroke:#ef4444,stroke-width:2px
style N stroke:#10b981,stroke-width:2px
public class SemanticIndexingBackgroundService : BackgroundService
{
protected override async Task ExecuteAsync(CancellationToken stoppingToken)
{
// Wait for app to be ready
await Task.Delay(TimeSpan.FromSeconds(10), stoppingToken);
// Initialize (downloads model if needed)
await _semanticSearchService.InitializeAsync(stoppingToken);
// Get all posts from main directory only
var markdownFiles = Directory.GetFiles(
_markdownConfig.MarkdownPath,
"*.md",
SearchOption.TopDirectoryOnly); // NOT subdirectories
foreach (var file in markdownFiles)
{
var needsIndexing = await _semanticSearchService.NeedsReindexingAsync(
slug, language, contentHash, stoppingToken);
if (needsIndexing)
await _semanticSearchService.IndexPostAsync(document, stoppingToken);
}
}
}
Dit garandeert:
In de delen 4a, 4b en 5 hebben we nu:
Toekomstverbeteringen:
Dit completeert de praktische implementatie van RAG-stijl semantisch zoeken. Deel 4 bis (stichting) en Deel 4b (search UI), je hebt alles wat nodig is om intelligente zoekopdracht toe te voegen aan uw .NET applicatie - volledig draait op CPU, tegen nul extra kosten.
Alle code is beschikbaar op: github.com/scottgal/meestallucidweb
Mostlylucid.SemanticSearch/ - Semantische zoekbibliotheekMostlylucid/Blog/WatcherService/ - Filewatcher met semantische indexering
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.