# Database vettoriali self-hosted con Qdrant: un'immersione profonda

<datetime class="hidden">2025-11-23T13:00</datetime>

<!-- category -- ASP.NET, Semantic Search, Vector Databases, Qdrant, RAG, AI-Article -->
# Introduzione

**In relazione alla serie RAG:** Questo articolo fornisce un'immersione profonda in Qdrant, il database vettoriale utilizzato in:

- [Parte 4: Implementazione di ONNX e Qdrant](/blog/semantic-search-with-onnx-and-qdrant) - Costruire la ricerca semantica
- [Parte 5: Ricerca ibrida e integrazione automatica](/blog/rag-hybrid-search-and-indexing) - Integrazione della produzione

[QdrantCity name (optional, probably does not need a translation)](https://qdrant.tech/) (pronunciato "quadrant") è un database vettoriale open-source costruito in Rust. Questo articolo copre i concetti fondamentali, il client C#, la messa a punto delle prestazioni e i modelli di produzione.

[TOC]

# Che cos'è Qdrant?

A [banca dati vettoriale](https://qdrant.tech/documentation/overview/) memorizza vettori ad alta dimensione (imbeddings) e consente una rapida ricerca di somiglianza. A differenza dei database tradizionali che trovano corrispondenze esatte, Qdrant trova *Simile semanticamente* oggetti.

```mermaid
flowchart LR
    A[Text: 'Docker deployment'] --> B[Embedding Model]
    B --> C["Vector: [0.12, -0.34, 0.56, ...]"]
    C --> D[Qdrant]
    E[Query: 'container setup'] --> F[Embedding Model]
    F --> G["Vector: [0.11, -0.32, 0.58, ...]"]
    G --> H[Similarity Search]
    D --> H
    H --> I[Similar Results]

    style B stroke:#6366f1,stroke-width:3px
    style D stroke:#ef4444,stroke-width:3px
    style F stroke:#6366f1,stroke-width:3px
    style H stroke:#10b981,stroke-width:2px
```

**Caratteristiche chiave di Qdrant:**

- [Indexing HNSW](https://qdrant.tech/documentation/concepts/indexing/) - Tempi di ricerca sublineari
- [Filtraggio](https://qdrant.tech/documentation/concepts/filtering/) - Combina la ricerca di similarità con i filtri dei metadati
- [API gRPC & REST](https://qdrant.tech/documentation/interfaces/) - Accesso ad alte prestazioni
- [Implementazione distribuita](https://qdrant.tech/documentation/guides/distributed_deployment/) - Scala orizzontalmente
- [Istantanee](https://qdrant.tech/documentation/concepts/snapshots/) - Backup e ripristino

# Concetti principali

## Collezioni

A [raccolta](https://qdrant.tech/documentation/concepts/collections/) è come una tabella - contiene vettori con una dimensionalità fissa e una metrica di distanza.

```mermaid
flowchart TB
    subgraph Collection["Collection: blog_posts"]
        A[Vector Size: 384]
        B[Distance: Cosine]
        C[HNSW Index]
    end

    subgraph Points
        D[Point 1: slug=docker-intro]
        E[Point 2: slug=kubernetes-basics]
        F[Point N...]
    end

    Collection --> Points

    style A stroke:#6366f1,stroke-width:2px
    style B stroke:#6366f1,stroke-width:2px
    style C stroke:#f59e0b,stroke-width:2px
    style D stroke:#10b981,stroke-width:2px
    style E stroke:#10b981,stroke-width:2px
```

```csharp
// Create collection - see https://qdrant.tech/documentation/concepts/collections/#create-a-collection
await client.CreateCollectionAsync(
    collectionName: "blog_posts",
    vectorsConfig: new VectorParams
    {
        Size = 384,              // Must match your embedding model
        Distance = Distance.Cosine  // Best for text embeddings
    }
);
```

**Metri di distanza** ([docs](https://qdrant.tech/documentation/concepts/collections/#distance-metrics)):

- **Coseno** - Misura l'angolo tra i vettori (meglio per il testo)
- **Punto** - Prodotto interno grezzo (per vettori prenormalizzati)
- **EuclidCity name (optional, probably does not need a translation)** - Distanza geometrica (per dati territoriali)

## Punti

A [punto](https://qdrant.tech/documentation/concepts/points/) è un singolo record contenente:

```mermaid
flowchart LR
    subgraph Point
        A[ID: uuid/int]
        B["Vector: float[384]"]
        C[Payload: JSON metadata]
    end

    style A stroke:#8b5cf6,stroke-width:2px
    style B stroke:#f59e0b,stroke-width:2px
    style C stroke:#10b981,stroke-width:2px
```

```csharp
// Upsert points - see https://qdrant.tech/documentation/concepts/points/#upload-points
var point = new PointStruct
{
    Id = new PointId { Uuid = Guid.NewGuid().ToString() },
    Vectors = embedding,  // float[384]
    Payload =
    {
        ["slug"] = "my-post",
        ["title"] = "Vector Databases",
        ["language"] = "en",
        ["categories"] = new[] { "AI", "Databases" },
        ["published"] = DateTimeOffset.UtcNow.ToUnixTimeSeconds()
    }
};

await client.UpsertAsync("blog_posts", points: new[] { point });
```

## Filtraggio

[Filtraggio](https://qdrant.tech/documentation/concepts/filtering/) esegui *prima* ricerca di somiglianza - estremamente efficiente.

```mermaid
flowchart TB
    A[Search Query] --> B{Apply Filters First}
    B --> C[Language = 'en']
    B --> D[Year >= 2024]
    C --> E[Filtered Subset]
    D --> E
    E --> F[Vector Similarity Search]
    F --> G[Ranked Results]

    style B stroke:#ec4899,stroke-width:3px
    style E stroke:#f59e0b,stroke-width:2px
    style F stroke:#6366f1,stroke-width:2px
    style G stroke:#10b981,stroke-width:2px
```

```csharp
// Filter conditions - see https://qdrant.tech/documentation/concepts/filtering/#filtering-conditions
var filter = new Filter
{
    Must =  // AND conditions
    {
        new Condition { Field = new FieldCondition
        {
            Key = "language",
            Match = new Match { Keyword = "en" }
        }},
        new Condition { Field = new FieldCondition
        {
            Key = "published",
            Range = new Range { Gte = 1704067200 }  // 2024-01-01
        }}
    },
    MustNot =  // Exclude conditions
    {
        new Condition { Field = new FieldCondition
        {
            Key = "slug",
            Match = new Match { Keyword = "draft-post" }
        }}
    }
};
```

**Tipo di filtro** ([docs](https://qdrant.tech/documentation/concepts/filtering/#match)):

- `Match.Keyword` - Corrispondenza stringa esatta
- `Match.Text` - Full-text match
- `Match.Any` - Corrisponde a qualsiasi array
- `Range` - Gamme numeriche (Gte, Lte, Gt, Lt)
- `GeoBoundingBox` / `GeoRadius` - Geofiltraggio

# Il client C#

Installare il funzionario [Qdrant.Client](https://www.nuget.org/packages/Qdrant.Client) pacchetto ([GitHubCity name (optional, probably does not need a translation)](https://github.com/qdrant/qdrant-dotnet)):

```bash
dotnet add package Qdrant.Client
```

## Configurazione connessione

```csharp
using Qdrant.Client;
using Qdrant.Client.Grpc;

// gRPC client (recommended) - see https://qdrant.tech/documentation/interfaces/#grpc-interface
var client = new QdrantClient(
    host: "localhost",
    port: 6334,  // gRPC port (6333 is REST)
    https: false
);

// With API key - see https://qdrant.tech/documentation/guides/security/
var secureClient = new QdrantClient(
    host: "your-qdrant.cloud",
    port: 6334,
    https: true,
    apiKey: "your-api-key"
);
```

> **Usare sempre gRPC** (porto 6334) per la produzione - 3-5x più veloce del REST.

## Windows HTTP/2 Fix

Su Windows, abilitare HTTP/2 non cifrato **prima** creazione del client:

```csharp
AppContext.SetSwitch("System.Net.Http.SocketsHttpHandler.Http2UnencryptedSupport", true);
```

## Operazioni chiave

### Cerca

```csharp
// Vector search - see https://qdrant.tech/documentation/concepts/search/
var results = await client.SearchAsync(
    collectionName: "blog_posts",
    vector: queryEmbedding,
    limit: 10,
    filter: filter,
    scoreThreshold: 0.5f,  // Minimum similarity
    searchParams: new SearchParams
    {
        HnswEf = 128,  // Search accuracy (higher = better recall)
        Exact = false  // Use approximate search
    },
    withPayload: true
);

foreach (var result in results)
{
    Console.WriteLine($"{result.Payload["title"].StringValue}: {result.Score}");
}
```

### Batch Upsert

```csharp
// Batch operations - see https://qdrant.tech/documentation/concepts/points/#batch-update
var points = documents.Select(doc => new PointStruct
{
    Id = new PointId { Uuid = doc.Id },
    Vectors = doc.Embedding,
    Payload = { ["slug"] = doc.Slug, ["title"] = doc.Title }
}).ToList();

await client.UpsertAsync(
    collectionName: "blog_posts",
    points: points,
    wait: true  // Wait for indexing
);
```

### Elimina

```csharp
// Delete by filter - see https://qdrant.tech/documentation/concepts/points/#delete-points
await client.DeleteAsync(
    collectionName: "blog_posts",
    filter: new Filter
    {
        Must = { new Condition { Field = new FieldCondition
        {
            Key = "slug",
            Match = new Match { Keyword = "old-post" }
        }}}
    }
);
```

# Tuning dell'indice HNSW

[HNSWCity name (optional, probably does not need a translation)](https://qdrant.tech/documentation/concepts/indexing/#vector-index) (Hierarchical Navigable Small World) è l'algoritmo indice di Qdrant.

```mermaid
flowchart TB
    subgraph "HNSW Graph Layers"
        L2[Layer 2 - Sparse]
        L1[Layer 1 - Medium]
        L0[Layer 0 - Dense]
    end

    Q[Query] --> L2
    L2 --> L1
    L1 --> L0
    L0 --> R[Nearest Neighbors]

    style L2 stroke:#8b5cf6,stroke-width:2px
    style L1 stroke:#6366f1,stroke-width:2px
    style L0 stroke:#3b82f6,stroke-width:2px
    style Q stroke:#10b981,stroke-width:2px
    style R stroke:#ef4444,stroke-width:2px
```

## Parametri dell'indice

```csharp
// HNSW config - see https://qdrant.tech/documentation/concepts/indexing/#hnsw-index
var hnswConfig = new HnswConfigDiff
{
    M = 16,              // Edges per node (16-32 recommended)
    EfConstruct = 100,   // Build-time accuracy (100-200)
    FullScanThreshold = 10000  // Brute force threshold
};

await client.UpdateCollectionAsync(
    collectionName: "blog_posts",
    hnswConfig: hnswConfig
);
```

**Precisione del tempo di ricerca:**

```csharp
var searchParams = new SearchParams
{
    HnswEf = 128  // Higher = better recall, slower (64-256)
};
```

**Linee guida per la sintonizzazione:**
| Caso d'uso | M | EfConstruct | HnswEf |
|----------|---|-------------|--------|
| Richiamo rapido e basso | 8 | 64 | 32 |
| Bilanciato | 16 | 100 | 128 |
| Richiamo alto | 32 | 200 | 256 |

# Indici di carico

Crea [indici di carico](https://qdrant.tech/documentation/concepts/indexing/#payload-index) per i campi filtrati frequentemente:

```csharp
// Keyword index - see https://qdrant.tech/documentation/concepts/indexing/#payload-index
await client.CreatePayloadIndexAsync(
    collectionName: "blog_posts",
    fieldName: "language",
    schemaType: PayloadSchemaType.Keyword
);

// Integer index for ranges
await client.CreatePayloadIndexAsync(
    collectionName: "blog_posts",
    fieldName: "published",
    schemaType: PayloadSchemaType.Integer
);
```

**Impatto:** 10-100x filtraggio più veloce su grandi collezioni.

# Quantizzazione

[Quantizzazione](https://qdrant.tech/documentation/guides/quantization/) riduce l'utilizzo della memoria:

```csharp
// Scalar quantization - see https://qdrant.tech/documentation/guides/quantization/#scalar-quantization
await client.UpdateCollectionAsync(
    collectionName: "blog_posts",
    quantizationConfig: new ScalarQuantization
    {
        Scalar = new ScalarQuantizationConfig
        {
            Type = ScalarType.Int8,  // float32 -> int8
            Quantile = 0.99f,
            AlwaysRam = true
        }
    }
);
```

**Trade-off:** 4x meno memoria, ~2% perdita di richiamo, 1.5x ricerca più veloce.

# Docker Deployment

```yaml
# docker-compose.yml - see https://qdrant.tech/documentation/guides/installation/
services:
  qdrant:
    image: qdrant/qdrant:v1.12.1  # Pin version!
    ports:
      - "6333:6333"  # REST
      - "6334:6334"  # gRPC
    volumes:
      - qdrant_data:/qdrant/storage
    environment:
      - QDRANT__SERVICE__GRPC_PORT=6334
      - QDRANT__SERVICE__HTTP_PORT=6333
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:6333/health"]
      interval: 30s
      timeout: 10s
      retries: 3

volumes:
  qdrant_data:
```

## Sicurezza

Abilita [Autenticazione chiave API](https://qdrant.tech/documentation/guides/security/):

```yaml
environment:
  - QDRANT__SERVICE__API_KEY=your-secret-key
```

# Monitoraggio

## MetricsCity name (optional, probably does not need a translation)

Qdrant espone [Prometheus metriche](https://qdrant.tech/documentation/guides/monitoring/) a `/metrics`:

```bash
curl http://localhost:6333/metrics
```

metriche chiave:

- `qdrant_collections_vector_count` - Totale vettori
- `qdrant_rest_responses_duration_seconds` - Interrogazione di latenza
- `qdrant_memory_usage_bytes` - Consumo di memoria

## Istantanee

Crea [backup](https://qdrant.tech/documentation/concepts/snapshots/):

```bash
# Create snapshot
curl -X POST http://localhost:6333/collections/blog_posts/snapshots

# List snapshots
curl http://localhost:6333/collections/blog_posts/snapshots

# Restore (copy snapshot to storage/collections/blog_posts/snapshots/)
```

# Common GotchasCity name (optional, probably does not need a translation)

## 1. Confusione del porto

- **6333** = API REST
- **6334** = API GRPC (usa questo!)

## 2. Errore di dimensione vettoriale

```
Error: expected dim: 384, got 768
```

Il modello e la collezione devono corrispondere:

- `all-MiniLM-L6-v2`: 384 dimensioni
- `nomic-embed-text`: 768 dimensioni
- OpenAICity name (optional, probably does not need a translation) `text-embedding-3-small`: 1536 dimensioni

## 3. Prima domanda lenta

HNSW carica pigro nella memoria. Riscaldamento dopo l'avvio:

```csharp
await client.SearchAsync("blog_posts", new float[384], limit: 1);
```

## 4. Filtraggio dell'array

Uso `Match.Any` per i campi array:

```csharp
new Match { Any = new RepeatedStrings { Strings = { "AI", "ML" } } }
```

# Risorse

## Documentazione ufficiale Qdrant

- [Panoramica](https://qdrant.tech/documentation/overview/) - Iniziare.
- [Concetti](https://qdrant.tech/documentation/concepts/) - Concetti fondamentali
- [Collezioni](https://qdrant.tech/documentation/concepts/collections/) - Creazione e gestione di collezioni
- [Punti](https://qdrant.tech/documentation/concepts/points/) - Lavorare con i vettori
- [Cerca](https://qdrant.tech/documentation/concepts/search/) - Operazioni di query
- [Filtraggio](https://qdrant.tech/documentation/concepts/filtering/) - Condizioni del filtro
- [Indicizzazione](https://qdrant.tech/documentation/concepts/indexing/) - HNSW e indici di carico
- [Quantizzazione](https://qdrant.tech/documentation/guides/quantization/) - Ottimizzazione della memoria
- [Sicurezza](https://qdrant.tech/documentation/guides/security/) - Autenticazione
- [Monitoraggio](https://qdrant.tech/documentation/guides/monitoring/) - Metrics e telemetry
- [Istantanee](https://qdrant.tech/documentation/concepts/snapshots/) - Backup e ripristino

## Librerie dei clienti

- [Qdrant .NET Client](https://github.com/qdrant/qdrant-dotnet) - Official C# SDK
- [Pacchetto NuGet](https://www.nuget.org/packages/Qdrant.Client) - Ultimo rilascio

## Articoli correlati

- [Parte 4: Implementazione di ONNX e Qdrant](/blog/semantic-search-with-onnx-and-qdrant)
- [Parte 5: Ricerca ibrida e integrazione automatica](/blog/rag-hybrid-search-and-indexing)
- [Panoramica della serie RAG](/blog/rag-primer)

## Codice sorgente

Tutti i codici disponibili al seguente indirizzo: [github.com/scottgal/mostlylucidweb](https://github.com/scottgal/mostlylucidweb)

- `Mostlylucid.SemanticSearch/Services/QdrantVectorStoreService.cs` - Integrazione Qdrant