WAARSCHUWING: Deze zijn ontwerp-Posts die 'onthuld'.
Het is waarschijnlijk veel van wat hieronder zal niet werken; IK genereren deze als how-to voor MIJ en dan doen alle stappen en krijg de sample app werken...Je bent stiekem en ze gezien! ze zullen waarschijnlijk klaar zijn medio december.
## Inleiding
Welkom bij deel 3Deel 2), en we begrijpen de architectuur (Deel 1****Nu is het tijd om in de magie te duiken die semantisch zoeken mogelijk maakt:inbeddingen.
en
vectordatabases
Dezelfde stem, hetzelfde pragmatisme, gewoon snellere vingers.
We zullen begrijpen hoe we tekst als getallen kunnen representeren op een manier die betekenis vangt, niet alleen trefwoorden.
graph TD
subgraph "2D Embedding Space (simplified)"
A[cat: 0.8, 0.2]
B[kitten: 0.7, 0.3]
C[dog: 0.6, 0.1]
D[puppy: 0.5, 0.2]
E[car: -0.5, 0.8]
F[vehicle: -0.6, 0.7]
G[database: 0.1, -0.7]
H[SQL: 0.2, -0.8]
end
class A,B cats
class C,D dogs
class E,F vehicles
class G,H tech
classDef cats stroke:#333
classDef dogs stroke:#333
classDef vehicles stroke:#333
classDef tech stroke:#333
Het is het verschil tussen het vinden van berichten die het woord "docker" bevatten vs het vinden van berichten die semantisch over containerization concepten.
**Soortgelijke concepten clusteren samen:**Huisdieren (rood/groen) zijn dicht bij elkaar
Technische termen (geel) cluster
graph LR
A[Text: 'Docker container'] --> B[Embedding Model]
B --> C[Vector: 384 floats]
D[Text: 'containerization'] --> B
B --> E[Vector: 384 floats]
C -.Similar.-> E
F[Text: 'chocolate cake'] --> B
B --> G[Vector: 384 floats]
C -.Very Different.-> G
class B model
class C,E similar
class G different
classDef model stroke:#333,stroke-width:4px
classDef similar stroke:#333
classDef different stroke:#333
Hoe het werkt**Een inbedding model is een neuraal netwerk getraind om tekst in kaart te brengen naar vectoren die:**Soortgelijke betekenissen → vectoren sluiten
public static float CosineSimilarity(float[] vectorA, float[] vectorB)
{
if (vectorA.Length != vectorB.Length)
throw new ArgumentException("Vectors must have same length");
// Dot product: sum of element-wise multiplication
float dotProduct = 0;
for (int i = 0; i < vectorA.Length; i++)
{
dotProduct += vectorA[i] * vectorB[i];
}
// Magnitude of each vector: sqrt(sum of squares)
float magnitudeA = 0;
float magnitudeB = 0;
for (int i = 0; i < vectorA.Length; i++)
{
magnitudeA += vectorA[i] * vectorA[i];
magnitudeB += vectorB[i] * vectorB[i];
}
magnitudeA = MathF.Sqrt(magnitudeA);
magnitudeB = MathF.Sqrt(magnitudeB);
// Cosine similarity: dot product / (magnitude_a * magnitude_b)
return dotProduct / (magnitudeA * magnitudeB);
}
Verschillende betekenissen → verre vectoren:
1.0Gelijksoortigheid meten0.0We gebruiken-1.0Cosinus-vergelijkbaarheidom te meten hoe dicht twee vectoren zijn::
var dockerEmbed = new float[] { 0.5f, 0.3f, -0.2f, 0.8f }; // "Docker container"
var containerEmbed = new float[] { 0.45f, 0.35f, -0.18f, 0.75f }; // "containerization"
var cakeEmbed = new float[] { -0.7f, 0.1f, 0.9f, -0.3f }; // "chocolate cake"
Console.WriteLine(CosineSimilarity(dockerEmbed, containerEmbed)); // ~0.95 (very similar!)
Console.WriteLine(CosineSimilarity(dockerEmbed, cakeEmbed)); // ~0.15 (unrelated)
= identieke betekenis
= niet gerelateerd
= tegenovergestelde betekenis (zeldzaam in de praktijk)
**"In deze post zal ik laten zien hoe entiteit Framework te gebruiken met..."**Het systeem zou eerder berichten moeten vinden over:
graph TB
subgraph "Traditional Keyword Search"
A1[Query: 'Docker setup'] --> B1[Find: 'Docker' OR 'setup']
B1 --> C1[❌ Misses: 'containerization guide']
B1 --> D1[❌ Misses: 'running containers']
B1 --> E1[✅ Finds: 'Docker setup tutorial']
end
subgraph "Embedding-Based Semantic Search"
A2[Query: 'Docker setup'] --> B2[Generate embedding]
B2 --> C2[Find similar embeddings]
C2 --> D2[✅ Finds: 'containerization guide']
C2 --> E2[✅ Finds: 'running containers']
C2 --> F2[✅ Finds: 'Docker setup tutorial']
end
class B2,C2 semantic
classDef semantic stroke:#333,stroke-width:2px
ORM-configuraties
Werkt met ONNX Runtime |-------|------------|------|---------|-------| | (zodat we onze GPU kunnen gebruiken) | 384 | 80MB | Good | Very Fast ⚡⚡⚡ | | Goede kwaliteit | 768 | 420MB | Better | Fast ⚡⚡ | | (nauwkeurig semantisch begrip) | 384 | 133MB | Better | Very Fast ⚡⚡⚡ | | Juiste grootte | 768 | 436MB | Best | Fast ⚡⚡ | | (384-768 afmetingen is goed evenwicht) | 1536 | N/A (API) | Excellent | Slow (network) ⚡ |
Populaire opties: Model Afmetingen Grootte Kwaliteit Snelheid
Mijn aanbeveling
bge-base-en-v1.5:
pip install optimum[exporters]
State-of-the-art open source model:
optimum-cli export onnx --model BAAI/bge-base-en-v1.5 --task feature-extraction bge-base-en-onnx/
768 afmetingen (goed evenwicht)
bge-base-en-onnx/
model.onnx # The neural network
tokenizer.json # Text → tokens converter
tokenizer_config.json
special_tokens_map.json
config.json
Werkt geweldig met ONNX Runtime: Vrij en loopt lokaal
De meeste modellen zijn in PyTorch formaat.
mkdir EmbeddingTest
cd EmbeddingTest
dotnet new console
dotnet add package Microsoft.ML.OnnxRuntime.Gpu --version 1.16.3
dotnet add package Microsoft.ML.Tokenizers --version 0.1.0-preview.23511.1
Optimum installeren (Python-bibliotheek voor conversie)
OnnxRuntime.GpuOmzetten BGE modelMicrosoft.ML.TokenizersDit creëert:Veel modellen zijn voorgeconverteerd en beschikbaar op Hugging Face met "onnx" in de naam.
using Microsoft.ML.Tokenizers;
using System;
using System.Linq;
public class SimpleTokenizer
{
private readonly Tokenizer _tokenizer;
public SimpleTokenizer(string tokenizerPath)
{
// Load the tokenizer.json file
_tokenizer = Tokenizer.CreateTokenizer(tokenizerPath);
}
public (long[] InputIds, long[] AttentionMask) Tokenize(string text, int maxLength = 512)
{
// Tokenize the text
var encoding = _tokenizer.Encode(text);
// Get token IDs
var ids = encoding.Ids.Select(i => (long)i).ToArray();
// Pad or truncate to maxLength
var inputIds = new long[maxLength];
var attentionMask = new long[maxLength];
int length = Math.Min(ids.Length, maxLength);
// Copy actual tokens
Array.Copy(ids, inputIds, length);
// Set attention mask (1 = real token, 0 = padding)
for (int i = 0; i < length; i++)
{
attentionMask[i] = 1;
}
return (inputIds, attentionMask);
}
}
Inbeddingen in C# gebruiken
**Laten we een praktische inbedding generator bouwen met behulp van ONNX Runtime.**Projectopstelling[101, 8667, 2088, 102]
**Voor inbedding moeten we token (tekst omzetten naar getallen):**Wat gebeurt hier?
Elk nummer is een token ID uit de woordenschat van het modelSpeciale penningen: 101 =
1CLS], 102 =0SEP]graph LR
A["Text: 'Docker setup'"] --> B[Tokenizer]
B --> C[Token IDs:<br/>101, 12849, 12229, 102]
C --> D[Pad to 512]
D --> E[Input IDs:<br/>101, 12849, 12229, 102, 0, 0,...]
D --> F[Attention Mask:<br/>1, 1, 1, 1, 0, 0,...]
E --> G[Feed to Model]
F --> G
class B,G process
classDef process stroke:#333,stroke-width:2px
using Microsoft.ML.OnnxRuntime;
using Microsoft.ML.OnnxRuntime.Tensors;
using System;
using System.Collections.Generic;
using System.Linq;
public class EmbeddingGenerator : IDisposable
{
private readonly InferenceSession _session;
private readonly SimpleTokenizer _tokenizer;
private readonly int _embeddingDimension;
public EmbeddingGenerator(string modelPath, string tokenizerPath, bool useGpu = true)
{
// Setup session options
var options = new SessionOptions();
if (useGpu)
{
options.AppendExecutionProvider_CUDA(0);
}
// Load model
_session = new InferenceSession(modelPath, options);
// Load tokenizer
_tokenizer = new SimpleTokenizer(tokenizerPath);
// Get embedding dimension from model output shape
var outputMetadata = _session.OutputMetadata["last_hidden_state"];
_embeddingDimension = outputMetadata.Dimensions[2]; // Usually 768 for base models
}
public float[] GenerateEmbedding(string text)
{
// Step 1: Tokenize
var (inputIds, attentionMask) = _tokenizer.Tokenize(text);
// Step 2: Create input tensors
var inputIdsTensor = new DenseTensor<long>(inputIds, new[] { 1, inputIds.Length });
var attentionMaskTensor = new DenseTensor<long>(attentionMask, new[] { 1, attentionMask.Length });
var inputs = new List<NamedOnnxValue>
{
NamedOnnxValue.CreateFromTensor("input_ids", inputIdsTensor),
NamedOnnxValue.CreateFromTensor("attention_mask", attentionMaskTensor)
};
// Step 3: Run inference
using var results = _session.Run(inputs);
// Step 4: Extract embeddings from output
var outputTensor = results.First().AsTensor<float>();
// Output shape is [batch_size, sequence_length, embedding_dim]
// We want [batch_size, embedding_dim] by mean pooling
return MeanPooling(outputTensor, attentionMask);
}
private float[] MeanPooling(Tensor<float> outputTensor, long[] attentionMask)
{
int seqLength = outputTensor.Dimensions[1];
int embeddingDim = outputTensor.Dimensions[2];
var embedding = new float[embeddingDim];
int tokenCount = 0;
// Average across all non-padded tokens
for (int seq = 0; seq < seqLength; seq++)
{
if (attentionMask[seq] == 0) continue; // Skip padding
tokenCount++;
for (int dim = 0; dim < embeddingDim; dim++)
{
embedding[dim] += outputTensor[0, seq, dim];
}
}
// Divide by count to get mean
for (int dim = 0; dim < embeddingDim; dim++)
{
embedding[dim] /= tokenCount;
}
// Normalize to unit length (common practice)
return Normalize(embedding);
}
private float[] Normalize(float[] vector)
{
float magnitude = 0;
foreach (var val in vector)
{
magnitude += val * val;
}
magnitude = MathF.Sqrt(magnitude);
var normalized = new float[vector.Length];
for (int i = 0; i < vector.Length; i++)
{
normalized[i] = vector[i] / magnitude;
}
return normalized;
}
public void Dispose()
{
_session?.Dispose();
}
}
Als de tekst kort is: pad met nullen:
graph TB
A[Model Output:<br/>Token Embeddings] --> B["Token 0 (CLS):<br/>(0.1, 0.5, -0.3, ...)"]
A --> C["Token 1 (Docker):<br/>(0.4, 0.2, -0.1, ...)"]
A --> D["Token 2 (setup):<br/>(0.3, 0.6, -0.2, ...)"]
A --> E["Token 3 (SEP):<br/>(0.2, 0.3, -0.4, ...)"]
B --> F[Average]
C --> F
D --> F
E --> F
F --> G["Sentence Embedding:<br/>(0.25, 0.4, -0.25, ...)"]
class A input
class F process
class G output
classDef input stroke:#333
classDef process stroke:#333,stroke-width:2px
classDef output stroke:#333,stroke-width:2px
Vormen van gegevens voor modelinvoer
Conclusie
Gemiddelde pooling
using System;
class Program
{
static void Main(string[] args)
{
using var embedder = new EmbeddingGenerator(
modelPath: "bge-base-en-onnx/model.onnx",
tokenizerPath: "bge-base-en-onnx/tokenizer.json",
useGpu: true
);
// Generate embeddings
var embedding1 = embedder.GenerateEmbedding("Docker containerization tutorial");
var embedding2 = embedder.GenerateEmbedding("Setting up containers with Docker");
var embedding3 = embedder.GenerateEmbedding("Baking a chocolate cake");
Console.WriteLine($"Embedding dimension: {embedding1.Length}");
Console.WriteLine($"First 5 values: {string.Join(", ", embedding1.Take(5).Select(f => f.ToString("F4")))}");
// Calculate similarities
float sim12 = CosineSimilarity(embedding1, embedding2);
float sim13 = CosineSimilarity(embedding1, embedding3);
Console.WriteLine($"\nSimilarity (Docker vs Containers): {sim12:F4}"); // ~0.85
Console.WriteLine($"Similarity (Docker vs Cake): {sim13:F4}"); // ~0.10
}
static float CosineSimilarity(float[] a, float[] b)
{
// Since vectors are normalized, dot product = cosine similarity
float dot = 0;
for (int i = 0; i < a.Length; i++)
{
dot += a[i] * b[i];
}
return dot;
}
}
Normalisatie:
Embedding dimension: 768
First 5 values: 0.0123, -0.0456, 0.0789, -0.0234, 0.0567
Similarity (Docker vs Containers): 0.8542
Similarity (Docker vs Cake): 0.1023
We gemiddelden omdat:
We hebben een inbedding nodig voor de hele zin.
Averaging vangt de algemene betekenis op:
float bestSimilarity = -1;
int bestIndex = -1;
for (int i = 0; i < 10000; i++)
{
float sim = CosineSimilarity(queryEmbedding, storedEmbeddings[i]);
if (sim > bestSimilarity)
{
bestSimilarity = sim;
bestIndex = i;
}
}
GebruiksvoorbeeldUitvoer
Prachtig!
Nu hebben we inbeddingen.
Het probleem
graph TB
A[Query Embedding] --> B[Vector Database]
B --> C{HNSW Index}
C --> D[Layer 2:<br/>Coarse Search]
D --> E[Layer 1:<br/>Refined Search]
E --> F[Layer 0:<br/>Exact Search]
F --> G[Top K Results]
H[10,000 vectors] -.Indexed.-> C
class B db
class C index
class G results
classDef db stroke:#333,stroke-width:4px
classDef index stroke:#333,stroke-width:2px
classDef results stroke:#333,stroke-width:2px
Laten we zeggen dat we 1000 blog posts hebben, elk in stukken verdeeld in 10 stuks = 10.000 inbeddingen.:
Langzaam!
~30 miljoen transacties met drijvende punten
Snelheidsvergelijking |----------|------------|------------|-------------|---------| | Naïef zoeken: 50-100ms voor 10K vectoren | ✅ Excellent | Docker | Very Fast | Apache 2.0 | | Vector DB (HNSW): 1-5ms voor 10K vectoren | ✅ (via Npgsql) | Postgres extension | Fast | PostgreSQL License | | 10-50x sneller! | ✅ Good | Docker | Very Fast | BSD-3 | | En het schalen: miljoen vectoren nog steeds slechts ~10-20ms. | ⚠️ Limited | Docker/K8s | Very Fast | Apache 2.0 | | Een vectordatabase kiezen | ❌ Python-first | Docker | Fast | Apache 2.0 |
Voor ons C# project hebben we:
Qdrant.Client)Qdrant
ChromaMijn keuze: QdrantUitstekende C# client (
docker run -p 6333:6333 -p 6334:6334 \
-v $(pwd)/qdrant_storage:/qdrant/storage \
qdrant/qdrant
Geweldige documentatie:
6333Actieve ontwikkeling6334Alternatief: pgvector**We gebruiken PostgreSQL al voor de blog!**Kan alles in één database bewaren./qdrant_storageIets minder performant maar eenvoudiger architectuur
dotnet add package Qdrant.Client --version 1.7.0
omdat het is ontworpen en gemakkelijker om de concepten te begrijpen.
using Qdrant.Client;
using Qdrant.Client.Grpc;
public class QdrantSetup
{
private readonly QdrantClient _client;
public QdrantSetup(string host = "localhost", int port = 6334)
{
_client = new QdrantClient(host, port);
}
public async Task CreateCollectionAsync(string collectionName, ulong vectorSize)
{
// Check if collection exists
var collections = await _client.ListCollectionsAsync();
if (collections.Any(c => c.Name == collectionName))
{
Console.WriteLine($"Collection '{collectionName}' already exists");
return;
}
// Create collection
await _client.CreateCollectionAsync(
collectionName: collectionName,
vectorsConfig: new VectorParams
{
Size = vectorSize, // 768 for bge-base
Distance = Distance.Cosine // Cosine similarity
}
);
Console.WriteLine($"Created collection '{collectionName}' with {vectorSize} dimensions");
}
}
Maar ik zal pgvector laten zien als alternatief.:
SizeQdrant instellenDistanceDocker Implementatie
Distance.CosineHavensDistance.Euclid- REST APIDistance.Dot- gRPC API (sneller, we zullen dit gebruiken)using Qdrant.Client.Grpc;
using System.Collections.Generic;
public class QdrantInserter
{
private readonly QdrantClient _client;
public QdrantInserter(QdrantClient client)
{
_client = client;
}
public async Task InsertBlogChunkAsync(
string collectionName,
ulong id,
float[] embedding,
string blogPostSlug,
string chunkText,
int chunkIndex)
{
var point = new PointStruct
{
Id = id,
Vectors = embedding,
Payload =
{
["blog_post_slug"] = blogPostSlug,
["chunk_text"] = chunkText,
["chunk_index"] = chunkIndex,
["timestamp"] = DateTimeOffset.UtcNow.ToUnixTimeSeconds()
}
};
await _client.UpsertAsync(collectionName, new[] { point });
}
public async Task InsertBatchAsync(
string collectionName,
List<(ulong id, float[] embedding, Dictionary<string, object> payload)> points)
{
var qdrantPoints = points.Select(p => new PointStruct
{
Id = p.id,
Vectors = p.embedding,
Payload = { p.payload }
}).ToList();
// Batch insert for efficiency
await _client.UpsertAsync(collectionName, qdrantPoints);
Console.WriteLine($"Inserted {points.Count} points");
}
}
: Persist data to:
Een verzameling is als een tabel - het bevat vectoren van een specifieke dimensie.:
public class QdrantSearcher
{
private readonly QdrantClient _client;
public QdrantSearcher(QdrantClient client)
{
_client = client;
}
public async Task<List<SearchResult>> SearchAsync(
string collectionName,
float[] queryEmbedding,
int topK = 10)
{
var searchResult = await _client.SearchAsync(
collectionName: collectionName,
vector: queryEmbedding,
limit: (ulong)topK,
scoreThreshold: 0.7f // Only return if similarity > 0.7
);
return searchResult.Select(r => new SearchResult
{
Id = r.Id.Num,
Score = r.Score,
BlogPostSlug = r.Payload["blog_post_slug"].StringValue,
ChunkText = r.Payload["chunk_text"].StringValue,
ChunkIndex = (int)r.Payload["chunk_index"].IntegerValue
}).ToList();
}
public async Task<List<SearchResult>> SearchWithFilterAsync(
string collectionName,
float[] queryEmbedding,
string blogPostSlug, // Only search within this post
int topK = 5)
{
var filter = new Filter
{
Must =
{
new Condition
{
Field = new FieldCondition
{
Key = "blog_post_slug",
Match = new Match { Keyword = blogPostSlug }
}
}
}
};
var searchResult = await _client.SearchAsync(
collectionName: collectionName,
vector: queryEmbedding,
filter: filter,
limit: (ulong)topK
);
return searchResult.Select(r => new SearchResult
{
Id = r.Id.Num,
Score = r.Score,
BlogPostSlug = r.Payload["blog_post_slug"].StringValue,
ChunkText = r.Payload["chunk_text"].StringValue,
ChunkIndex = (int)r.Payload["chunk_index"].IntegerValue
}).ToList();
}
}
public class SearchResult
{
public ulong Id { get; set; }
public float Score { get; set; }
public string BlogPostSlug { get; set; }
public string ChunkText { get; set; }
public int ChunkIndex { get; set; }
}
- Cosinus overeenkomst (meest voorkomende):
limit- Euclidische afstandscoreThreshold- PuntproductfilterVectoren invoegenusing System;
using System.Threading.Tasks;
class Program
{
static async Task Main(string[] args)
{
// Setup
var embedder = new EmbeddingGenerator(
"bge-base-en-onnx/model.onnx",
"bge-base-en-onnx/tokenizer.json",
useGpu: true
);
var client = new QdrantClient("localhost", 6334);
var searcher = new QdrantSearcher(client);
// User query
string query = "How do I set up Docker with ASP.NET Core?";
// Generate query embedding
Console.WriteLine($"Searching for: {query}");
var queryEmbedding = embedder.GenerateEmbedding(query);
// Search
var results = await searcher.SearchAsync(
collectionName: "blog_embeddings",
queryEmbedding: queryEmbedding,
topK: 5
);
// Display results
Console.WriteLine($"\nFound {results.Count} results:\n");
foreach (var result in results)
{
Console.WriteLine($"Score: {result.Score:F4}");
Console.WriteLine($"Post: {result.BlogPostSlug}");
Console.WriteLine($"Chunk: {result.ChunkText.Substring(0, Math.Min(100, result.ChunkText.Length))}...");
Console.WriteLine();
}
}
}
Zoals metadata verbonden aan elke vector:
Searching for: How do I set up Docker with ASP.NET Core?
Found 5 results:
Score: 0.8923
Post: dockercomposedevdeps
Chunk: In this post, I'll show you how to set up a development environment using Docker Compose. This is p...
Score: 0.8654
Post: dockercompose
Chunk: Docker Compose is a tool for defining and running multi-container Docker applications. With Compose...
Score: 0.8102
Post: addingentityframeworkforblogpostspt1
Chunk: You can set it up either as a windows service or using Docker as I presented in a previous post on...
Score: 0.7891
Post: imagesharpwithdocker
Chunk: When running ASP.NET Core applications in Docker containers, you may encounter issues with ImageSha...
Score: 0.7654
Post: selfhostingseq
Chunk: I use Docker Compose to run all my services. Here's the relevant part of my docker-compose.yml file...
Kan alles opslaan: posttitel, brok tekst, datum, categorieën
Veel sneller dan een-voor-een
public class BatchEmbeddingGenerator
{
private readonly EmbeddingGenerator _embedder;
public BatchEmbeddingGenerator(EmbeddingGenerator embedder)
{
_embedder = embedder;
}
public List<float[]> GenerateBatch(List<string> texts, int batchSize = 32)
{
var embeddings = new List<float[]>();
for (int i = 0; i < texts.Count; i += batchSize)
{
var batch = texts.Skip(i).Take(batchSize).ToList();
foreach (var text in batch)
{
embeddings.Add(_embedder.GenerateEmbedding(text));
}
Console.WriteLine($"Processed {Math.Min(i + batchSize, texts.Count)} / {texts.Count}");
}
return embeddings;
}
}
Qdrant verwerkt batches van 100-1000 efficiënt
using System.Security.Cryptography;
using System.Text;
public class EmbeddingCache
{
private readonly Dictionary<string, float[]> _cache = new();
public float[] GetOrGenerate(string text, Func<string, float[]> generator)
{
string hash = ComputeHash(text);
if (_cache.TryGetValue(hash, out var cached))
{
return cached;
}
var embedding = generator(text);
_cache[hash] = embedding;
return embedding;
}
private string ComputeHash(string text)
{
using var sha256 = SHA256.Create();
var bytes = sha256.ComputeHash(Encoding.UTF8.GetBytes(text));
return Convert.ToBase64String(bytes);
}
}
Uitvoer
CREATE EXTENSION vector;
CREATE TABLE blog_embeddings (
id SERIAL PRIMARY KEY,
blog_post_slug VARCHAR(255),
chunk_text TEXT,
chunk_index INT,
embedding VECTOR(768) -- 768 dimensions
);
-- Create HNSW index for fast search
CREATE INDEX ON blog_embeddings USING hnsw (embedding vector_cosine_ops);
using Npgsql;
using Pgvector;
public async Task InsertEmbeddingAsync(
string slug,
string chunkText,
int chunkIndex,
float[] embedding)
{
await using var conn = new NpgsqlConnection(connectionString);
await conn.OpenAsync();
await using var cmd = new NpgsqlCommand(
"INSERT INTO blog_embeddings (blog_post_slug, chunk_text, chunk_index, embedding) VALUES ($1, $2, $3, $4)",
conn
)
{
Parameters =
{
new() { Value = slug },
new() { Value = chunkText },
new() { Value = chunkIndex },
new() { Value = new Vector(embedding) }
}
};
await cmd.ExecuteNonQueryAsync();
}
public async Task<List<SearchResult>> SearchAsync(float[] queryEmbedding, int topK = 10)
{
await using var conn = new NpgsqlConnection(connectionString);
await conn.OpenAsync();
await using var cmd = new NpgsqlCommand(
@"SELECT blog_post_slug, chunk_text, chunk_index,
1 - (embedding <=> $1) as similarity
FROM blog_embeddings
ORDER BY embedding <=> $1
LIMIT $2",
conn
)
{
Parameters =
{
new() { Value = new Vector(queryEmbedding) },
new() { Value = topK }
}
};
var results = new List<SearchResult>();
await using var reader = await cmd.ExecuteReaderAsync();
while (await reader.ReadAsync())
{
results.Add(new SearchResult
{
BlogPostSlug = reader.GetString(0),
ChunkText = reader.GetString(1),
ChunkIndex = reader.GetInt32(2),
Score = reader.GetFloat(3)
});
}
return results;
}
**<=>Genereer geen inbeddingen één voor één.**Batch ze!
**1 - distance**Waarom?
Geheugenefficiëntie: hergebruikt buffers
Voortgangstracking: feedback van de gebruiker
Inbeddingen niet regenereren voor ongewijzigde inhoud!**pgvector alternatief**Als je alles in PostgreSQL wilt houden:
Samenvatting
Deel 2: GPU-instellingen & CUDA in C#Deel 3: Inbeddingen en vectordatabases begrijpen!
© 2026 Scott Galloway — Unlicense — All content and source code on this site is free to use, copy, modify, and sell.