Embedding recipes

EmbeddingService

Purpose: Text-to-vector conversion and similarity search.

Use cases

Semantic translation memory (textdb).
Content similarity.
Duplicate detection.
Semantic search.

Key features

Aggressive caching (deterministic).
Batch processing.
Cosine similarity calculations.
Top-K similarity search.

Example

Example: Using EmbeddingService

use Netresearch\NrLlm\Service\Feature\EmbeddingService;

// Generate embedding
$vector = $embeddingService->embed('Search query text');

// Find similar
$similar = $embeddingService->findMostSimilar(
    queryVector: $vector,
    candidateVectors: $allVectors,
    topK: 5
);

Methods

EmbeddingService methods

// Generate embedding (cached automatically)
$vector = $embeddingService->embed('Some text');

// Full response with metadata
$response = $embeddingService->embedFull('Some text');

// Batch embedding
$vectors = $embeddingService->embedBatch(['Text 1', 'Text 2']);

// Calculate cosine similarity
$similarity = $embeddingService->cosineSimilarity($vectorA, $vectorB);

// Find most similar vectors
$results = $embeddingService->findMostSimilar(
    $queryVector,
    $candidateVectors,
    topK: 5
);

// Normalize a vector
$normalized = $embeddingService->normalize($vector);