Vector Search

Setup

Add a vector column to your model:

class Product {
  @vector(1536)
  embedding: number[];
}

Similarity Search

TypeScript

const similar = await pulsabase.from(Product)
  .vectorSearch('embedding', {
    query: [0.1, 0.2, 0.3, /* ...1536 dims */],
    limit: 10,
  })
  .find();

Dart

final similar = await pulsabase.from('products')
    .where('embedding', vectorMatch([0.1, 0.2, 0.3, ...], limit: 10))
    .find();

Tip

Use OpenAI text-embedding-3-small (1536 dims), Cohere embed-english-v3.0, or any embedding API. Store vectors in a vector(N) column.

Combining with Filters

final results = await pulsabase.from('products')
    .where('category', 'shoes')
    .where('price', lte(100))
    .where('embedding', vectorMatch(queryVector, limit: 20))
    .find();