Build related content links using vector embeddings and pgvector for Laravel

Laravel News

Laravel Related Content is a package that uses vector embeddings and PostgreSQL's pgvector extension to automatically discover semantically related content across different model types. Instead of real-time similarity searches, it pre-computes relationships at save time and stores them as database records, enabling fast (~5ms) lookups. The package supports multiple embedding providers (OpenAI, Ollama), cross-model relationships, background processing via queues, and semantic search by meaning rather than keywords. Setup involves enabling pgvector, configuring an embedding provider, adding a trait to models, and defining which fields generate embeddings.

Laravel Related Content: Semantic Relationships Using pgvector