pgvector

What problem does it solve?

This Skill enables adding powerful vector similarity search directly into your existing PostgreSQL database, eliminating the need for a separate vector store and simplifying your architecture.

Core Features & Use Cases

• Vector Column Types: Store embeddings efficiently within PostgreSQL.
• Indexing: Supports HNSW and IVFFlat for fast similarity lookups.
• Hybrid Queries: Seamlessly combine SQL filtering and sorting with vector similarity search.
• Use Case: Integrate semantic search into your existing application by storing product descriptions as embeddings alongside product data in PostgreSQL, allowing users to find products using natural language queries.

Quick Start

Use the pgvector skill to create a vector column and add a HNSW index to your documents table.