What is Supabase Vector?
Supabase Vector extends your Postgres database with vector operations, allowing you to perform similarity searches on embeddings generated by AI models. It integrates seamlessly with Supabase's suite of tools, providing an AI toolkit that includes functions for embedding generation, indexing, and querying. With support for various distance metrics (Euclidean, cosine, inner product) and approximate nearest neighbor search using indexes, Supabase Vector is designed for production-scale AI applications. Developers can store embeddings alongside other relational data, enabling powerful hybrid queries. The toolkit also includes helper functions for working with popular embedding providers. Whether building a recommendation engine, semantic search, or anomaly detection, Supabase Vector simplifies the process. It is fully managed, ensuring high availability and performance. The pricing starts at $25/month, making it accessible for startups and enterprises alike. With Supabase Vector, you can harness the power of AI without leaving your Postgres ecosystem.
Use Cases
Key Features
Seamless integration with Postgres Support for multiple distance metrics (Euclidean cosine inner product) Approximate nearest neighbor search with indexes Built-in embedding generation helpers Hybrid queries combining vector and relational data Fully managed and scalableWho is it for?
Full, stack developers, AI engineers, data scientists, and startups building AI, powered applications
