Lantern

Lantern is an open-source PostgreSQL database extension to store vector data, generate embeddings, and handle vector search operations. It provides a new index type for vector columns called lantern_hnsw which speeds up ORDER BY ... LIMIT queries. Lantern builds and uses usearch, a single-header state-of-the-art HNSW implementation. With Lantern Cloud, developers have access to everything they need to build an AI application: embedding generation, vector compression, vector search, efficient indexing, and more. All on top of the database they already know, Postgres, and using infrastructure that scales to billions. * Built on top of Postgres- Add AI to your existing applications by just writing another SQL query. We support Postgres 11 - 16. * Fast index creation that scales to billions of vectors- Create an HNSW index for your data in minutes (see our benchmarks). * Create embeddings without worrying about infrastructure- Simply select the model you'd like to use to embed your data, and we'll handle the rest. No need to worry about finding the right library, switching languages, or handling API call failures. * Index hyperparameter optimization- We'll automatically tune your index for you, so you don't have to worry about finding the right set of parameters, and changing them over time.