#41 · Primary category: Vector Databases

lantern

ai ann approximate-nearest-neighbor-search data-science database embeddings hnsw image-search knn machine-learning mlops nearest-neighbor-search neural-search open-source postgres postgresql search vector ycombinator

PostgreSQL vector database extension for building AI applications

Project last updated:12/12/24

GitHub Stars

890

Forks

67

Contributors

14

License

AGPL-3.0

Why we included this project

Teams that already run PostgreSQL can add semantic search without standing up a separate vector store: Lantern is a native extension that brings vector columns, embedding generation, and approximate nearest-neighbor queries into the database they already manage. Its lantern_hnsw index, built on the usearch HNSW implementation, speeds up ORDER BY ... LIMIT similarity searches, and it ships distance operators for L2, cosine, and Hamming similarity plus helpers that generate embeddings from CLIP or Hugging Face models. Since the standard Postgres interface stays intact, existing tools and drivers keep working, and install paths include Docker, Homebrew, precompiled binaries, and a source build.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category