GPU-Accelerated Indexing in LanceDB

GPU-Accelerated Indexing in LanceDB(blog.lancedb.com)

19 points by yurisagalov 2 years ago | 4 comments

gardnr 2 years ago |

If you are just getting into this tech, like me, then this article leads down the rabbit hole of different index types supported in different vector stores. Most easy-to-use vector stores only use HNSW indices, which is "good enough".

A few offer different types of indices. Milvus[1] and FAISS[2] are a couple that support IVF indices. It's great to see another lightweight tool that does this with GPU acceleration.

1. https://objectbox.io/vector-database/

2. https://www.pinecone.io/learn/series/faiss/vector-indexes/

eynsham 2 years ago | |

Faiss is a library that supports indexing, not a fully-fledged vector database on its own. Milvus uses Faiss with a few other libraries to build a full vector database (https://github.com/milvus-io/milvus#acknowledgments).

esafak 2 years ago |

They do predicate pushdown for filtering too. Noice! https://lancedb.github.io/lance/read_and_write.html#filter-p...

schneehertz 2 years ago |

LanceDB is one of the few options for embeddable vector databases, and I have used it in my Electron application. If they could choose a less confusing npm package name than "vectordb," maybe I would be more forgiving towards them. Moreover, the documentation for LanceDB is also poorly written.