Weaviate Blog

Weaviate 1.21 released with new operators, performance improvements, multi-tenancy improvements, and more!

Learn about why you need distance metrics in vector search and the metrics implemented in Weaviate (Cosine, Dot Product, L2-Squared, Manhattan, and Hamming).

What is a Vector Database? Explaination of core concepts, such as vector embeddings, vector search, and vector indexing

Learn about our latest open source demo and how we used Semantic and Generative Search to improve access to health

Learn how to make testing less of a chore with Embedded Weaviate, and other tips for better automated testing.

Weaviate 1.20 released with multi-tenancy, PQ, search re-ranking, autocut, hybrid fusion algorithm ... take a look!

ML Models that can see, read, hear and more!

An introductory overview of LlamaIndex, the LLM framework

Learn about the new native multi-tenancy feature

Learn about the intersection between LLMs and Search

The Weaviate server can be run locally directly from client code

A discussion on data privacy and privacy-preserving machine learning for LLMs