Weaviate Blog

Fine-tuning LlaMA 7B to use the Weaviate GraphQL APIs

How hybrid search works, and under the hood of Weaviate's fusion algorithms.

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).

Vector databases explained by their core concepts of 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