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!

Understand the distance metrics that power similarity search: cosine similarity, dot product, Euclidean, Manhattan, and Hamming. Learn how to choose the right metric for your vector search application.

Learn what a vector database is and how it powers vector search, semantic search, and LLM RAG with embeddings, indexing (HNSW/ANN), and scalable retrieval.

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