📰 Weaviate Blog

An end-to-end generative feedback loop demo using Weaviate, Ollama, Mistral and Snowflake’s Snowpark Container Services!

The new (v4) release of the Weaviate Python Client is - faster (gRPC), provides better IDE support and more type-safety, and many other developer experience imp

What you need to consider when using the Weaviate vector database with non-English languages, such as Hindi, Chinese, or Japanese.

We look at how to build Multimodal applications in TypeScript and dive into everything that needs to happen in between.

A reflection on 2023 from team Weaviate!

Weaviate 1.23 released with AutoPQ, flat indexing + Binary Quantization, OSS LLM support through Anyscale, and more!

Learn how to build Multimodal Retrieval Augmented Generation (MM-RAG) systems that combine text, images, audio, and video. Discover contrastive learning, any-to

Recap the first Weaviate visit to Amazon re:Invent in Las Vegas

Learn about high-availability setups with Weaviate, which can allow upgrades and other maintenance with zero downtime.

Learn about new trends in RAG evaluation and the current state of the art.

UK-based startup Moonsift is harnessing the power of AI with Weaviate.

Weaviate 1.22 released with nest object storage, async indexing, further gRPC support, and more!

Join us in celebrating Hacktoberfest, a month-long celebration of open source!

A preview release of our new Python client is now available! Help us make it better by trying it out and providing your feedback.

Learn how to build an application using Weaviate and Confluent

The details behind how you can compress vectors using PQ with little loss of recall!

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 m

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!