📰 Weaviate Blog

Did you know that Weaviate can summarize information during retrieval? Learn how you can summarize your data to tackle the problem of information overload.

LangChain is one of the most exciting new tools in AI. It helps overcome many limitations of LLMs, such as hallucination and limited input lengths.

Learn about the six pillars outlining how Weaviate will evolve in 2023.

Recent advances in AI are breathing new life into podcasting! The Whisper speech-to-text model is a game-changer!

Machine learning models can create beautiful and novel images. Learn how Diffusion Models work and how you could make use of them.

Get an intuitive understanding of what exactly vector embeddings are, how they're generated, and how they're used in semantic search.

Ever wonder how Weaviate turns objects into vectors, behind-the-scenes? Find out in this post!

Learn about the hardware, software and performance metric specifications behind our ~1B object import of the Sphere dataset into Weaviate.

Weaviate 1.17 introduces Replication, Hybrid Search, BM25, Faster Startup and Imports and more. Learn all about it.

Cohere announced the release of the text-understanding multilingual model. Learn how to use it in Weaviate.

Learn how to import and query the Sphere dataset in Weaviate!

Learn more about the differences between vector libraries and vector databases!

Weaviate introduces Ref2Vec, a new module that utilises Cross-References for Recommendation!

Learn how to quickly and easily back up and restore your Weaviate data with the native backup feature.

Weaviate 1.16 introduces New Filter Operators, Distributed Backups, Centroid Module, Node Status API, Azure-based OIDC, and more. Lear all about it.

The Lock Striping pattern is a great way to solve race conditions without sacrificing performance. Lean about Weaviate's improvements.

Learn how to use build an image search application using the Img2vec-neural module in Weaviate.

Vector search on disks: How does Vamana compare to HNSW?

Learn about the various Sentence Transformers from Hugging Face!

Running ML Model Inference in production is hard. You can use Weaviate – a vector database – with Hugging Face Inference module to delegate the heavy lifting.

Two weeks after the 1.15 release, we have a patch (v1.15.1) release for you, which brings 15 bug fixes and 2 UX improvements.

Weaviate 1.15 introduces Cloud-native Backups, Memory Optimizations, faster Filtered Aggregations and Ordered Imports, new Distance Metrics and new Weaviate mod

Press Release: Pay-as-you-grow comes to Vector Search.

Self-Supervised Retrieval can surpass BM25 and Supervised techniques. This technique also pairs very well alongside BM25 in Hybrid Retrieval. Learn more about i