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 new hybrid search feature that enables you to combine dense and sparse vectors to deliver the best of both search methods.
Learn about the hardware, software and performance metric specifications behind our ~1B object import of the Sphere dataset into 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 about the vision of the AI-First Database Ecosystem, which drives the R&D of the databases of the future.
What Weaviate users should know about Docker & Containers.
How the vector database Weaviate overcomes the limitations of popular Approximate Nearest Neighbor (ANN) libraries.
Any kind of data storage architecture needs an API. Learn how and why Weaviate picked GraphQL.
Weaviate is an open-source vector database with a built-in NLP model called the Contextionary. Learn what makes Weaviate unique.
Learn how the AI-first vector database Weaviate unlocks the potential of unstructured data and why this is important.
