Weaviate - Vector database that is robust, scalable, cloud-native, and fast

Weaviate is an open-source vector database. It allows you to store data objects and vector embeddings from your favorite ML-models, and scale seamlessly into billions of data objects.

Weaviate offers Semantic Search, Question-Answer Extraction, Classification, Customizable Models (PyTorch/TensorFlow/Keras), etc. Built from scratch in Go, Weaviate stores both objects and vectors, allowing for combining vector search with structured filtering and the fault tolerance of a cloud-native database. It is all accessible through GraphQL, REST, and various client-side programming languages.

Weaviate provides out-of-the-box modules for NLP / semantic search, automatic classification, and image similarity search. It has a modular setup that allows you to use your ML models inside Weaviate. You can also use out-of-the-box ML models (e.g., SBERT, ResNet, fasttext, etc.). It typically performs nearest neighbor (NN) searches of millions of objects in considerably less than 100ms. 

Weaviate allows for efficient, combined vector and scalar searches. For example, "articles related to the COVID-19 pandemic published within the past 7 days." Weaviate stores both objects and vectors and ensures the retrieval of both is always efficient. There is no need for a third-party object storage. Within Weaviate, all individual data objects are based on a class property structure where a vector represents each data object. You can connect data objects (like in a traditional graph) and search for data objects in the vector space.