Vald

Vald is high scalable distributed high-speed approximate nearest neighbor search engine

A Highly Scalable Distributed Vector Search Engine Vald is a highly scalable distributed fast approximate nearest neighbor dense vector search engine. Vald is designed and implemented based on the Cloud-Native architecture. It uses the fastest ANN Algorithm NGT to search neighbors. Vald has automatic vector indexing and index backup, and horizontal scaling which made for searching from billions of feature vector data. Vald is easy to use, feature-rich and highly customizable as you needed. Usually the graph requires locking during indexing, which cause stop-the-world. But Vald uses distributed index graph so it continues to work during indexing. Vald implements it's own highly customizable Ingress/Egress filter. Which can be configured to fit the gRPC interface. Horizontal scalable on memory and cpu for your demand. Vald supports to auto backup feature using Object Storage or Persistent Volume which enables disaster recovery. Vald distribute vector index to multiple agent, each agent stores different index. Vald stores each index in multiple agents which enables index replicas. Automatically rebalance the replica when some Vald agent goes down. Vald can be easily installed in a few steps. You can configure the number of vector dimension, the number of replica and etc. Golang, Java, Nodejs and python is supported. Overview shows the concept of Vald and mentions the top level design of Vald. If you'd like to configure for your Vald Cluster or wonder how to operate, you can find out the answer from these documents. When you encounter any problem, please refer to these documents and try to resolve it. When wondering anything about Vald, please contact to us via Slack or Github.