datastores.ai
Vald

Vald

Open SourceKubernetes

Highly scalable distributed vector search engine

Categoryopen-sourceLanguageGoLicenseApache-2.0Websitevald.vdaas.org

About Vald

Vald is an open-source distributed vector search engine designed for scalability and reliability in cloud-native environments. Built on Kubernetes, Vald provides automatic scaling, fault tolerance, and high availability, making it suitable for large-scale AI applications. It supports efficient similarity search across distributed clusters and integrates well with modern containerized infrastructure. Vald is commonly used in applications requiring high scalability, such as recommendation systems, semantic search, and real-time AI workloads.

Key features

Kubernetes-native deployment
Custom NGT algorithm
Horizontal auto-scaling
gRPC API
Automatic rebalancing
Multi-index support

Pricing

Open SourceFree
Self-hosted on K8s

Common use cases

Large-scale similarity search
Image search at scale
Real-time recommendations
Internal ML platforms

Common questions about Vald

Is Vald free to use?

Yes, Vald is open source under the Apache-2.0 license. You can self-host it at no licensing cost, though you'll need to manage infrastructure and operational costs.

Can I get support for Vald?

Vald has community support through documentation, forums, and GitHub issues. Some open-source databases also offer commercial enterprise support contracts.

What are the main use cases for Vald?

Vald is commonly used for large-scale similarity search, image search at scale, real-time recommendations, and similar applications requiring semantic similarity search.

Does Vald integrate with popular AI tools?

Most vector databases integrate with LangChain, LlamaIndex, and popular embedding providers. Check the Vald documentation for specific integration guides and examples.

Not sure if Vald is right for you?

Compare it side-by-side with other vector databases to find the best fit for your project.