Introduction

VectorX is a high-performance encrypted vector database built for privacy-focused applications that need blazing-fast similarity search.

With client-side encryption, flexible metadata filters, and support for multiple distance metrics (cosine, L2, and inner product), VectorX enables secure Approximate Nearest Neighbor (ANN) search on sensitive data — without compromising speed.

Why VectorX?

Traditional vector databases expose sensitive embeddings to the server for indexing and querying. VectorX flips the model — encrypting everything client-side, so only you control access.

This makes VectorX ideal for:

• Privacy-first search applications
• Regulated industries (e.g., finance, healthcare)
• Decentralized and edge-based inference

Core Highlights

• Client-side Encryption: Vectors are encrypted using private keys before being sent to the server
• Fast ANN Searches: Efficient similarity searches on encrypted vector data
• Multiple Distance Metrics: Support for cosine, L2, and inner product distance metrics
• Metadata Support: Attach and search with metadata and filters
• High Performance: Optimized for speed and efficiency with encrypted data

What’s in the Docs?

This documentation covers:

• Quick Start: Get up and running in minutes
• Installation: Install and configure the SDK
• Usage Guides: Client, Index, and Vector operations
• API Reference: Full reference for SDK classes
• Security: Key management and encryption best practices

Let’s get started → Quick Start