This Rust library provides a fast, pure-Rust implementation of the Hierarchical Navigable Small Worlds (HNSW) algorithm for approximate nearest neighbor (ANN) searching. It is designed for developers needing efficient similarity search capabilities, particularly for use cases like word vector indexing or finding closest points in large datasets.

How It Works

Instant Distance leverages the HNSW graph-based indexing structure, which allows for efficient querying by navigating through layers of interconnected nodes. This approach offers a good trade-off between search speed and accuracy for ANN problems, outperforming brute-force methods on large datasets. The implementation is written entirely in Rust, aiming for performance and memory safety.

Quick Start & Requirements

• Primary install: cargo add instant-distance
• Prerequisites: Rust toolchain.
• Example usage and testing instructions are provided in the README.

Highlighted Details

• Pure Rust implementation of HNSW.
• Powers backend services for Instant Domain Search.
• Supports Euclidean distance metric.

Maintenance & Community

• The project is maintained by djc.
• No explicit community links (Discord/Slack) or roadmap are provided in the README.

Licensing & Compatibility

• The README does not explicitly state a license. This is a critical omission for adoption decisions.

Limitations & Caveats

The absence of a declared license is a significant blocker for adoption, especially for commercial or closed-source projects. Further investigation into the licensing status is required.