Crate ruvector_router_core 

Router Core

High-performance vector database and neural routing inference engine.

This crate provides the core functionality for:

• Vector storage and retrieval
• HNSW (Hierarchical Navigable Small World) indexing
• Multiple quantization techniques (scalar, product, binary)
• SIMD-optimized distance calculations
• AgenticDB API compatibility

Re-exports

pub use error::Result;

pub use error::VectorDbError;

pub use types::DistanceMetric;

pub use types::SearchQuery;

pub use types::SearchResult;

pub use types::VectorEntry;

pub use vector_db::VectorDB;

Modules

distance

SIMD-optimized distance calculations using SimSIMD

error

Error types for the vector database

index

HNSW index implementation

quantization

Quantization techniques for memory compression

storage

Storage layer with redb and memory-mapped files

types

Core types for the vector database

vector_db

Main VectorDB API