Crate velesdb_core

Crate velesdb_core 

Source
Expand description

§VelesDB Core

High-performance vector database engine written in Rust.

VelesDB is a local-first vector database designed for semantic search, recommendation systems, and RAG (Retrieval-Augmented Generation) applications.

§Features

  • Blazing Fast: HNSW index with SIMD-optimized distance calculations
  • Persistent Storage: Memory-mapped files for efficient disk access
  • Simple API: Easy-to-use interface for vector operations

§Quick Start

ⓘ
use velesdb_core::{Database, Collection, DistanceMetric};

// Create a new database
let db = Database::open("./data")?;

// Create a collection
let collection = db.create_collection("documents", 768, DistanceMetric::Cosine)?;

// Insert vectors
collection.upsert(vec![
    Point::new(1, vec![0.1, 0.2, ...], json!({"title": "Hello World"})),
])?;

// Search for similar vectors
let results = collection.search(&query_vector, 10)?;

Re-exports§

pub use index::HnswIndex;
pub use index::HnswParams;
pub use index::SearchQuality;
pub use index::VectorIndex;
pub use collection::Collection;
pub use distance::DistanceMetric;
pub use error::Error;
pub use error::Result;
pub use filter::Condition;
pub use filter::Filter;
pub use point::Point;
pub use quantization::BinaryQuantizedVector;
pub use quantization::QuantizedVector;
pub use quantization::StorageMode;
pub use column_store::ColumnStore;
pub use column_store::ColumnType;
pub use column_store::ColumnValue;
pub use column_store::StringId;
pub use column_store::StringTable;
pub use column_store::TypedColumn;

Modules§

collection
Collection management for VelesDB.
column_store
Column-oriented storage for high-performance metadata filtering.
distance
Distance metrics for vector similarity calculations.
error
Error types for VelesDB.
filter
Metadata filtering for vector search.
half_precision
Half-precision floating point support for memory-efficient vector storage.
index
Index implementations for efficient vector search.
point
Point data structure representing a vector with metadata.
quantization
Scalar Quantization (SQ8) for memory-efficient vector storage.
simd
SIMD-optimized vector operations for high-performance distance calculations.
simd_avx512
Enhanced SIMD operations with runtime CPU detection and optimized processing.
simd_explicit
Explicit SIMD optimizations using the wide crate for portable vectorization.
storage
Storage backends for persistent vector storage.
velesql
VelesQL - SQL-like query language for VelesDB.

Structs§

Database
Database instance managing collections and storage.