Crate velesdb_core 

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 explicit SIMD (4x faster)
• 5 Distance Metrics: Cosine, Euclidean, Dot Product, Hamming, Jaccard
• Hybrid Search: Vector + BM25 full-text with RRF fusion
• Quantization: SQ8 (4x) and Binary (32x) memory compression
• Persistent Storage: Memory-mapped files for efficient disk access

Quick Start

use velesdb_core::{Database, DistanceMetric, Point, StorageMode};
use serde_json::json;

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

// Create a collection (all 5 metrics available)
db.create_collection("documents", 768, DistanceMetric::Cosine)?;
// Or with quantization: DistanceMetric::Hamming + StorageMode::Binary

let collection = db.get_collection("documents").unwrap();

// Insert vectors (upsert takes ownership)
collection.upsert(vec![
    Point::new(1, vec![0.1; 768], Some(json!({"title": "Hello World"}))),
])?;

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

// Hybrid search (vector + text)
let hybrid = collection.hybrid_search(&query_vector, "hello", 5, Some(0.7))?;

Re-exports

pub use index::HnswIndex;

pub use index::HnswParams;

pub use index::SearchQuality;

pub use index::VectorIndex;

pub use collection::Collection;

pub use collection::CollectionType;

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 point::SearchResult;

pub use quantization::cosine_similarity_quantized;

pub use quantization::cosine_similarity_quantized_simd;

pub use quantization::dot_product_quantized;

pub use quantization::dot_product_quantized_simd;

pub use quantization::euclidean_squared_quantized;

pub use quantization::euclidean_squared_quantized_simd;

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;

pub use config::ConfigError;

pub use config::HnswConfig;

pub use config::LimitsConfig;

pub use config::LoggingConfig;

pub use config::QuantizationConfig;

pub use config::SearchConfig;

pub use config::SearchMode;

pub use config::ServerConfig;

pub use config::StorageConfig;

pub use config::VelesConfig;

pub use fusion::FusionError;

pub use fusion::FusionStrategy;

pub use metrics::average_metrics;

pub use metrics::compute_latency_percentiles;

pub use metrics::hit_rate;

pub use metrics::mean_average_precision;

pub use metrics::mrr;

pub use metrics::ndcg_at_k;

pub use metrics::precision_at_k;

pub use metrics::recall_at_k;

pub use metrics::LatencyStats;

Modules

alloc_guard

RAII guards for safe manual memory management.

cache

Caching layer for VelesDB (SOTA 2026).

collection

Collection management for VelesDB.

column_store

Column-oriented storage for high-performance metadata filtering.

compression

Column compression for VelesDB (SOTA 2026).

config

VelesDB Configuration Module

distance

Distance metrics for vector similarity calculations.

error

Error types for VelesDB.

filter

Metadata filtering for vector search.

fusion

Multi-query fusion strategies for VelesDB.

gpu

GPU-accelerated vector operations using wgpu (WebGPU).

half_precision

Half-precision floating point support for memory-efficient vector storage.

index

Index implementations for efficient vector search.

metrics

Search quality metrics for evaluating retrieval performance.

perf_optimizations

Performance optimizations module for ultra-fast vector operations.

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_dispatch

Zero-overhead SIMD function dispatch using OnceLock.

simd_explicit

Explicit SIMD optimizations using the wide crate for portable vectorization.

simd_native

Native SIMD intrinsics for maximum performance.

storage

Storage backends for persistent vector storage.

vector_ref

Zero-copy vector reference abstraction.

velesql

VelesQL - SQL-like query language for VelesDB.

Structs

Database

Database instance managing collections and storage.