oxirs_vec/learned_index/mod.rs
1//! Learned vector indexes using neural networks
2//!
3//! This module implements learned index structures that use neural networks
4//! to learn data distributions and provide faster lookups than traditional
5//! index structures.
6//!
7//! ## Key Concepts
8//! - **Recursive Model Index (RMI)**: Hierarchy of models for indexing
9//! - **Learned CDF**: Neural networks learn cumulative distribution function
10//! - **Error Bounds**: Track prediction errors for correctness guarantees
11//! - **Hybrid Approach**: Combine learned models with traditional search
12//!
13//! ## References
14//! - "The Case for Learned Index Structures" (Kraska et al., 2018)
15//! - "Learning to Hash for Indexing Big Data" (Wang et al., 2016)
16
17pub mod config;
18pub mod neural_index;
19pub mod rmi;
20pub mod training;
21pub mod types;
22
23pub use config::{LearnedIndexConfig, ModelArchitecture, TrainingConfig};
24pub use neural_index::NeuralVectorIndex;
25pub use rmi::{RecursiveModelIndex, RmiStage};
26pub use training::{IndexTrainer, TrainingStats};
27pub use types::{LearnedIndexError, LearnedIndexResult, PredictionBounds};