Contents

Introduction
- Introduction
Audience and scope
- Audience and scope
Adding the crate
- Adding the crate
Running the clustering pipeline
- Running the clustering pipeline
Incremental clustering sessions
- Incremental clustering sessions
- Limitations
Implementing data sources
- Implementing data sources
Working with `CpuHnsw` directly
- Working with `CpuHnsw` directly
- Insertion guarantees
Results and assignments
- Results and assignments
Error handling
- Error handling
Distance helpers
- Distance helpers
Feature flags and execution strategies
- Feature flags and execution strategies
Preparing benchmark datasets
Benchmarking
- Benchmarking
- Neighbour-scoring diagnostics

Audience and scope

Updated Sep 20, 2026

The guide targets developers embedding Chutoro inside their services. It assumes familiarity with Rust, asynchronous job runners, and dependency management via Cargo.