vicinity

Approximate nearest-neighbor search.

Install

Each algorithm is a separate feature. Enable what you need:

[dependencies]
vicinity = { version = "0.4", features = ["hnsw"] }          # graph index
# vicinity = { version = "0.4", features = ["ivf_pq"] }      # compressed index
# vicinity = { version = "0.4", features = ["nsw"] }         # flat graph

Usage

HNSW

High recall, in-memory. Best default choice.

use vicinity::hnsw::HNSWIndex;

let mut index = HNSWIndex::builder(128).m(16).ef_search(50).build()?;
index.add_slice(0, &[0.1; 128])?;
index.add_slice(1, &[0.2; 128])?;
index.build()?;

let results = index.search(&[0.1; 128], 5, 50)?;
// results: Vec<(doc_id, distance)>

IVF-PQ

Compressed index. 32–64× less memory than HNSW, lower recall. Use for datasets that don't fit in RAM.

use vicinity::ivf_pq::{IVFPQIndex, IVFPQParams};

let params = IVFPQParams { num_clusters: 256, num_codebooks: 8, nprobe: 16, ..Default::default() };
let mut index = IVFPQIndex::new(128, params)?;
index.add_slice(0, &[0.1; 128])?;
index.add_slice(1, &[0.2; 128])?;
index.build()?;

let results = index.search(&[0.1; 128], 5)?;

Persistence

Save and load indexes with the serde feature:

[dependencies]
vicinity = { version = "0.4", features = ["hnsw", "serde"] }

// Save
index.save_to_file("my_index.json")?;

// Load
let index = HNSWIndex::load_from_file("my_index.json")?;

See examples/06_save_and_load.rs for a full example.

Benchmark

GloVe-25 (1.18M vectors, 25-d, cosine), Apple Silicon, single-threaded:

Full numbers in docs/benchmark-results.md.

Algorithms

Each algorithm has a named feature flag:

Quantization: RaBitQ, SAQ (quantization feature, via qntz crate). PQ is part of ivf_pq.

See docs.rs for the full API.

License

MIT OR Apache-2.0