closevector-hnswlib-node

> This package is modified from hnswlib-node to make the output work with closevector-hnswlib-web. All APIs are the same as hnswlib-node. you can refer to hnswlib-node for documentations.

hnswlib-node provides Node.js bindings for Hnswlib that implements approximate nearest-neghbor search based on hierarchical navigable small world graphs.

Installation

$ npm install hnswlib-node

Documentation

• hnswlib-node API Documentation
• How to run hnswlib-node on AWS Lambda

Usage

Generating search index:

import { HierarchicalNSW } from 'hnswlib-node';

const numDimensions = 8; // the length of data point vector that will be indexed.
const maxElements = 10; // the maximum number of data points.

// declaring and intializing index.
const index = new HierarchicalNSW('l2', numDimensions);
index.initIndex(maxElements);

// inserting data points to index.
for (let i = 0; i < maxElements; i++) {
  const point = new Array(numDimensions);
  for (let j = 0; j < numDimensions; j++) point[j] = Math.random();
  index.addPoint(point, i);
}

// saving index.
index.writeIndexSync('foo.dat');

Searching nearest neighbors:

import { HierarchicalNSW } from 'hnswlib-node';

// loading index.
const index = new HierarchicalNSW('l2', 3);
index.readIndexSync('foo.dat');

// preparing query data points.
const numDimensions = 8;
const query = new Array(numDimensions);
for (let j = 0; j < numDimensions; j++) query[j] = Math.random();

// searching k-nearest neighbor data points.
const numNeighbors = 3;
const result = index.searchKnn(query, numNeighbors);

console.table(result);

License

hnswlib-node is available as open source under the terms of the Apache-2.0 License.

Contributing

Bug reports and pull requests are welcome on GitHub at https://github.com/yoshoku/hnswlib-node. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the Contributor Covenant code of conduct.