Embedding as a vector of numbers (PHP)

Minimal example: embedding as a vector of numbers (PHP)

Below is a minimal pure PHP example where we emulate embeddings with fixed vectors and compare a query against documents using cosine similarity. This is the core semantic-search mechanic without external libraries.

Example of use


                
<?php

include 'code-en.php';

$query = 'speed up email sending';
$documents = [
    'email newsletter optimization',
    'how to prepare coffee',
];

$queryEmbedding = embed($query);

foreach ($documents as $doc) {
    $score = cosineSimilarity(
        $queryEmbedding,
        embed($doc)
    );

    echo $doc . ': ' . round($score, 3) . PHP_EOL;
}

Documents:


            Query: speed up email sending

email newsletter optimization
how to prepare coffee

Result: Memory: 0.005 Mb Time running: < 0.001 sec.


                email newsletter optimization: 0.998
how to prepare coffee: 0.202