Tag product photos with 2x Amazon Rekognition’s accuracy, 98% cheaper

import { readFile } from 'node:fs/promises';
import { SIEClient } from '@superlinked/sie-sdk';

const client = new SIEClient(undefined, { apiKey: 'sk-sie-…' });

const banks = {
  "type": ["ottoman", "stool", "sofa"],
  "colour": ["blue", "brown", "purple"],
  "material": ["velvet", "suede", "fabric"]
};
const templates = {
  "type": ["a photo of {article} {label}.", "{label}", "a product photo of {article} {label}."],
  "colour": ["a {label} object."],
  "material": ["a photo of a product made of {label}."]
};
const imageUrl = "https://superlinked.com/reference/image-classify/blue-velvet-ottoman.jpg";
const source = await fetch(imageUrl);
if (!source.ok) throw new Error('Could not download the original image.');
const image = new Uint8Array(await source.arrayBuffer());
const names = ['type', 'colour', 'material'] as const;
const prompts = names.flatMap((bank) => banks[bank].flatMap((label) =>
  templates[bank].map((template) => template
    .replaceAll('{article}', /^[aeiou]/i.test(label) ? 'an' : 'a')
    .replaceAll('{label}', label)),
));
const vecs = await client.encode('google/siglip-so400m-patch14-384', [
  { images: [image] },
  ...prompts.map((text) => ({ text })),
]);
console.log(vecs.map((vector) => vector.dense));

image_bytes=$(curl --fail --silent --show-error --location 'https://superlinked.com/reference/image-classify/blue-velvet-ottoman.jpg' | base64 | tr -d '\n')
curl https://api.superlinked.com/v1/encode/google%2Fsiglip-so400m-patch14-384 \
  -H "Authorization: Bearer sk-sie-…" \
  -H "Content-Type: application/json" \
  -d "{\"items\":[{\"images\":[{\"data\":\"$image_bytes\",\"format\":\"jpeg\"}]},{\"text\":\"a photo of an ottoman.\"},{\"text\":\"ottoman\"},{\"text\":\"a product photo of an ottoman.\"},{\"text\":\"a photo of a stool.\"},{\"text\":\"stool\"},{\"text\":\"a product photo of a stool.\"},{\"text\":\"a photo of a sofa.\"},{\"text\":\"sofa\"},{\"text\":\"a product photo of a sofa.\"},{\"text\":\"a blue object.\"},{\"text\":\"a brown object.\"},{\"text\":\"a purple object.\"},{\"text\":\"a photo of a product made of velvet.\"},{\"text\":\"a photo of a product made of suede.\"},{\"text\":\"a photo of a product made of fabric.\"}],\"params\":{\"output_types\":[\"dense\"]}}"