A world of art.
Yours to discover.

HTML supplies the page structure, CSS its appearance, and JavaScript its interactions. Python handles import preparation and the live server requests. SQLite performs searches using FTS5, its native full-text indexing engine. Node.js is used for local preview and packaging, not the production API. The finite data import and thumbnail preparation jobs have finished; no always-running collection worker is needed.

A browser request goes through Amazon’s API Gateway to a Python function on AWS Lambda, which runs when needed. That function reads an immutable SQLite snapshot. A new execution environment loads the pinned, compressed snapshot from private S3 storage into /tmp, checks its size and SHA-256, and opens it read-only. Later requests in that environment reuse it. CloudFront, Amazon’s content-delivery service, serves the website and hosted thumbnails.

The following abbreviated example shows the same request-and-render pattern used by this site. The production client also validates responses and image destinations, cancels superseded requests, handles errors and builds the artwork controls.

async function showCollection() {
  const options = new URLSearchParams({
    imageCollection: 'true',
    page: '1',
    limit: '60'
  });
  const response = await fetch('/api/search?' + options);
  if (!response.ok) throw new Error('Search is unavailable');
  const result = await response.json();

  const cards = result.items.map(work => {
    const card = document.createElement('article');
    const title = document.createElement('h3');
    title.textContent = work.title;
    card.append(title);
    return card;
  });
  document.querySelector('#art-grid').replaceChildren(...cards);
}

The example renders titles as text. Explore adds imageCollection=true; Complete catalogue leaves it out. Search results include the matching total and timing fields. Database time, snapshot-loading time, server time and browser request time measure different parts of the trip.