Loading editorial discovery…
Loading editorial discovery…
About
Retrievals is a semantic search engine for the National Gallery of Art's open collection. Instead of matching keywords, it understands meaning, so “melancholy figure in candlelight” finds Rembrandt before you know to look for him.
Museum search is broken. The NGA's own search requires you to already know the artist, the title, or the accession number. If you remember a painting from a childhood visit (warm light, a woman reading, Dutch) you have no way in.
Retrievals fixes that. Describe what you remember, or what you feel, and the index finds it. The 40,368 curated artwork images are embedded into a shared vector space where visual and semantic similarity are the same thing.
Each indexed artwork image was passed through Google EmbeddingGemma 2, a multimodal model that produces a normalized 768-dimensional vector. Those image vectors live in a Modal Volume beside the model checkpoint.
When you search, the same model embeds your text with its search-query prompt. The service compares that vector against all 40,368 image vectors and returns the closest matches. Search is text-query only in the public app today; image upload is not available yet.
Embeddings
Google EmbeddingGemma 2
Multimodal model: maps text queries and artwork images into a shared 768-dimensional space
Vector search
Cosine similarity (768D)
Exact similarity search across 40,368 curated artwork image vectors
Compute
Modal CPU
Quantized CPU inference that scales with search traffic
Collection
National Gallery of Art open data
40,368 curated images from the NGA's public-domain dataset, thumbnails served from Cloudflare R2
The NGA's official search is built for lookup when you already know what you're looking for. Retrievals is built for discovery when you only have a memory or a feeling.
| Aspect | NGA catalog search | Retrievals |
|---|---|---|
| What you need to know | Artist name, title word, accession number, or catalog classification | A description: mood, scene, colour, memory, or visual impression |
| How matching works | Keyword and field match against catalog metadata | Semantic similarity in a shared vector space (40,368 indexed artwork images) |
| Example query | "Rembrandt" or "Girl with a Pearl Earring" | "melancholy figure alone by candlelight, Dutch" |
| Collection | Full NGA catalog (official site) | 40,368 indexed images from the NGA open-access dataset |
The search index covers 40,368 curated images from the 68,816 objects in the NGA's open-access dataset, which the gallery releases under a Creative Commons Zero licence. Works range from 13th-century panel paintings to 20th-century photographs. Thumbnails are served from Cloudflare R2; high-resolution images link back to the NGA's own IIIF server.