LinkedCulture has a new milestone.

LinkedCulture has a new milestone.

The main LinkedCulture semantic search index now includes more than 220,000 open-access museum records across six collections, including the Art Institute of Chicago, Rijksmuseum, Cleveland Museum of Art, The Getty, Harvard Art Museums, and The Met.

I’ve also published a first multilingual experiment: semantic search in French across more than 50,000 Getty open-access records, indexed with a multilingual Nomic embedding model.

The main index is still primarily English-based. The multilingual page is intentionally narrower, using Getty records as a focused test case for French-language queries against real cultural metadata.

Main LinkedCulture project:   https://linkedculture.org/

Multilingual Getty test:   https://linkedculture.org/multilingual

The goal is not to replace museum catalogues or turn collections into chatbots.

The goal is to test whether open-access metadata, embeddings, and vector search can support better discovery by meaning, material, symbol, mood, and visual idea.

The current stack is intentionally practical: custom ingestion pipelines, Nomic embeddings, Qdrant vector search, Next.js, Cloudflare, and Hetzner Cloud.

Records remain with their source institutions. LinkedCulture is an independent research prototype using open-access collection metadata.

Open to conversations with museums, archives, libraries, researchers, and digital humanities teams interested in semantic discovery across open collections.