Varbase AI Search Base

Gives a site a vector index of its own content, so AI features can find pages by meaning rather than by keyword. It is the retrieval layer that Varbase AI Chatbot Base and Varbase AI Answers Base answer from.

The recipe applies Varbase Search Base, adds a search_index display per content type, and creates the content_vector Search API server and index on the site's default vector database. It holds every published node and Canvas page, in all languages, and content is indexed again on save and on cron.

Apply Varbase AI Base first, then one vector database recipe, Varbase AI VDB: MariaDB or Varbase AI VDB: Milvus, as the site's default. The recipe stops before changing anything when no default embeddings model is set. This recipe is an alpha release, not covered by the Drupal security advisory policy. Try it on a development site first.

Best used with Varbase Starter site template.

Can be installed with any Drupal CMS ~2.0 or Drupal Core ~11 site. Even if installed with the Minimal or Standard profile.

However, using it with Varbase gives you way much more cool stuff!

Sponsored and developed by Vardot.