Databricks AI Search

Databricks AI Search is the current Databricks name, previously Mosaic AI Vector Search (since June 2026).

Databricks Vector Search → Mosaic AI Vector Search → Databricks AI Search

Managed search over Unity Catalog data; now supports full-text and hybrid search without pre-computed embeddings.

• It outgrew pure vector search - it now also does full-text keyword search and hybrid keyword-similarity search, and on storage-optimized endpoints you can even build an index with no precomputed embedding columns at all. 🔗

⚠ Limitations: Row- and column-level permissions aren't supported, indexes can't be cloned across workspaces, and the _id column name is reserved. Query results are capped (10000 rows for ANN, 200 for hybrid/full-text) with a 10 MB max response, and storage-optimized endpoints add limits such as no continuous sync, embedding dimensions divisible by 16, and no CMK or FedRAMP support. 🔗

Category

AI / ML

In use from

June 2026🔗

Also known as

Mosaic AI Vector Search, Databricks Vector Search, Vector Search

Verified

2026-07-23