Mosaic AI Vector Search
A native vector search service from Databricks that serves as the retrieval layer for RAG and agent applications on the lakehouse. Indexes sync automatically from Delta tables and are governed by Unity Catalog, supporting similarity search, hybrid search, and full-text keyword search.
Timeline (last 90 days)
Mosaic AI Vector Search is Databricks' native vector search service, serving as the retrieval layer for RAG and agent applications on the lakehouse.
Mosaic AI Vector Search offers two endpoint types: Standard endpoints handle low-latency queries; storage-optimized endpoints target larger indexes and automatically scale down after an index is deleted. A single endpoint can host up to 50 indexes.
Mosaic AI Vector Search's Delta Sync index listens to the change log of a Delta table and automatically syncs newly added or modified rows into the vector index, with no need for teams to write and maintain a separate embedding pipeline.
Unstructured supports Databricks Delta Tables (including Volumes) as an output destination, producing a Delta Sync index that can be fed directly to Mosaic AI Vector Search.
All Facts (4)
Mosaic AI Vector Search is Databricks' native vector search service, serving as the retrieval layer for RAG and agent applications on the lakehouse.
50%UnverifiedMosaic AI Vector Search offers two endpoint types: Standard endpoints handle low-latency queries; storage-optimized endpoints target larger indexes and automatically scale down after an index is deleted. A single endpoint can host up to 50 indexes.
50%UnverifiedMosaic AI Vector Search's Delta Sync index listens to the change log of a Delta table and automatically syncs newly added or modified rows into the vector index, with no need for teams to write and maintain a separate embedding pipeline.
50%UnverifiedUnstructured supports Databricks Delta Tables (including Volumes) as an output destination, producing a Delta Sync index that can be fed directly to Mosaic AI Vector Search.
50%