Follows changes in a source table automatically, in either Continuous or Triggered mode. This type of AI Search index can take your own embeddings or have Databricks generate them.
Read more: Databricks docs
In the Ultra Transcenders books
Each book explains Delta Sync Index in context, with comparison tables and the common traps.
Terms in this definition
- Event
Table in Log Analytics where entries from Windows event logs are kept.
- Triggered pipeline mode
A Lakeflow pipeline setting where a run handles whatever data is available and finishes, rather than staying up as continuous mode does. The great majority of pipelines suit it.
- AI Search
The Databricks service for similarity retrieval in RAG: it turns a source table into an index of embeddings and metadata, then answers each query with the closest matches.
- Index
Speeds up queries that filter on certain columns by keeping those columns sorted, with pointers back to each row; the price is more storage and slower writes.
- Embeddings
Vectors of numbers encoding what text means, placing related content close together as judged by cosine similarity. Switching model or vector size requires embedding all content again.
- Databricks
Analytics platform built on Apache Spark where data is processed in notebooks; Unity Catalog is the governance model it recommends.
- Field generation method
How a Content Understanding schema field is filled: extract takes the value as written (documents only), classify chooses from categories, and generate infers or summarises it.
Related terms
- Direct Vector Access Index
An index type in AI Search that you manage through API calls from your own code, as nothing feeds it from a source table.
vector_search()can't reach it, and its capacity for embeddings is far below a Delta Sync Index's. - Kilobyte
A way of measuring how much data there is; each row in a Delta Sync index, for instance, may hold up to 100 KB.