What does DiskANN vector indexing in Cosmos DB optimize for?
- A Full-text search across documents
- B Approximate Nearest Neighbour (ANN) search over high-dimensional vectors (correct answer)
- C Geospatial queries
- D Time-series aggregation
Shortcut: DiskANN is a disk-based ANN algorithm that enables efficient vector similarity search (cosine, dot product, Euclidean) on high-dimensional embeddings stored in Cosmos DB.