先試後買

A. Increase the VECTOR_MEMORY_SIZE initialization parameter

B. Add the TARGET_ACCURACY clause to the query with a higher value for the accuracy

C. Re-create the index with a higher EFCONSTRUCTION value

D. Change the index type to HNSW for better accuracy

A. They are hierarchical with multilayered connections

B. They use hash-based clustering

C. They require exact match for searches

D. They are disk-based structures

A. Different external embedding models produce vectors with varying dimensions and data types

B. It restricts the database to a single embedding model

C. It impacts the accuracy of similarity searches

D. It limits the length of text that can be vectorized

A. Real-time vector data updates across locations

B. Built-in version control for vector data

C. Specialized vector embedding compression

D. Automatic translation of vector embeddings between formats

A. Enclose vector components in curly braces ({})

B. Rely on SQL*Loader's automatic normalization of vector data

C. Use sparse format for vector data

D. As FVEC is a binary format and the vector dimensions have a known width, fixed offsets can be used to make parsing the vectors fast and efficient

A. It guarantees higher accuracy than Euclidean Distance

B. It is simpler and faster because it avoids square-root calculations

C. It is the default distance metric for Oracle AI Vector Search

D. It supports hierarchical partitioning of vectors

A. To automatically optimize database queries for improved performance

B. To provide real-time monitoring and diagnostics for AI applications

C. To accelerate AI workloads by leveraging Exadata RDMA Memory (XRMEM), Exadata Smart Cache, and on-storage processing