Question 1

How are vectqr embeddings stored in Oracle Database 23ai?

Options :

A : They are stored in a separate, specialized vector database.

B : They are not stored; they are only used for querying.

C : By creating columns with the VECTOR data type in relational tables.

D : They are appended as metadata to existing data files.

Answer: B

Question 2

A machine learning team is using IVF indexes in Oracle Database 23ai to find similar images in a large dataset. During testing, they observe that the search results are often incomplete, missing relevant images. They suspect the issue lies in the number of partitions probed. How should they improve the search accuracy?

Options :

A : Add the TARGET_ACCURACY clause to the query with a higher value for the accuracy

B : Change the index type to HNSW for better accuracy

C : Increase the VECTOR_MEMORY_SIZE initialization parameter

D : Re-create the index with a higher EFCONSTRUCTION value

Answer: A

Question 3

You are tasked with creating a table to store vector embeddings with the following characteristics: Each vector must have exactly 512 dimensions, and the dimensions should be stored as 32-bitfloating point numbers. Which SQL statement should you use?

Options :

A : CREATE TABLE vectors (id NUMBER, embedding VECTOR(512))

B : CREATE TABLE vectors (id NUMBER, embedding VECTOR)

C : CREATE TABLE vectors (id NUMBER, embedding VECTOR(*, INT8

D : CREATE TABLE vectors (id NUMBER, embedding VECTOR(512, FLOAT32))

Answer: D

Question 4

Multi-Vector Similarity Search is typically used for:

Options :

A : Exact vector matching

B : Single-vector comparisons

C : Multi-document search

D : Image recognition

Answer: C

Question 5

Which of the fpllowing statements is NOT true regarding operations on VECTOR columns?

Options :

A : You can use CTAS (Create Table As Select) to create a new table with a VECTOR column based on an existing table.

B : You tan update a VECTOR column based on the value of another column in the same table.

C : You can drop a VECTOR column from a table using ALTER DROP COLUMN.

D : You can perform direct comparisons between two VECTOR columns using operators like

Answer: D