Exam 1Z0-184-25: Oracle AI Vector Search Professional

August 05,2025 92%

1. When generating vector embeddings outside the database, what is the most suitable option for
storing the embeddings for later use?
Yo

• in a CSV file
• In a binary FVEC file with the relational data in a CSV file
• In the database as BLOB (Binary Large Object) data
ut

• In a dedicated vector database

ub

2. When generating vector embeddings for a new dataset outside of Oracle Database 23ai, which
factor is crucial to ensure meaningful similarity search results?
e

• The choice of programming language used to process the dataset (for example, Python, Java)
• The physical location where the vector embeddings are stored
ch

• The storage format of the new dataset (for example, CSV, JSON)
• The same vector embedding model must be used for vectorizing the data and creating a query
vector
an

3. You are working with vector search in Oracle Database 23ai and need to ensure the integrity
of your vector data during storage and retrieval
ne

Which factor is crucial for maintaining the accuracy and reliability of your vector search results

•
l:

Using the same embedding model for both vector creation and similarity search
• Regularly updating vector embeddings to reflect changes in the source data
• The specific distance algorithm employed for vector comparisons
Ex

• The physical storage location of the vector data

4. Which DDL operation is NOT permitted on a table containing a VECTOR column in Oracle
pl

Database 23ai?

•
oi

Creating a new table using CTAS CREATE TABLE AS SELECT that includes the VECTOR
column from the original table
t&

• Dropping an existing VECTOR column from the table

• Modifying the data type of an existing VECTOR column to a non-VECTOR type
• Adding a new VECTOR column to the table
O

5. Which SQL statement correctly adds a VECTOR column named v with 4 dimensions and
FLOAT 32 format to an existing table named my_table?
pe

• ALTER TABLE my_table MODIFY (V VECTOR (4, FLOAT32))

• ALTER TABLE my_table ADD (V VECTOR (4, FLOAT32))
ra

• UPDATE my_table SET v - VECTOR (4, FLOAT32)

• ALTER TABLE my_table ADD v VECTOR (4, FLOAT32)
te

6. 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?
 • Add the TARGET ACCURACY clause to the query with a higher value for the accuracy.
• Change the index type to HNSW for better accuracy.
• Increase the VECTOR MEMORY SIZE initialization parameter.
• Re-create the index with a higher EFCONSTRUCTION value
7. What happens when querying with an IVF index if you increase the value of the NEIGHBOR
PARTITION probes parameter?
Yo

• The number of centroids decreases.

• Accuracy decreases.
ut

• Index creation time is reduced.

• More partitions are probed, improving accuracy, but also increasing query latency
ub

8. Which PL/SQL package is primarily used for interacting with Generative Al services in
Oracle Database 23ai?
e

• DBMS AI
ch

• DBMS ML
• DBMS VECTOR CHAIN
• DBMS GENAI
an

9. Which SQL function is used to create a vector embedding for a given text string in Oracle
Database 23ai?
ne

• GENERATE EMBEDDING
• CREATE VECTOR_EMBEDDING
l:

• EMBED TEXT
• VECTOR EMBEDDING
Ex

10. Which PL/SQL function converts documents such as PDF, DOC, JSON, XML, or HTML to
plain text?
pl

• DBMS VECTOR.TEXT_TO_PLAIN
• DBMS VECTOR_CHAIN. UTL TO TEXT
oi

• DBMS VECTOR CHAIN.UTIL_TO_CHUNKS

• DBMS VECTOR.CONVERT_TO_TEXT
t&

11. What is the primary purpose of the DBMS_VECTOR_CHAIN_UTL_TO_CHUNS package

in a RAG application?
O

• To generate vector embeddings from a text document

• To load a document into the database
pe

• To split a large document into smaller chunks to improve vector quality by minimizing token
truncation
• To convert a document into a single, large text string.
ra

12. What is the first step in setting up the practice environment for Select Al?
te

• Optionally create an OCI compartment.

• Create a policy to enable access to OCI Generative Al
• Drop any compartment that does not use OCI Generative Al.
13. How is the security interaction between Autonomous Database and OCI Generative Al
managed in the context of Select Al?
 • By encrypting all communication between the Autonomous Database and OCI Generative Al
using TLS/SSL protocols
• By utilizing Resource Principals, which grant the Autonomous Database instance access to
OCI Generative Al without exposing sensitive credentials
• By establishing a secure VPN tunnel between the Autonomous Database and OCI Generative
Al service
• By requiring users to manually enter their OCI API keys each time they execute a natural
Yo

language query
14. You are storing 1,000 embeddings in a VECTOR column, each with 256 dimensions using
ut

FLOAT32. What is the approximate size of the data on disk?

•
ub

1 MB
• 4 MB
• 256 KB
e

• 1GB
15. Which Oracle Cloud Infrastructure (OC) service is directly integrated with Select Al?
ch

• 000 Language
•
an

OCI Generative Al
• OCT Vision
• OCI Data Science
ne

16. Which is NOT a feature or capability related to Al and Vector Search in Exadata?

• Native Support for Vector Search Only within the Database Server
l:

• Vector Replication with Golden Gate

• Loading Vector Data using SQL "Loader
Ex

• Al Smart Scan
17.Which statement best describes the core functionality and benefit of Retrieval Augmented
pl

Generation (RAG) in Oracle Database 23ai?

• it empowers LLMs to interact with private enterprise data stored within the database, leading
oi

to more context aware and precise responses to user queries

• It primarily aims to optimize the performance and efficiency of LLMs by using advanced data
t&

retrieval techniques, thus minimizing response times, and reducing computational overhead
• It allows users to train their own specialized LLMs directly within the Oracle Database
environment using their internal data, thereby reducing the reliance on external ai providers
O

• It enables Large Language Models (LLMs) to access and process real-time data streams from
diverse sources to generate the most up-to-date insights
pe

18.lf a query vector uses a different distance metric than the one used to create the index, what
happens?
ra

• The query fails.

• An exact match search is triggered.
te

• The index automatically updates.

• A warning is logged, but the query executes.
 19. What are the key advantages and considerations of using Retrieval Augmented Generation
(RAG) in the context of Oracle Ai Vector Search?

• it excels at optimizing the performance and efficiency of LLM inference through advanced
caching and precomputation techniques, leading to faster response times but potentially
storage requirements.
• It priorities real-time data extraction and summarization from various sources to ensure the
Yo

LLM always has the most up-to-date information

• It focuses on training specialized LLMs within the database environment for specific tasks,
offering greater control over model behavior and data privacy bum potentially requiring more
ut

development effort.
• It leverages existing database security and access controls, thereby enabling secure and
ub

controlled access to both the database content and the LLM

20. Which Python library is used to vectorize text chunks and the user's question in the
e

following example
import oracledb
ch

connection oracledb, connect (uner-un, password-pw, den-es)

table name - Page
an

with connection.cursor() as cursort

Create the table
create_table_sqi
ne

CREATE TABLE IF NOT EXISTS (table_name) (

id NUMBER PRIMARY KEY,
payload CLOR CHECK (payload TS JSON).
l:

vector VECTOR
try:
cursor.execute(create table sql)
Ex

except oracledb. Database Error as es

raise
pl

connection.autocommit True
from sentence_transformers import Sentence Transformer encoder Sentence Transformer('all
oi

MiniLM-L12-v2)
• Sentence transformers
t&

• oci
• oracledb
• json
O

21. What is the function of the COS INE parameter in the SQL query used to retrieve similar
vectors?
pe

topk = 3
sqlf'select payload, vector distance (vector, vector, COSINE) as score from (table_name) order
ra

by score fetch approxfirat (topk) rows only"""

te

...

• It filters out vectors with a cosine similarity below a certain threshold.

• It converts the vectors to a format compatible with the SQL database.
• It indicates that the cosine distance metric should be used to measure similarity between
vectors.
 • It specifies the type of vector encoding used in the database.
22. You are tasked with finding the closest matching sentences across books, where each book
has multiple paragraphs and sentences. Which SQL structure should you use?

• GROUP BY with vector operations.

• FETCH PARTITIONS BY clause.
Yo

• A nested query with ORDER BY.

• Exact similarity search with a single query vector
23.In the following Python code, what is the significance of prepending the source filename to
ut

each text chunk before storing it in the vector database?

ub

...
docs = [("text": filename + ''+ section, 'path': filename) for filename, sections in faqs.item() for
e

section in sections]
#Sample the resulting data
ch

docs [:2]
an

...

• It preserves context and aids in the retrieval process by associating each vectorized chunk
with its original source file.
ne

• It helps differentiate between chunks from different files but has no impact on vectorization.
• It speeds up the vectorization process by providing a unique identifier for each chunk.
l:

• It improves the accuracy of the LLM by providing additional training data.

24. How does an application use vector similarity search to retrieve relevant information from a
Ex

database, and how is this information then integrated into the generation process?

• Encodes the question and database chunks into vectors, finds the most similar using cosine
pl

similarity, and includes them in the LLM prompt.

• Trains a separate LLM on the database and uses it to answer, ignoring the general LLM.
oi

• Converts the question to keywords, searches for matches, and inserts the text into the
response.
t&

• Clusters similar text chunks and randomly selects one from the most relevant cluster.
25. When using SQL "Loader to load vector data for search applications, what is a critical
consideration regarding the formatting of the vector data within the input CSV file?
O

• Enclose vector components in curly braces (()).

•
pe

As FVEC is a binary format and the vector dimensions have a known width, fixed offsets can
he used to make parsing the vectors fast and efficient
• Use sparse format for vector data.
ra

• Rely on SQL "Loader's automatic normalization of vector data.

26. Which function is used to generate vector embeddings within an Oracle database?
te

• DBMS_VECTOR_CHAIN.UTL_TO_CHUNKS
• DBMS_VECTOR_CHAIN.UTL_TO_TEXT
• DBMS_VECTOR_CHAIN.UTL_TO_EMBEDDINGS
• DBMS_VECTOR_CHAIN.UTL_TO_GENERATE_TEXT
 27.Which statement best describes the capability of Oracle Data Pump for handling vector data
in the context of vector search applications?

• Data Pump only export and import vector data if the vector embeddings are stored as BLOB
(Binary Large Object) data types in the database.
• Data Pump treats vector embeddings as regular text strings, which can lead to data corruption
or loss of precision when transferring vector data for vector search.
Yo

• Data Pump provides native support for exporting and importing tables containing vector data
types, facilitating the transfer of vector data for vector search applications.
• Because of the complexity of vector data Data Pump requires a specialized plug in to handle
ut

the export andimport operations involving vector data types

28. What happens when you attempt to insert a vector with an incorrect number of dimensions
ub

into a VECTOR column with a defined number of dimensions?

• The database truncates the vector to fit the defined dimensions,

e

• The database pads the vector with zeros to match the defined dimensions.
• The insert operation fails, and an error message is thrown.
ch

• The database ignores the defined dimensions and inserts the vector as is
29.In Oracle Database 23ai, which data type is used to store vector embeddings for similarity
an

search?

• VECTOR2
ne

• BLOB
• VECTOR
l:

• VARCHAR2
30.What is created to facilitate the use of OCI Generative Al with Autonomous Database?
Ex

• An Al profile for OCI Generative Al

• A dedicated OCI compartment
•
pl

A new user account with elevated privileges

31. Why would you choose to NOT define a specific sire for the VECTOR column during
oi

development?
t&

• it impacts the accuracy of similarity searches.

• it restricts the database to a single embedding model
• it limits the length of text that can be vectorized.
• Different external embedding models produce vectors with varying dimensions and data
O

types.
pe

32. What is the correct order of steps for building a RAG application using PL/SQL in Oracle
ra

Database 23ai?

• Load ONNX Model, Vectorize Question, Load Document, Split Text into Chunks, Create
te

Embeddings, Perform Vector Search, Generate Output.

• Load Document, Split Text into Chunks, Load ONNX Model, Create Embeddings, Vectorize
Question, Perform Vector Search, Generate Output.
• Vectorize Question, Load ONNX Model, Load Document, Split Text into Chunks, Create
Embeddings, Perform Vector Search, Generate Output.
 • Load Document, Load ONNX Model, Split Text into Chunks, Create Embeddings, Vectorize
Question, Perform Vector Search, Generate Output.
33. What is the primary purpose of a similarity search in Oracle Database 23ai?

• optimize relational database operations

• to compute distances between all data points in a database
Yo

• To find exact matches in BLOB data

• To retrieve the most semantically similar entries using distance metrics between different
vectors
ut
ub

34. What is the advantage of using Euclidean Squared Distance rather than Euclidean Distance
in similarity search queries?
e

• it is the default distance metric for Oracle Al Vector Search,

• It supports hierarchical partitioning of vectors
ch

• it is simpler and faster because it avoids 70% calculations

• It guarantees higher accuracy than Euclidean Distance.
an

35.you need to prioritize accuracy over speed in a similarity search for a dataset of images.
which should you Use?

•
ne

Approximate similarity search with HNSW indexing and target accuracy of 70%.
• Multivector similarity search with partitioning.
• Exact similarity search using a full table scan.
l:

• Approximate similarity search with IVF indexing and target accuracy of 70%.
36.What is the significance of splitting text into chunks in the process of loading data into
Ex

Oracle Al Vector Search?

• To reduce the computational burden on the embedding model

pl

• To facilitate parallel processing of the data during vectorization

• To minimize token truncation as each vector embedding model has its own maximum token
oi

limit
37. What the purpose of the VECTOR_ DISTANCE function in Oracle Database 23ai similarity
t&

search?

• To fetch rows that match exact vector embeddings.

• To create vector indexes for efficient searches
O

• To group vectors by their exact scores

pe

• To calculate the distance between vectors using a specified metric

ra

38. You are asked with creating table to store vector embeddings with the following
characteristics: Each vector must have exactly 512 dimensions. • The dimensions should be
te

stored as 32-bit floating point numbers. Which SQL statement should you use?

• CREATE Table vectors (id NUMBER, embedding VECTOR(512))f

• CREATE TABLE vectors (id NUMBER, embedding VECTOR),
• CREATE TabLE vectors (id NUNBER, embedding VECTOR(*, INT8)),
• CREATE TABLE vectors (id NUNBER, embedding VECTOR (512, FLOAT32));
 39. Which function should you use to determine the storage format of a vector?

• VECTOR_DIMENSION_FORMAT
• VECTOR_CHUNKS
• VECTOR_NORM
• VECTOR_ENBEDDING
Yo

40. what security enhancement is introduced in Exadata system software 24ai?

• Integration with third party security tool

• Enhanced encryption algorithm for data at rest
ut

• Snmp securitys
ub

41. you need to generate a vector from the string 1[1.2, 3.4]" in FLOAT32 format with 2
dimensions Which function will you use?
e

• To VECTOR
• VECTOR DISTANCE
ch

• FROM_VECTOR
• VECTOR SERIALIZE
an

42. What is the primary purpose of the VECTOR_EMBEDDING function in Oracle Database
23ai?
ne

• To calculate vector dimensions

• To calculate vector distances
• To serialize vectors into a string
l:

• To generate a single vector embedding for data

43. What is a key characteristic of HNSW vector indexes?
Ex

• They are hierarchical with multilayered connections

• They require exact match for searches
pl

• They are disk-based structures.

• They use hash- based clustering.
oi

44. What is the primary function of Al Smart Scan in Exadata System Software 24ai?
t&

• To provide real-time monitoring and diagnostics for Al applications.

• To accelerate Al workloads by leveraging Exadata RDMA Memory (XRMEM), Exadata
Smart | Cache, and on-storage processing.
O

• To automatically optimize database queries for improved performance.

45. Which parameter is used to define the number of closest vector candidates considered
pe

during HNSW index creation?

• EFCONSTRUCTION
ra

• VECTOR_MEMORY_SIZE
• NEIGHBOURS
te

• TARGET_ACCURACY
46. You want to quickly retrieve the top-10 matches for a query vector from a dataset of billions
of vectors, prioritizing speed over exact accuracy.What is the best approach?

• Exact similarity search using flat search

 • Approximate similarity search with a low target accuracy setting
• Relational filtering combined with an exact search
• Exact similarity search with a high target accuracy setting
47. Which is a characteristic of an approximate similarity search in Oracle Database 23ai?

• It compares every vector in the dataset.

Yo

• It trades off accuracy for faster performance.

• always guarantees 100% accuracy.
• It is slower than exact similarity search.
ut

48. Which operation is NOT permitted on tables containing VECTOR columns?

ub

• SELECT
• UPDATE
• DELETE
e

• JOIN ON VECTOR columns.

ch

49. Which is a characteristic of an approximate similarity search in Oracle Database 23ai?

• It compares every vector in the dataset

an

• trades off accuracy for faster performance

• always guarantees 100% accuracy.
• it is slower than exact similarity search
ne

50. You are asked to fetch the top five vectors nearest to a query vector, but only for a specific
category of documents
l:

Which query structure should you use?

Ex

• Use UNION ALL with vector operations.

• Perform the similarity search without a WHERE clause.
• Apply relational filters and a similarity search in the query.
pl

• Use VECTOR_INDEX_HINT and NO WHERE clause

oi

51. What is the primary function of an embedding model in the context of vector search?
t&

• To define the schema for a vector database

• To execute similarity search operations within a database
• To Transform text or data into numerical vector representations
O

• To store vectors in a structured format for efficient retrieval

pe

52. What is the significance of using local ONNX models for embedding within the database?

• Support for legacy SQL*Plus clients

ra

• Improved accuracy compared to external models

• Reduced embedding dimensions for faster processing
te

• Enhanced security because data remains within the database

53. Which of the following actions will result in an error when using
VECTOR_DIMENSION_COUNT() in Oracle Database 23ai?

• Providing a vector with a dimensionality that exceeds the specified dimension count.
• Using a vector with a data type that is not supported by the function.
 • Providing a vector with duplicate values for its components.
• Calling the function on a vector that has been created with to_vector().
54. An application needs to fetch the top-3 matching sentences from a dataset of books while
ensuring a balance between speed and accuracy. Which query structure should you use?

• Approximate similarity search with the VECTOR_DISTANCE function

Yo

• Exact similarity search with Euclidean distance

• Multivector similarity search with approximate fetching and target accuracy
• A combination of relational filters and similarity search
ut

55. You are asked with finding the closest matching sentences across books, where each book has
multiple paragraphs and sentences. Which SQL structure should you use?
ub

• A nested query with ORDER BY

• Exact similarity search with a single query vector
e

• GROUP BY with vector operations

• FETCH PARTITIONS BY clause
ch

56. What is the primary difference between the HNSW and IVF vector indexes in Oracle
Database 23ai?
an

• Both operate identically but differ in memory usage.

• HNSW guarantees accuracy, whereas IVF sacrifices performance for accuracy.
ne

• HNSW uses an in-memory neighbor graph for faster approximate searches, whereas IVF use
the buffer cache with partitions
• HNSW is partition based, whereas IVF uses neighbor graphs for indexing.
l:

57. A database administrator wants to change the VECTOR MEMORY SIZE parameter for a
pluggable database (PDB) in Oracle Database 23a. Which SQL command is correct?
Ex

• ALTER SYSTEM SET vector memory size-1G SCOFE-BOTH:

• ALTER DATABASE SET vector_memory_size-1G SCOPE-VECTOR/
pl

• ALTER SYSTEM SET vector_memory_size-1G SCOPE-SGA

• ALTER SYSTEM RESET vector_memory_size:
oi

58.Which vector index available in Oracle Database 23ai is known for its speed and accuracy,
t&

making it a preferred choice for vector search

• Binary Tree (BT) index

• Inverted File System (IFS) index
O

• Full-Text (FT) index

• Hierarchical Navigable Small World (HNSW) index
pe

59. What is the purpose of the Vector Pool in Oracle Database 2.3ai?
ra

• To manage database partitioning

• To store HNSW vector indexes and IVF index metadata
•
te

To enable longer SQL execution

• To store non-vector data types
60. What is the default distance metric used by the VECTOR DISTANCE function if none is
specified?

• Euclidean
 • Hamming
• Cosine
• Manhattan
61. In Oracle Database 23ai, which SQL function calculates the distance between two vectors
using the Euclidean matric?
Yo

• L1 DISTANCE
• L2 DISTANCE
• HANMING DISTANCE
ut

• COSINE DISTANCE
62. What is a key advantage of using GoldenGate 23ai for managing and distributing vector
ub

data for Al applications?

• Real-time vector data updates across locations.

e

• Automatic translation of vector embeddings between formats.

• Specialized vector embedding compression.
ch

• Built-in version control for vector data.

63. What happens when you attempt to insert a vector with an incorrect number of dimensions
an

into a VECTOR column with a defined number of dimensions?

• The database pads the vector with zeros to match the defined dimensions
ne

• The database ignores the defined dimensions and inserts the vector as is.
• The database truncates the vector to fit the defined dimensions.
• The insert operation fails, and an error message is thrown
l:

64. The question asks which SQL statement will successfully insert a vector into a table named
my_table with a single VECTOR column named v.
Ex

The correct syntax for inserting a vector in Oracle’s AI Vector Search would typically use the
proper vector format. Based on the options provided:
pl

• INSERT INTO my_table VALUES ((1.1, 2.2, 3.3))

oi

• INSERT INTO my_table (v) VALUES ('[1.1, 2.2, 3.3]')

• INSERT INTO my_table (v) VALUES (1.1, 2.2, 3.3)
t&

• INSERT INTO my_table VALUES ('1.1, 2.2, 3.3')

O

67. Which Oracle Cloud Infrastructure (OCI) service is directly integrated with Select Al? O
OCI Vision OCI Data Science OCI Generative Al OOO Language
pe

Answer: OCI Generative AI.

68. How does Select AI RAG leverage vector stores to enhance the capabilities of Large
ra

Language Models (LLMS)?

• Select AI RAG leverages vector stores to perform semantic similarity searches, finding and
te

adding pertinent information from private data to improve prompts for LLMS.
• Select Al RAG uses vector stores to reduce the size of LLM prompts by retrieving only the
most relevant information, minimizing computational overhead.
• Select AI RAG utilizes vector stores for the efficient management and retrieval of large
volumes of textual data, leading to faster response times from LLMs.
 • Select AI RAG employs vector stores to isolate sensitive data, ensuring LLMs do not have
direct access to private information.
69. Which of the following is NOT a benefit of Select Al?

• It requires extensive SQL knowledge to formulate complex queries.

• It leverages Oracle Database security to protect data.
Yo

• It provides flexibility in choosing the most suitable large language model.

70. Which is NOT a valid distance metric for vector indexing in Oracle Database 23ai?
ut

• Binary Search
• Cosine
ub

• Euclidean
• Hamming
e

71. A retail company uses an Oracle Database 23ai HNSW vector index to recommend products
to customers based on their browsing history.
ch

The database administrator notices that the after restarting the database, product
recommendations are slower.
an

What steps should the administrator take to resolve the issue?

• Decrease the VECTOR_MEMORY_SIZE parameter.

ne

• Adjust the NEIGHBOR PARTITION PROBES parameter for improved accuracy.

• Rebuild the HNSW index or enable automatic reload.
• Modify the distance metric to DOT.
l:

72. What is a key advantage of generating vector embeddings outside the database?
Ex

• Simplified data management

• Flexibility in choosing specialized embedding models
• Improved data security
pl

• Reduced storage requirements

oi

73. What does the VECTOR_NORM function return?

t&

• The Euclidean norm or distance between the vector and the origin.
• The number of dimensions of a vector
• The angle between two vectors
• The negated dot product of two vectors
O

74. What is one type of notebook used for interacting with Select Al?
pe

• Oracle Machine Learning (OML) Notebooks

• ROCE Notebooks
ra

• Wyde Rule Notebooks

76. Where are ONNX models stored after being loaded into an Oracle Database instance?
te

• A table that includes BLOB data type

• System Global Area (SGA)
• Program Global Area (PGA)
• A table that includes VECTOR data type
 77. Which SQL operation is NOT supported when working with VECTOR columns in Oracle
Database 23ai?

• Loading data with SQL*Loader

• JOIN conditions
• INSERT INTO statements
• Distance computations using custom distance functions
Yo

78. Based on the source code provided, which specific Generative Al model is being utilized?
BEGIN
ut

--drops the profile if it already exists

ub

DBMS_CLOUD_AI.drop_profile(
profile name => 'OCIAI COHERE',
e

force => true);

ch

DBMS CLOUD AI.CREATE PROFILE (

profile_name => 'OCIAI_COHERE',
an

attributes => '{

ne

"provider": "oci",
"credential_name": "OCISRESOURCE_PRINCIPAL",
l:

"model": "cohere.command-r-plus",
"oci_apiformat":"COHERE"}');
Ex

END;
/
pl

• LaMDA
oi

• TensorFlow
• Cohere
t&

• GPT-3
79. What is the purpose of the policy created in the Select Al practice environment setup?
O

• To enable access to OCI Generative Al

• To enforce data encryption protocols
pe

• To define backup and recovery procedures

80. Why would you choose to NOT define a specific size for the VECTOR column during
ra

development?

• It restricts the database to a single embedding model.

te

• Different external embedding models produce vectors with varying dimensions and data
types.
• It impacts the accuracy of similarity searches.
• It limits the length of text that can be vectorized.
 81. Which SQL query would retrieve the top-10 vectors based on Euclidean distance using exact
similarity search?

• SELECT docID
FROM vector tab
ORDER BY VECTOR DISTANCE (embedding,query_vector, COSINE)
FETCH EXACT FIRST 10 ROWS ONLY;
Yo

• SELECT docID
FROM vector tab
ut

WHERE VECTOR_DISTANCE (embedding, query_vector, EUCLIDEAN) < 10;

ub

• SELECT docID
FROM vector tab
GROUP BY VECTOR DISTANCE (embedding, query vector, EUCLIDEAN)
e

FETCH FIRST 10 ROWS ONLY;

ch

• SELECT docID
FROM vector tab
ORDER BY VECTOR DISTANCE (embedding, query vector, EUCLIDEAN)
an

FETCH EXACT FIRST 10 ROWS ONLY;

82. Which is NOT a feature or capability related to Al and Vector Search in Exadata?
ne

• Vector Replication with GoldenGate

• Al Smart Scan
l:

• Loading Vector Data using SQL*Loader

• Native Support for Vector Search Only within the Database Server
Ex

August 05,2025 92%

83. Which is a type of Neighbor Partition Vector Index supported in Oracle Database 23ai?
pl

• Hierarchical Navigable Small World (HNSW)

oi

• Binary Tree Index

• Inverted File Flat (IVF)
t&

• Neighbor Hash Table (NHT)

84. What is the advantage of using Euclidean Squared Distance rather than Euclidean Distance
in similarity search queries?
O

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

•
pe

It is the default distance metric for Oracle Al Vector Search.

• It guarantees higher accuracy than Euclidean Distance.
• It supports hierarchical partitioning of vectors.
ra

85. In the following example, what is the primary purpose of the chunk_overlap attribute when
defining a vector index using the DBMS_CLOUD_AI.CREATE_VECTOR_INDEX procedure?
te

BEGIN
--Create the vector index and the pipeline. Its source is the web site DBMS_CLOUD_AI.
create_vector_index(
index_name => 'support',
attributes(
 "vector_db_provider"; "oracle",
"location": "https://objectstorage.us-xxx/o/",
"profile_name": "GENAI VECTOR",
"vector dimension": 1024,
"vector distance_metric": "cosine",
"chunk overlap":50,
"chunk_size" : 450}');
Yo

END;
/
ut

• Limits the number of documents stored.

ub

• Sets the similarity threshold for relevance.

• Specifies vector embedding dimensions.
• Controls text overlap between consecutive chunks.
e

86. In the context of Select Al, what is an "Al Profile," and what purpose does it serve?
ch

• It is a user profile that stores preferences for data visualization and reporting in Select Al
applications.
an

• It is a security feature that restricts access to sensitive data within Select Al applications.
• It encapsulates connection information for an Al provider, including security credentials,
provider name, model name, and a list of target tables.
ne

• It is a machine learning model trained on specific data sets to enhance the accuracy of natural
language query processing.
l:

87. In Oracle Database 23ai, which SQL function is used to split text into words, sentences, or
paragraphs for vector embedding preparation?
Ex

• VECTOR_CHUNKS
• VECTOR_NORM
• VECTOR_EMBEDDING
pl

• VECTOR_DISTANCE
oi
t&

September 01,2025 88%

88. What does a target accuracy of 80% in an approximate similarity search imply?
O

• Only 80% of the indexed vectors are used.

• 80% of the query results will match the exact search results.
pe

• The search will process 80% of the dataset.

• 80% accuracy seen in the index calculated distances.
ra
te