1Z0-184-25: Oracle AI Vector Search

Professional
1:
* What is the primary difference between the HNSW and IVF vector
indexes in Oracle Database 23c?
* Correct Answer: HNSW uses an in-memory neighbor graph for faster
approximate searches, whereas IVF uses the buffer cache with partitions.
2:
* What is the purpose of the Vector Pool in Oracle Database 23c AI?
Correct Answer: To store HNSW vector indexes and IVF index
metadata. 3:
* If a query vector uses a different distance metric than the one used to
create the index, what happens?
* Correct Answer: The query
fails.
4:
* Which vector index available in Oracle Database 23c is known for its
speed and accuracy, making it a preferred choice for vector search?
Correct Answer: Hierarchical Navigable Small World
(HNSW) index 5:
* Which SQL operation is NOT supported when working with VECTOR
columns in Oracle Database 23c?
Correct Answer: JOIN
conditions 6:
* What happens when querying with an IVF index if you increase the value of
the NEIGHBOR PARTITION PROBES parameter?
Correct Answer: More partitions are probed, improving accuracy, but also increasing
query latency.
7:
* Correct Answer: Inverted File Flat
(IVF)
8:
* Which parameter is used to define the number of closest vector candidates
considered during HNSW index creation?
Correct Answer:
EFCONSTRUCTION 9:
* A retail company uses an Oracle Database 23c HNSW vector index to
recommend products to customers based on their browsing history. The
database administrator notices that after restarting the database, product
recommendations are slower. What steps should the administrator take to
resolve the issue?
Correct Answer: Rebuild the HNSW index or enable automatic
reload. 10:
* What is a key advantage of using GoldenGate 23c AI for managing and
distributing vector data for AI applications?
Correct Answer: Real-time vector data updates across
locations. 11:
* You are tasked with creating a table to store vector embeddings
with the following characteristics:
Correct Answer: CREATE TABLE vectors (id NUMBER, embedding VECTOR(512,
FLOAT32)); 12:
* Which function should you use to determine the storage format of a vector?
Correct Answer:

*info.tipsandtricks10@gma
VECTOR_DIMENSION_FORMAT 13:
In Oracle Database 23c AI, which SQL function is used to split text into

com
words, sentences, or paragraphs for vector embedding preparation?
Correct Answer: VECTOR_CHUNKS
14:
* You need to generate a vector from the string '[1.2, 3.4]' in
FLOAT32 format with 2 dimensions. Which function will you use?
Correct Answer: FROM_VECTOR
15:
* You are working with vector search in Oracle Database 23c AI and need to
ensure the integrity of your vector data during storage and retrieval. Which
factor is crucial for maintaining the accuracy and reliability of your vector
search results?
Correct Answer: Using the same embedding model for both vector creation and similarity
search
16:
*
Correct Answer: Flexibility in choosing specialized embedding
models 17:
* When generating vector embeddings for a new dataset outside of
Oracle Database 23c, which factor is crucial to ensure meaningful similarity
search results?
Correct Answer: The same vector embedding model must be used for vectorizing
the data and creating a query vector.
18:
* In the following Python code, what is the significance of prepending the
source filename to each text chunk before storing it in the vector database?
Correct Answer: It preserves context and aids in the retrieval process by associating
each vectorized chunk with its original source file.
19:
* Which Python library is used to vectorize text chunks and the user's
question in the following example?
*
Correct Answer: sentence-
transformers 20:
* What is the function of the COSINE parameter in the SQL query used to
retrieve similar vectors?
Correct Answer: It indicates that the cosine distance metric should be used to measure
similarity between vectors.
21:
* How does an application use vector similarity search to retrieve relevant
information from a database, and how is this information then integrated into
the generation process?
* Correct Answer: Encodes the question and database chunks into vectors,

info.tipsandtricks10@gma
finds the most similar using cosine similarity, and includes them in the LLM
prompt.

com
22:
* Why would you choose to NOT define a specific size for the VECTOR
column during development?
* Correct Answer: Different external embedding models produce vectors with
varying dimensions and data types.
23:
* In Oracle Database 23c AI, which data type is used to store vector
embeddings for similarity search?
Correct Answer:
VECTOR 24:
* Which SQL function is used to create a vector embedding for a given
text string in Oracle Database 23c AI?
Correct Answer: GENERATE_EMBEDDING
25:
* Which PL/SQL function converts documents such as PDF, DOC, JSON,
XML, or HTML to plain text?
Correct Answer: ODMS_VECTOR_CHAIN.UTIL_TO_TEXT
26:
* Which PL/SQL package is primarily used for interacting with Generative AI
services in Oracle Database 23c AI?
Correct Answer:
ODMS_GENAI 27:
* What is the primary purpose of the DBMS_VECTOR_CHAIN.UTIL_TO_CHUNKS
package in a RAG application?
Correct Answer: To split a large document into smaller chunks to improve vector
quality by minimizing token truncation.
28:
Correct Answer: Native Support for Vector Search Only within the
Database Server 29:
* Which DDL operation is NOT permitted on a table containing a VECTOR
column in Oracle Database 23c AI?
Correct Answer: Modifying the data type of an existing VECTOR column to a non-
VECTOR type. 30:
* Which SQL statement correctly adds a VECTOR column named v with 4
dimensions and FLOAT32 format to an existing table named my_table?
Correct Answer: ALTER TABLE my_table ADD v VECTOR (4, FLOAT32);
31:
* 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?
Correct Answer: Multivector similarity search with approximate fetching and
target accuracy 32:
* 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?
Correct Answer: A nested query with ORDER
BY

33:
* Which statement best describes the capability of Oracle Data Pump for
handling vector data in the context of vector search applications?
Correct Answer: Data Pump provides native support for exporting and importing
tables containing vector data types, facilitating the transfer of vector data for vector
search applications. 34:
* What is the purpose of the VECTOR_DISTANCE function in Oracle
Database 23c AI similarity search?
Correct Answer: To calculate the distance between vectors using a
specified metric 35:
* You need to prioritize accuracy over speed in a similarity search for a
dataset of s. Which approach should you use?
*
Correct Answer: Exact similarity search using a full
table scan 36:
* Which SQL query would retrieve the top 10 vectors based on Euclidean
distance using exact similarity search?
Correct Answer: SELECT
docID FROM vector_tab
ORDER BY VECTOR_DISTANCE (embedding, :query_vector, EUCLIDEAN_SQUARED)
FETCH FIRST 10 ROWS ONLY;

37:
* What is the advantage of using Euclidean Squared Distance rather than
Euclidean Distance in similarity search queries?
*
Correct Answer: It is simpler and faster because it avoids square-root
calculations. 38:
* What is the default distance metric used by the VECTOR_DISTANCE
function if none is specified?
Correct Answer:
Cosine 39:
* In Oracle Database 23c AI, which SQL function calculates the distance
between two vectors using the Euclidean metric?
Correct Answer: L2_DISTANCE
40:
 * 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 file?
Correct Answer: 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.
41:
* How does Select AI RAG leverage vector stores to enhance the
capabilities of Large Language Models (LLMs)?
Correct Answer: 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.

42:
* Which Oracle Cloud Infrastructure (OCI) service is directly integrated with Select AI?
Correct Answer: OCI Generative
AI 43:
Correct Answer: Apply relational filters and a similarity search in
the query. 44:
* What does a target accuracy of 80% in an approximate similarity search imply?
Correct Answer: 80% accuracy seen in the index calculated
distances. 45:
* Which statement best describes the core functionality and benefit of
Retrieval Augmented Generation (RAG) in Oracle Database 23c AI?
* Correct Answer: It empowers LLMs to interact with private enterprise data
stored within the database, leading to more context-aware and precise
responses.
46:
Correct Answer: It leverages existing database security and access controls, thereby
enabling secure and controlled access to both the database content and the LLM.
47:
Correct Answer: Enhanced security because data remains within the database.
48:
Correct Answer: To transform text or data into numerical vector representations

Question 49:
What is the key advantage of using GoldenGate 23ai for managing and distributing
vector data for AI applications?
*

Answer: Real-time vector data updates across locations.

Question 50: Which SQL statement correctly creates a table named "vectors" with an "id"
column of NUMBER type and an "embedding" column of VECTOR type with 512
dimensions, where each dimension is a 32-bit floating-point number?
Options:
* CREATE TABLE vectors (id NUMBER, embedding VECTOR(512, FLOAT32));
* CREATE TABLE vectors (id NUMBER, embedding VECTOR(512));
* CREATE TABLE vectors (id NUMBER, embedding VECTOR(, INT8));
* CREATE TABLE vectors (id NUMBER, embedding VECTOR);
Answer: CREATE TABLE vectors (id NUMBER, embedding VECTOR(512, FLOAT32));

Question 51: Which function returns information about how the dimensions of a
vector are stored (e.g., data type, precision)?
Answer: VECTOR_DIMENSION_FORMAT

Question 52: What is the crucial factor for maintaining the accuracy and reliability of
vector search results?
Answer: Using the same embedding model for both vector creation and similarity search.

Question 53: What is the crucial factor when generating embeddings outside the
database and using them for similarity searches within the database?
Answer: The same vector embedding model must be used for vectorizing the data and
creating a query vector.

Question 54: What is the key advantage of generating vector embeddings outside the
database? Options:
Answer: Flexibility in choosing specialized embedding models.

info.tipsandtricks10@gma
Question 55: What is the purpose of prepending the filename to each text chunk
before vectorization?
Answer: It preserves context and aids in the retrieval process by associating each

com
vectorized chunk with its original source file.

Question 56: Which Python library is used to vectorize text chunks and the user's question
in the example?
Options:

Answer: sentence_transformers (based on the code snippet `from sentence_transformers

Question 57: What does the 'COSINE' parameter within the 'vector_distance'
function indicate?
Answer: It indicates that the cosine distance metric should be used to measure similarity
between vectors.

Question 58: What is the primary reason for not defining a specific size (number of
dimensions) and data type for a VECTOR column?
Answer: Different external embedding models produce vectors with varying
dimensions and data types.

Question 59: What is the correct function to create a vector from a string
representation of the vector's components?
Answer: FROM_VECTOR

Question 60: What is the primary purpose of the

Answer: To split a large document into smaller chunks to improve vector quality by
minimizing token truncation.

info.tipsandtricks10@gma
Question 61: What is the DDL operation that is NOT permitted on a table containing
a VECTOR column?
Answer: Modifying the data type of an existing VECTOR column to a non-VECTOR type.

Question 62: What is the correct SQL statement to add a new VECTOR column named "v"
with 4 dimensions and FLOAT32 data type to a table named "my_table"?
Answer: ALTER TABLE my_table ADD (v VECTOR(4, FLOAT32));

Question 63: What is the crucial step in a vector search process that encodes the
question and database chunks into vectors, finds the most similar using cosine
similarity, and includes them in the LLM prompt?

Answer: Encodes the question and database chunks into vectors, finds the most
similar using cosine similarity, and includes them in the LLM prompt.

Question 64: What is the correct data type to store vector embeddings for similarity
searches in Oracle Database 23ai?
Answer: VECTOR

Question 65: What is the specific SQL function used in Oracle Database 23ai to generate
vector embeddings from text strings?

Answer: VECTOR_EMBEDDING

Question 66: What is the PL/SQL package primarily used for interacting with Generative
AI services in Oracle Database 23ai?
Options:

Answer: DBMS_GENAI

info.tipsandtricks10@gma
Question 67: What is the PL/SQL function used to extract text content from various
document formats like PDF, DOC, JSON, XML, and HTML for vector embedding

com
preparation?
Options:

Answer: DBMS_VECTOR_CHAIN.UTIL_TO_TEXT

Question 68: What is NOT a feature related to AI and Vector Search in

Question 69: What is the best SQL structure for finding the closest matching
sentences across
Answer: A nested query with ORDER BY

Question 70: What is the primary function of an embedding model in

Question 71: What is the most significant advantage of using local ONNX models for
embedding within the database?

Answer: Enhanced security because data remains within the database.

Question 72: What are the key advantages and considerations of using Retrieval
Augmented Generation (RAG) in the context of databases?
Options:

Answer : Leverages existing database security and access controls.

Question 73: What statement best describes the core functionality and benefit of
Retrieval Augmented Generation (RAG) in Oracle Database?
Options:

Answer: It empowers LLMs to interact with private enterprise data stored within the
database, leading to more context-aware and precise responses.

Question 74: What is the most accurate interpretation of a target accuracy of 80% in
an approximate similarity search?
Answer: 80% of the query results will match the exact search results.

Question 75: What is the best approach to retrieve the top 5 most similar documents from
a specific category using vector search?
Answer: Apply relational filters and a similarity search in the query.

Question 76: What is the OCI service directly integrated with

Answer: OCI Language

Question 77: What is the most accurate statement about Select AI RAG and vector
stores? Options:

Answer: Select AI RAG uses vector stores to reduce the size of LLM prompts by
retrieving only the most relevant information.

Question 78: What is the SQL function that calculates the distance between two vectors
using the Euclidean metric in Oracle Database 23ai?
Options:

Answer: L2_DISTANCE

Question 79: What is the primary advantage of using Euclidean Squared Distance
rather than Euclidean Distance in similarity search queries?
Answer: It is simpler and faster because it avoids square-root calculations.

Question 80: What is the correct SQL query to retrieve the top 10 vectors based on
Euclidean distance using exact similarity search?Not enough information provided.
Answer:
```sql
SELECT docID
FROM vector_tab
ORDER BY VECTOR_DISTANCE(embedding, query_vector,
EUCLIDEAN) FETCH EXACT FIRST 10 ROWS ONLY;

Question 81: What is the most accurate way to perform a similarity search when accuracy
is the top priority? Options:
● Answer: Exact similarity search using a full table scan.
Question 82: What is the purpose of the VECTOR_DISTANCE function in Oracle Database
23ai similarity search? Options:
● Answer: To calculate the distance between vectors using a specified metric.

Question 83: What is the most accurate statement about Data Pump and vector data
Answer: Data Pump provides native support for exporting and importing tables containing
vector data types, facilitating the transfer of vector data for vector search applications.

Question 84: What is the purpose of the policy created in the Select AI practice
environment?
● To enable access to OCI Generative AI ✅ (Correct Answer)
Question 85: What is the default distance metric used by the VECTOR_DISTANCE
function if none is specified? Options:
● Answer:
Cosine

Question 86: What is the most accurate way to perform a similarity search when accuracy
is the top priority? Options:
Answer: Exact similarity search using a full table scan.

87 How is the security interaction between Autonomous Database and OCI Generative AI
managed?

Correct Answer:
✅ Option 4: By utilizing Resource Principals, which grant the Autonomous
Database instance access to OCI services

88 Which SQL statement will successfully insert a vector into a table named my_table
with a single VECTOR column named v?
Correct Answer:
✅ Option 2: INSERT INTO my_table (v) VALUES ('{1.1, 2.2, 3.3}')

89 Which is NOT a valid distance metric for vector indexing

in Oracle Database 23ai? Correct Answer: "Binary Search"

90 What is one type of notebook used for interacting with

Select AI?" The correct answer is:

Oracle Machine Learning (OML) Notebooks

91 You are storing 1,000 embeddings in a VECTOR column, each with 256 dimensions.
What is the approximate size of the data on disk?"

1mb

92 What does the VECTOR_NORM function

Correct Answer:
✅ The Euclidean norm or distance between the vector and the origin.

93 When generating vector embeddings outside the database, what is the most
common way to store them?

Correct Answer:
In a dedicated vector database