1Z0-184-25 Sample Questions & Answers
Checks your knowledge of building a retrieval-augmented generation solution, the single biggest weight, plus vector fundamentals and the VECTOR data type, creating and tuning vector indexes, exact and approximate similarity search, generating embeddings, and Select AI.
Launch the full 1Z0-184-25 simulator →Showing 6 of 12 free samples.
- Question 1Beginner
Understanding Vector Fundamentals · Vectors, embeddings and the VECTOR data type
When defining a VECTOR column in Oracle Database 23ai, an administrator uses the syntax
VECTOR(*, FLOAT32). What does the asterisk (*) indicate in this column definition?Show answer & explanation
Correct answer: D
In Oracle Database 23ai, using an asterisk (*) in the VECTOR dimension definition allows for flexible dimensions. This means the column is not constrained to a specific number of dimensions (e.g., 768 or 1536) and can store vectors of varying lengths in the same table, though all must adhere to the FLOAT32 format specified.
- Question 2Beginner
Understanding Vector Fundamentals · DDL and DML operations on vector data
A security analyst is comparing digital fingerprints represented as binary vectors (composed strictly of 0s and 1s). Which distance metric is mathematically designed to count the number of positions at which the corresponding symbols in two binary vectors are different?
Show answer & explanation
Correct answer: B
The Hamming distance metric is specifically designed for comparing binary vectors. It calculates the similarity by counting the exact number of positions where the bits differ between two vectors. It is highly efficient for hashing and fingerprinting use cases.
- Question 3Intermediate
Understanding Vector Fundamentals · Vectors, embeddings and the VECTOR data type
A developer attempts to insert a vector generated by a lightweight embedding model (768 dimensions) into a table column explicitly defined as
VECTOR(1536, FLOAT32). What will be the result of this DML operation in Oracle Database 23ai?Show answer & explanation
Correct answer: B
When a VECTOR column is defined with a specific dimension count (e.g., 1536), Oracle strictly enforces this constraint. Attempting to insert a vector with 768 dimensions will result in an immediate error because the dimensions do not match the explicit DDL definition.
- Question 4Intermediate
Understanding Vector Fundamentals · DDL and DML operations on vector data
When utilizing the
VECTOR_DISTANCEfunction with theMANHATTAN(L1) metric, how does Oracle Database 23ai mathematically calculate the distance between two vectors?Show answer & explanation
Correct answer: C
The Manhattan distance (also known as L1 norm or taxicab geometry) is calculated as the sum of the absolute differences between the corresponding components of two vectors. The square root of squared differences describes Euclidean (L2) distance.
- Question 5Intermediate
Understanding Vector Fundamentals · Vector embeddings and semantic meaning
In the context of Oracle AI Vector Search, which statement best describes the fundamental difference between traditional relational filtering and semantic similarity search?
Show answer & explanation
Correct answer: C
Traditional relational filtering (like WHERE clauses with '=' or 'LIKE') requires exact matches or specific string patterns. Semantic search uses vector embeddings to map data into a high-dimensional space, allowing the system to find conceptually similar items based on spatial proximity, even if they share no exact keywords.
- Question 6Intermediate
Using Vector Indexes · HNSW (in-memory neighbor graph) indexes
A database administrator is evaluating vector index types for a new AI application. The dataset consists of 50 million vectors, and the queries require sub-millisecond latency with the highest possible recall. The server has limited RAM (SGA/PGA) available.
Which statement accurately describes the architectural constraints of choosing an HNSW index in this scenario?
Show answer & explanation
Correct answer: C
HNSW (Hierarchical Navigable Small World) indexes provide excellent latency and recall but maintain an in-memory graph architecture. For large datasets like 50 million vectors, this graph consumes significant memory (SGA/PGA). If RAM is limited, HNSW might cause memory exhaustion or heavy swapping, making IVF a better alternative despite HNSW's superior raw performance.
graph LR A[Query Vector] --> B[In-Memory Graph Layer 2] B --> C[In-Memory Graph Layer 1] C --> D[In-Memory Graph Layer 0] D --> E[Results] style B fill:#f9f,stroke:#333,stroke-width:2px style C fill:#f9f,stroke:#333,stroke-width:2px style D fill:#f9f,stroke:#333,stroke-width:2px
Ready for the real thing?
The full 1Z0-184-25 simulator has every exam-style question, timed mode, and instant scoring.