Oracle 1z0-184-25 - Oracle AI Vector Search Professional

Building a RAG application in Oracle 23ai using PL/SQL follows a logical sequence: (1) Load Document (e.g., via SQL*Loader) into the database; (2) Split Text into Chunks (e.g., DBMS_VECTOR_CHAIN.UTL_TO_CHUNKS) to manage token limits; (3) Load ONNX Model (e.g., via DBMS_VECTOR) for embedding generation; (4) Create Embeddings (e.g., UTL_TO_EMBEDDINGS) for the chunks; (5) Vectorize Question (using the same model) when a query is received; (6) Perform Vector Search (e.g., VECTOR_DISTANCE) to find relevant chunks; (7) Generate Output (e.g., via DBMS_AI with an LLM). Option B matches this flow. A starts with the model prematurely. C prioritizes the question incorrectly. D is close but loads the model too early. Oracle’s RAG workflow documentation outlines this document-first approach.

Oracle Database 23ai imposes restrictions on DDL operations for tables with VECTOR columns to preserve data integrity. CTAS (A) is permitted, as it copies the VECTOR column intact into a new table, maintaining its structure. Dropping a VECTOR column (B) is allowed via ALTER TABLE DROP COLUMN, as it simply removes the column without altering its type. Adding a new VECTOR column (D) is supported with ALTER TABLE ADD, enabling schema evolution. However, modifying an existing VECTOR column’s data type to a non-VECTOR type (C) (e.g., VARCHAR2, NUMBER) is not permitted because VECTOR is a specialized type with dimensional and format constraints (e.g., FLOAT32), and Oracle does not support direct type conversion due to potential loss of semantic meaning and structure. This restriction is documented in Oracle’s SQL reference.

Approximate similarity search (ANN) in Oracle 23ai (B) uses indexes (e.g., HNSW, IVF) to trade accuracy for speed, returning near-matches faster by not comparing all vectors. Exact search compares every vector (A), not ANN. It doesn’t guarantee 100% accuracy (C); that’s exact search. It’s faster, not slower (D), than exact search due to indexing. Oracle’s documentation defines ANN’s speed-accuracy trade-off as its hallmark.

The Vector Pool in Oracle 23ai is a dedicated SGA memory region (controlled by VECTOR_MEMORY_SIZE) for vector operations, specifically storing HNSW indexes (graph structures) and IVF index metadata (e.g., centroids) (B). This optimizes memory usage for vector search, keeping critical index data accessible for fast queries. Partitioning (A) is unrelated; that’s a tablespace feature. Longer SQL execution (C) might benefit indirectly from memory efficiency, but it’s not the purpose. Non-vector data (D) resides elsewhere (e.g., PGA, buffer cache). Oracle allocates the Vector Pool to enhance AI workloads, ensuring indexes don’t compete with other memory, a design choice reflecting vector search’s growing importance.

In Oracle Database 23ai, vector indexes (e.g., HNSW, IVF) are built with a specific distance metric (e.g., cosine, Euclidean) that defines how similarity is computed. If a query specifies a different metric (e.g., querying with Euclidean on a cosine-based index), the index cannot be used effectively, and the query fails (A) with an error, as the mismatch invalidates the index’s structure. An exact match search (B) doesn’t occur automatically; Oracle requires explicit control. The index doesn’t update itself (C), and warnings (D) are not the default behavior—errors are raised instead. Oracle’s documentation mandates metric consistency for index usage.

In Oracle Database 23ai, a VECTOR column can be defined with a specific size (e.g., VECTOR(512, FLOAT32)) or left unspecified (e.g., VECTOR). Not defining a size (D) provides flexibility during development because different embedding models (e.g., BERT, SentenceTransformer) generate vectors with varying dimensions (e.g., 768, 384) and data types (e.g., FLOAT32, INT8). This avoids locking the schema into one model, allowing experimentation. Accuracy (A) isn’t directly impacted by size definition; it depends on the model and metric. A fixed size doesn’t restrict the database to one model (B) but requires matching dimensions. Text length (C) affects tokenization, not vector dimensions. Oracle’s documentation supports undefined VECTOR columns for flexibility in AI workflows.

In Oracle 23ai, tables with VECTOR columns support standard DML operations: SELECT (A) retrieves data, UPDATE (B) modifies rows, and DELETE (C) removes rows. However, JOIN ON VECTOR columns (D) is not permitted because VECTOR isn’t a relational type for equality comparison; it’s for similarity search (e.g., via VECTOR_DISTANCE). Joins must use non-VECTOR columns. Oracle’s SQL reference restricts VECTOR to specific operations, excluding direct joins.

To add a new column to an existing table, Oracle uses the ALTER TABLE statement with the ADD clause. Option B, ALTER TABLE my_table ADD (v VECTOR(4, FLOAT32)), correctly specifies the column name "v", the VECTOR type, and its attributes (4 dimensions, FLOAT32 precision) within parentheses, aligning with Oracle’s DDL syntax for VECTOR columns. Option A uses MODIFY, which alters existing columns, not adds new ones, making it incorrect here. Option C uses UPDATE, a DML statement for updating data, not a DDL operation for schema changes. Option D omits parentheses around the VECTOR specification, which is syntactically invalid as Oracle requires dimensions and format to be enclosed. The SQL Language Reference confirms this syntax for adding VECTOR columns.

In Oracle Database 23ai, vector distance calculations are primarily handled by the VECTOR_DISTANCE function, which supports multiple metrics (e.g., COSINE, EUCLIDEAN) specified as parameters (e.g., VECTOR_DISTANCE(v1, v2, EUCLIDEAN)). However, the question implies distinct functions, a common convention in some databases or libraries, and Oracle’s documentation aligns L2_DISTANCE (B) with the Euclidean metric. L2 (Euclidean) distance is the straight-line distance between two points in vector space, computed as √∑(xi - yi)², where xi and yi are vector components. For example, for vectors [1, 2] and [4, 6], L2 distance is √((1-4)² + (2-6)²) = √(9 + 16) = 5.

Option A, L1_DISTANCE, represents Manhattan distance (∑|xi - yi|), summing absolute differences—not Euclidean. Option C, HAMMING_DISTANCE, counts differing bits, suited for binary vectors (e.g., INT8), not continuous Euclidean spaces typically used with FLOAT32 embeddings. Option D, COSINE_DISTANCE (1 - cosine similarity), measures angular separation, distinct from Euclidean’s magnitude-inclusive approach. While VECTOR_DISTANCE is the general function in 23ai, L2_DISTANCE may be an alias or a contextual shorthand in some Oracle AI examples, reflecting Euclidean’s prominence in geometric similarity tasks. Misinterpreting this could lead to choosing COSINE for spatial tasks where magnitude matters, skewing results. Oracle’s vector search framework supports Euclidean via VECTOR_DISTANCE, but B aligns with the question’s phrasing.