Explanation: 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. Reference: Oracle Database 23ai SQL Language Reference, Section on VECTOR Data Type. What is the correct order of steps for building a RAG application using PL/SQL in Oracle Database 23ai?
What is the primary role of quantization in approximate similarity search?
B. To find exact matches in BLOB data C. To retrieve the most semantically similar entries using distance metrics between different vectors D. To group vectors by their exact scores Explanation: Similarity search in Oracle 23ai (C) uses vector embeddings in VECTOR columns to retrieve entries semantically similar to a query vector, based on distance metrics (e.g., cosine, Euclidean) via functions like VECTOR_DISTANCE. This is key for AI applications like RAG, finding “close” rather than exact matches. Optimizing relational operations (A) is unrelated; similarity search is vector -specific. Exact matches in BLOBs (B) don’t leverage vector semantics. Grouping by scores (D) is a post - processing step, not the primary purpose. Oracle’s documentation defines similarity search as retrieving semantically proximate vectors. Reference: Oracle Database 23ai AI Vector Search Guide, Section on Similarity Search. What is the advantage of using Euclidean Squared Distance rather than Euclidean Distance in similarity search queries?
D. Approximate similarity search with IVF indexing and target accuracy of 70% Explanation: To prioritize accuracy over speed, exact similarity search with a full table scan (C) computes distances between the query vector and all stored vectors, guaranteeing 100% recall without approximation trade - offs. HNSW with 70% target accuracy (A) and IVF with 70% (D) are approximate methods, sacrificing accuracy for speed via indexing (e.g., probing fewer neighbors). Multivector search (B) isn’t a standard Oracle 23ai term; partitioning aids scale, not accuracy. Exact search, though slower, ensures maximum accuracy, as per Oracle’s vector search options. Reference: Oracle Database 23ai AI Vector Search Guide, Section on Exact vs. Approximate Search. What is the significance of splitting text into chunks in the process of loading data into Oracle AI Vector Search?
The VECTOR_DISTANCE function in Oracle 23ai (D) computes the distance between two vectors using a specified metric (e.g., COSINE, EUCLIDEAN), enabling similarity search by quantifying proximity. It doesn’t fetch exact matches (A); it measures similarity. Index creation (B) is handled by CREATE INDEX, not this function. Grouping (C) requires additional SQL (e.g., GROUP BY), not VECTOR_DISTANCE’s role. Oracle’s SQL reference defines it as the core tool for distance calculation in vector queries. Reference: Oracle Database 23ai SQL Language Reference, Section on VECTOR_DISTANCE. 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?
Explanation: The VECTOR_EMBEDDING function in Oracle 23ai (D) generates a vector embedding from input data (e.g., text) using a specified model (e.g., ONNX), producing a single VECTOR -type output for similarity search or AI tasks. It doesn’t calculate dimensions (A); VECTOR_DIMENSION_COUNT does that. It doesn’t compute distances (B); VECTOR_DISTANCE is for that. It doesn’t serialize vectors (C); VECTOR_SERIALIZE handles serialization. Oracle’s documentation positions VECTOR_EMBEDDING as the core function for in -database embedding creation, central to vector search workflows. Reference: Oracle Database 23ai SQL Language Reference, Section on VECTOR_EMBEDDING. What is a key characteristic of HNSW vector indexes?
