What is the primary function of an embedding model in the context of vector search?

An embedding model in the context of vector search, such as those used in Oracle Database 23ai, is fundamentally a machine learning construct (e.g., BERT, SentenceTransformer, or an ONNX model) designed to transform raw data—typically text, but also images or other modalities—into numerical vector representations (C). These vectors, stored in the VECTOR data type, encapsulate semantic meaning in a high-dimensional space where proximity reflects similarity. For instance, the word "cat" might be mapped to a 512-dimensional vector like [0.12, -0.34, …], where its position relative to "dog" indicates relatedness. This transformation is the linchpin of vector search, enabling mathematical operations like cosine distance to find similar items.

Option A (defining schema) misattributes a database design role to the model; schema is set by DDL (e.g., CREATE TABLE with VECTOR). Option B (executing searches) confuses the model with database functions like VECTOR_DISTANCE, which use the embeddings, not create them. Option D (storing vectors) pertains to the database’s storage engine, not the model’s function—storage is handled by Oracle’s VECTOR type and indexes (e.g., HNSW). The embedding model’s role is purely generative, not operational or structural. In practice, Oracle 23ai integrates this via VECTOR_EMBEDDING, which calls the model to produce vectors, underscoring its transformative purpose. Misunderstanding this could lead to conflating data preparation with query execution, a common pitfall for beginners.