1Z0-184-25 Question 101
Single answerYour analytics team wants to incorporate semantic search capabilities in an e-commerce application by generating vector embeddings for product descriptions. They decide to generate these embeddings in an environment outside the Oracle Database to offload GPU-intensive processing. After generation, the embeddings must be stored in a newly created vector-enabled table within Oracle Database. Which approach best satisfies this requirement while maintaining a streamlined and secure workflow on Oracle Cloud Infrastructure?
- A
Use Oracle Data Science on a GPU shape to generate the embeddings, store them temporarily in Object Storage, and then load them into the Oracle Database� vector-enabled table via a secure connection.
- B
Use Oracle Database In-Memory feature to automatically generate embeddings from text columns without any external service or code.
- C
Deploy MySQL HeatWave ML on an OCI VM, generate the embeddings there, and push them directly into your Oracle Database� vector table.
- D
Rely on Oracle Automatic Storage Management (ASM) to parallelize embedding generation in the same server hosting the database, guaranteeing minimal network overhead.
Show answer and explanation
Correct answer: A
Explanation
Generating vector embeddings outside the Oracle Database offloads computationally heavy tasks to a service specifically designed for machine learning workloads. Oracle Data Science is the recommended approach for custom Python and ML frameworks on GPU shapes, securely interacting with the rest of OCI (including Object Storage and the database). Refer to the Oracle Data Science documentation and Oracle Database 23c Vector Search capabilities for best practices on generating, storing, and querying embeddings.
- A. Correct.
CORRECT. By using Oracle Data Science with a GPU shape, you can run custom Python or machine learning frameworks to generate embeddings outside the database. Storing embeddings in Object Storage first and then loading them into Oracle Database ensures a secure and decoupled workflow. This approach offloads the training workload from the database, leverages OCI� managed data science environment, and preserves data integrity.
- B. Incorrect.
INCORRECT. Oracle Database In-Memory accelerates queries rather than generating vector embeddings from raw text. It does not automatically convert text data into vectors for semantic search.
- C. Incorrect.
INCORRECT. MySQL HeatWave ML is an ML solution integrated into MySQL, not Oracle Database. Generating embeddings using a MySQL-based service cannot directly populate an Oracle Database� vector table without significant custom integration and is not the recommended approach for Oracle Database workloads.
- D. Incorrect.
INCORRECT. Oracle ASM primarily manages storage for Oracle Database but does not provide a mechanism to generate vector embeddings. This method would also place a heavy computational load on the same server running the database, contrary to the goal of offloading GPU-intensive processing.