1Z0-184-25 Question 152
Single answerYour organization has a serverless pipeline on Oracle Cloud Infrastructure (OCI) that ingests thousands of pieces of textual feedback in near real-time using OCI Streaming. The pipeline uses an Oracle Function to clean and normalize the text before storing it in OCI Object Storage for future analysis. The team wants to add immediate sentiment and key-phrase extraction without having to build and maintain a custom model. Which approach should you implement to quickly leverage advanced AI capabilities and minimize operational overhead?
- A
Invoke Oracle Cloud Infrastructure Language service APIs within the Oracle Function to perform sentiment and key-phrase analysis on the incoming text.
- B
Train a custom model in Oracle Data Science and deploy it within Oracle Functions for real-time inference on the streaming text.
- C
Migrate all text data to an Exadata Cloud Service instance and run custom SQL-based text analytics queries for sentiment detection.
- D
Set up an offline batch job in OCI Data Integration to periodically run sentiment analysis scripts on the text data stored in Object Storage.
Show answer and explanation
Correct answer: A
Explanation
To achieve immediate sentiment analysis and key-phrase extraction from real-time text data, the recommended approach is to invoke Oracle Cloud Infrastructure Language service APIs within an Oracle Function. This option requires minimal overhead, leverages pre-trained models, and integrates seamlessly with streaming data pipelines. For more details, refer to the Oracle documentation on AI Services at https://docs.oracle.com/en-us/iaas/language/. By using OCI Language, you avoid the complexity of training and maintaining custom models while still gaining advanced AI capabilities.
- A. Correct.
Correct. OCI Language service provides pre-trained APIs for sentiment and key-phrase extraction, which can be called directly from the Oracle Function. This approach requires minimal overhead and allows near real-time analysis of incoming text.
- B. Incorrect.
Incorrect. While Oracle Data Science allows you to train custom models, this option increases complexity and overhead. Maintaining and updating a custom model is more resource-intensive compared to leveraging pre-trained APIs.
- C. Incorrect.
Incorrect. Exadata Cloud Service excels at high-performance relational workloads but is not designed for real-time AI-driven sentiment analysis directly in SQL. This approach is neither streamlined nor cost-effective for the given requirements.
- D. Incorrect.
Incorrect. Scheduling a batch job in OCI Data Integration for sentiment analysis does not meet the near real-time requirement. This approach introduces delay and does not minimize operational overhead for continuous processing.