The following table lists the exam objectives and their weightings.

Understand Vector Fundamentals        

• Use Vector Data type for storing embeddings and enabling semantic queries
• Use Vector Distance Functions and Metrics for AI vector search
• Perform DML Operations on Vectors
• Perform DDL Operations on Vectors

Using Vector Indexes        

• Create Vector Indexes to speed up AI vector search
• Use HNSW Vector Index for search queries
• Use IVF Vector Index for search queries

Performing Similarity Search        

• Perform Exact Similarity Search
• Perform approximate similarity search using Vector Indexes
• Perform Multi-Vector similarity search for multi-document search

Using Vector Embeddings        

• Generate Vector Embeddings outside the Oracle database
• Generate Vector Embeddings inside the Oracle database
• Store Vector Embeddings in Oracle database

Building a RAG Application        

• Understand Retrieval-augmented generation (RAG) concepts
• Create a RAG application using PL/SQL
• Create a RAG application using Python

Leveraging related AI capabilities        

• Use Exadata AI Storage to accelerate AI vector search
• Use Select AI with Autonomous to query data using natural language prompts
• Use SQL Loader for loading vector data
• Use Oracle Data Pump for loading and unloading vector data