What is a vector embedding?
Select an option, then click Submit answer.
- ○ A numeric array that represents the semantic meaning of data such as text or images
- ○ A compressed backup of a table
- ○ A type of database index only
- ○ An encrypted password
Showing 1–10 of 10 questions
What is a vector embedding?
Select an option, then click Submit answer.
What does the VECTOR data type store in Oracle AI Database?
Select an option, then click Submit answer.
What is semantic similarity search?
Select an option, then click Submit answer.
What does VECTOR_EMBEDDING do?
Select an option, then click Submit answer.
Why import an ONNX embedding model into the database?
Select an option, then click Submit answer.
Which two are vector search foundations in Oracle AI Database? (Choose two)
Select all that apply, then click Submit answer.
What does VECTOR_DISTANCE compute?
Select an option, then click Submit answer.
Which distance metric is most commonly used for text embeddings?
Select an option, then click Submit answer.
What does the COSINE distance measure?
Select an option, then click Submit answer.
Which two factors influence HNSW index memory usage? (Choose two)
Select all that apply, then click Submit answer.
This page holds a free practice test for the Agentic AI for Oracle AI Database Professional exam (1Z0-1159-26), the exam that earns the Agentic AI for Oracle AI Database Certified Professional credential. The questions follow Oracle's official blueprint — Apply Vector Distance and Indexing is the largest topic area.
The free demo runs in the web test engine with no signup. The full practice test carries the complete question bank with an explanation for every answer.
Work through the questions in study mode first, checking the explanation for every answer — the 1Z0-1159-26 exam rewards candidates who can pick the right product feature or setting for a described situation. When your study scores are steady, switch to timed mode to rehearse the real exam's pace.
Explain Oracle AI Vector Search concepts, vector embeddings and semantic similarity search, embedding models, ONNX model import, and in-database vector generation.
Apply vector constructors, distance metrics and exact similarity search; analyse vector index options (HNSW and IVF), memory considerations and accuracy trade-offs; and apply approximate and multi-vector similarity search.
Explain the RAG workflow and Oracle AI Database support for RAG, build RAG flows with chunking, embeddings, vector search and LLM prompt generation, and implement RAG with PL/SQL packages such as DBMS_VECTOR_CHAIN and external models.
Explain Select AI Agent framework concepts, execution flow and core components, and design agent solutions using tools, tasks, agents, agent teams and built-in integrations.
Explain the Autonomous AI Database MCP Server's purpose, benefits and integration with Select AI Agent tools, and configure the MCP Server so MCP-enabled clients can use Select AI Agent tools safely.
Choose Private Agent Factory capabilities for no-code agent use cases, and analyse user roles, security controls and governance features for enterprise agent deployments.
Yes — the demo practice test on this page is free and needs no signup. The full bank of practice questions, with explanations for every answer, is in the premium practice test.
The full practice test holds 80 questions written to Oracle's official 1Z0-1159-26 blueprint; the free demo shows a 10-question sample.
Yes. The real exam is 50 questions taken in 90 minutes, with a passing score of 68%, and these practice questions follow the same topic coverage.