1Z0-1127-25 Practice Question: Building LLM Applications with RAG and Vector Search
Which TWO of the following are best practices when implementing a RAG application using OCI OpenSearch as a vector store?
⚠ Common exam trap
A common trap is the misconception that larger embedding dimensions always improve accuracy, when in fact the dimension should match the model's output (e.g., 768 for all-MiniLM-L6-v2) and larger dimensions increase cost without proportional benefit.
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Enable approximate nearest neighbor (ANN) search for large datasets.
For large datasets, exact nearest neighbor (k-NN) search becomes computationally expensive and slow. OCI OpenSearch supports approximate nearest neighbor (ANN) search using algorithms like HNSW, which dramatically reduce latency while maintaining high recall, making it essential for production RAG applications with millions of vectors.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use a large embedding dimension (e.g., 1536) to improve accuracy.
Why it's wrong here
Larger dimensions increase storage and search latency without proportional accuracy gains.
- ✗
Set index.number_of_replicas to 0 to speed up indexing.
Why it's wrong here
Disabling replicas reduces durability and is not recommended for production.
- ✓
Enable approximate nearest neighbor (ANN) search for large datasets.
Why this is correct
ANN search significantly reduces query latency for large vector collections.
- ✗
Store the embedding vectors in the _source field to simplify retrieval.
Why it's wrong here
Storing embeddings in _source is inefficient; they should be stored as a separate field.
- ✓
Use cosine similarity as the distance metric for vector comparison.
Why this is correct
Cosine similarity is the default and recommended metric for text embeddings.
Go deeper
Related to this question
About these practice questions
Courseiva writes every 1Z0-1127-25 question from scratch — 768 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This 1Z0-1127-25 practice question is part of Courseiva's free Oracle certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the 1Z0-1127-25 exam.