A Generative AI Engineer is designing a RAG application for answering user questions on technical regulations as they learn a new sport. What are the steps needed to build this RAG application and…

Question

Options

• AIngest documents from a source -> Index the documents and saves to Vector Search -> User
• BIngest documents from a source -> Index the documents and save to Vector Search -> User
• CIngest documents from a source -> Index the documents and save to Vector Search -> Evaluate
• DUser submits queries against an LLM -> Ingest documents from a source -> Index the

• A
  2% (1)
• B
  91% (52)
• C
  2% (1)
• D
  5% (3)

Explanation

A complete and correctly ordered RAG pipeline is: (1) Ingest documents from a source, (2) Chunk, embed, and index them into a Vector Store, (3) Accept a user query, (4) Retrieve the most relevant chunks via semantic search, (5) Pass retrieved context + query to the LLM, (6) Return the LLM's grounded answer to the user, (7) Deploy. Option A is likely missing or misordering steps. Option C swaps deployment for an evaluation-only step, which is incomplete for a production deploy. Option D reverses the pipeline entirely, querying an LLM before data has been ingested-logically impossible. Option B correctly captures the end-to-end build-and-deploy sequence.

No community discussion yet for this question.