These are RAG questions of the kind Wipro actually asks — the patterns that keep coming back in Wipro's AI project interviews, where what matters is applying RAG sensibly for clients rather than research depth. Treat this page as a mock interview: say every answer out loud before revealing it. If one surprises you, the lesson behind it is linked at the bottom.
Wipro RAG concept questions
What is a vector database and what does it store for a RAG application?
Asked in
Difference between keyword search and semantic search — and which would you use for a product catalogue?
Asked in
Name three advantages of RAG over asking an LLM directly, and one disadvantage.
Asked in
Wipro RAG applied & hands-on questions
Compare, with rough numbers, sending a 60,000-token handbook in every prompt versus RAG sending 2,500 tokens of retrieved context, at 5,000 queries/day and ₹0.010 per 1K input tokens.
Asked in
How to use this page: Wipro rarely asks something you've never seen — they ask a standard RAG concept and then push one level deeper ("why?", "what would you do if..."). Master the concept in the RAG course lessons, and the follow-up stops being scary.
Keep practising: What Is RAG?, Chunking, Retrieval Techniques and Evaluating RAG cover what most Wipro RAG rounds test — and the Wipro exam guide covers the rest of their selection process.