Prepare for AI engineer and Forward Deployed Engineer (FDE) interviews with free topic questions, matched source answers, foundation practice, and customer scenarios. All questions and answers are in English, with original source numbers preserved.
Explain the concept aloud, reveal the reference answer, and use the linked lab to try it yourself.
20 questions · Showing 1–10
Beginner · RAG & retrieval01
How should you choose chunk size?
Reveal reference answer
Start with the smallest passage that keeps a representative answer complete. Test those passages against a question set and the model input limit, then compare retrieval and answer quality.
Watch for: A character limit is not a token limit, and one size does not suit every document.
Overlap repeats boundary text so a fact split between adjacent chunks may remain available. Measure whether this improves evidence coverage enough to justify the added storage and context.
Watch for: Overlap does not guarantee that a distant exception travels with its rule.
Search small child passages for a precise match, then attach a bounded parent section for context. Keep the child location so the reader can verify the specific evidence.
Watch for: Returning an entire manual as the parent can erase the context savings.
Keep document ID, version, section or page, and the access scope required by the application. These fields support updates, filtering, and traceable citations.
Watch for: A sequential chunk number alone may change after the source is edited.
Use questions requiring a single fact, a rule with an exception, and information across a boundary. Inspect the actual chunks before measuring retrieval and final answers.
Watch for: A readable chunk is not proof that a retriever will select it.
They can find complementary evidence: exact identifiers matter for keyword matches, while meaning-based retrieval can help with paraphrases. Evaluate their combination against your own questions.
Watch for: Hybrid retrieval is not automatically better on every query.
The scales and distributions may differ, allowing one retriever to dominate. Use a calibrated combination or a rank-based method with explicit assumptions.
Watch for: A score of 0.8 from one system is not necessarily comparable to 0.8 from another.
Fusion merges candidate orderings. A reranker evaluates candidate relevance to the query with another scoring procedure. You may fuse first and rerank the resulting shortlist.
Watch for: A reranker cannot recover evidence absent from its candidate set.
Use stable document or passage IDs, deduplicate within each result list, then merge cross-list contributions. Also inspect near-duplicate passages before constructing the final context.
Watch for: Deduplicating unrelated passages only because their titles match can remove evidence.