top k

Every LLM product tunes these knobs, and the interviewer wants to hear what each one does to the probability distribution and which setting suits which task. That includes why factual and creative tasks call for opposite settings.

Pushing top-k higher raises recall but buries the answer in noise, and a tight reranker raises precision but can discard the one chunk you needed. The signal is knowing which metric caps the system and how to move both with a retrieve-wide-then-rerank shape.

The core operation beneath every embedding/RAG retrieval, posed as a coding exercise. The signal is vectorizing the similarity, normalizing correctly, and using a partial selection (argpartition) rather than a full sort. Here is the efficient implementation and the scaling follow-up.

A classic that checks whether you reach past sorting for the right structure. The signal is the heap solution (O(n log k)), the bucket-sort O(n) trick, and how it shifts for an unbounded stream. Here is the answer.