GO TO A SECTION

↑ ↓ to navigate · Enter to openExplore all sections →
FDEInterviews logo
← Coding & DSA / 59
easyOpenAICohereGlean

Compute the cosine similarity between two embedding vectors, handling the zero-vector case.

The arithmetic is three sums; the signal is what you do when a vector is all zeros and the denominator vanishes. The warm-up that gates every RAG and retrieval coding round.

Updated Aug 2026 · Grounded in real Forward Deployed Engineer interview loops and written to a senior-engineer editorial bar.

The arithmetic is three sums; the signal is what you do when a vector is all zeros and the denominator vanishes. The warm-up that gates every RAG and retrieval coding round.

20 answers per topic instead of 10, plus saved progress and bookmarks · no cardor unlock all 548 remaining answers · ₹2,000 / $25

Every answer, concept and course, every paper breakdown, all published video lessons, hands-on FDE Lab missions, Premium PDF guides and companion files, the full practice-test bank and work-sample downloads. Referral Premium excludes guide PDFs and their companion files.

6 months · One payment · No auto-renewal

Study alongside free video lessons.

Keep practising

Next in this trackParse a JSON-lines file of LLM logs and aggregate tokens generated per request.PremiumNext in this trackWrite a generator that yields fixed-size batches from a large iterator for streaming inference.PremiumNext in this trackMaintain a sliding-window average over a stream of metrics, like tokens/sec.Premium
FEDITOR'S NOTE

Interviewers watch for two things: the dimension-mismatch guard and the zero-vector branch. A candidate who returns NaN on a zero vector and shrugs has shipped the bug that later poisons a whole retrieval ranking, because NaN sorts unpredictably. The cleaner instinct, returning 0.0 for a degenerate vector, is the answer they want to hear narrated.

DISCUSSION · 0

No comments yet — be the first to share your approach.