AppliedAIPrep logoAppliedAI/Prep
← RAG & Agent System Design / 36
medium★ EssentialCohereMicrosoftElastic

How do you combine lexical (BM25) and semantic (vector) retrieval, and what is Reciprocal Rank Fusion?

Pure vector search misses exact terms; pure keyword search misses meaning. The signal is knowing why each fails alone and how to merge two rankings on incomparable scales without hand-tuning weights. Here is the answer.

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

Pure vector search misses exact terms; pure keyword search misses meaning. The signal is knowing why each fails alone and how to merge two rankings on incomparable scales without hand-tuning weights. Here is the answer.

Unlock the other 750 answers · ₹2,000 / $25Your progress and mastery stay saved · 6 months · one payment · no auto-renew
UP NEXT ON YOUR JOURNEY
Next in this trackHow do you handle multi-hop questions in RAG (questions needing several pieces of evidence)?Next in this trackHow do you keep a RAG system's knowledge fresh (index updates, stale data, changing documents)?Next in this trackWhat is late interaction (ColBERT), and how does it sit between bi-encoders and cross-encoders?
DISCUSSION · 0

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