Hybrid Search (BM25 + Dense) & RRF

Hybrid Search (Sparse BM25/SPLADE + Dense Vector) combined with Reciprocal Rank Fusion (RRF) is the industry standard retrieval architecture balancing exact keyword precision with deep semantic generalization; pure dense embeddings struggle with out-of-vocabulary exact tokens (error codes, product SKUs, acronyms), while pure BM25 fails under synonyms and conceptual queries; Hybrid Search executes dual-channel parallel retrieval: querying BM25 inverted indices and HNSW dense vector databases concurrently, then fusing their disjoint result sets via rank-based Reciprocal Rank Fusion: $\text{RRF\_Score}(d) = \sum_{m \in M} \frac{1}{k + r_m(d)}$ (with smoothing constant $k=60$), effortlessly normalizing heterogeneous score scales without manual weight calibration.

Enterprise document Q&A, e-commerce catalog search, and customer ticket troubleshooting.

Pure vector search misses exact SKU identifiers while pure BM25 fails colloquial queries; hybrid RRF boosts Recall@K by 20%-35% across diverse query distributions.

Derive the RRF formula and explain why rank-based reciprocal aggregation is more robust than linear score weighting against uncalibrated scores?

How does SPLADE predict vocabulary-level sparse weights to achieve automated term expansion over static BM25?

How do modern vector databases (Qdrant/Milvus) orchestrate single-query hybrid search across sparse and dense indices natively?

Design a Query Intent Classifier that dynamically modulates the ratio between sparse and dense retrieval channels?

How to orchestrate concurrent async hybrid queries with strict 15ms latency budgets to satisfy end-to-end SLAs?