← All parts of this equation

Equation 2 · Part 4 · Building Production RAG: An Advanced Technical Guide

Symbol hats_dense

shybrid(d)=α s^dense(d)+(1−α) s^sparse(d),α∈[0,1]s_{\mathrm{hybrid}}(d) = \alpha \, \hat{s}_{\mathrm{dense}}(d) + (1-\alpha)\, \hat{s}_{\mathrm{sparse}}(d), \qquad \alpha \in [0, 1]
s^dense\hat{s}_{\mathrm{dense}}

What this part means

hatsds_dense is one of the signed contributions combined to compute the quantity on the left.

Its job in the formula

hatsds_dense is one of the signed contributions combined to compute the quantity on the left.

The passage around this formula

The fix is hybrid retrieval: combine a lexical score, which is exact-match strong and semantically blind, with a dense score, which is semantically strong and exact-match weak. The complication is that the two scores are not on comparable scales. Pinecone’s documentation states the problem directly: dense vectors scored by inner product against unit-normalized embeddings fall roughly in the range [-1, 1] , while BM25-style sparse scores are unbounded positive values that grow with term frequency, document length, and vocabulary rarity, so that “without explicit weighting, the sparse component dominates the combined score” [ 4 ] . The documented fix is a convex combination of normalized…

Read this part in the article →

Learn the underlying idea

A subscript is a label attached below a symbol. It often selects a time step, component, category, or member of a sequence.

Open the illustrated subscripts: which member of a family? guide →

See this notation across published equations →

Sources cited in the surrounding passage

These citations provide research context; check each source for the exact claim it supports.