How E-commerce Search Retrieval Works

TRY A SEARCH

  1. 01Catalog6 demo · ~10M real
  2. 02Retrieval5 demo · ~1K · ~30 ms
  3. 03Ranking~1K → top 100
  4. 04ResultsTop 100 · ~100 ms total

Candidates for ranking

Retrieval removes 1 irrelevant item; ranking places 3 of the 5 candidates into results.

Knit walking shoe

Rank #1

Cushioned trainer

Rank #2

City sneaker

Rank #3

Trail hiking shoe

Candidate

Canvas low-top

Candidate

Coffee maker

Filtered by retrieval

Don't run a pairwise model on all 10 million products

Score every pair10M comparisons
At 100K pair scores / sec~100 sec / search
Combine three retrieval routes~30 ms
Full search, end to end~100 ms total

Map query and product into the same space

Semantic SLM and Personalization DNN both use two towers: one encodes the query, the other each product. Similar query–product meanings land close together.

  1. Two towers, one vector space Product vectors are precomputed offline; each search creates a query vector.
  2. ANN searches nearby groups It probes likely clusters or graph neighbors, not all 10M vectors.

Further reading: two-tower retrieval and ANN · vector index trade-offs.