We present WeSearch, a unified, model-centric retrieval framework for large-scale, continuously evolving content search. Prevailing methods assign documents fixed hierarchical Semantic IDs, implicitly assuming each document follows a single coherent semantic path-an assumption that often breaks down for multi-topic documents. WeSearch instead retrieves query-relevant clusters and then ranks atomic documents within the resulting query-specific candidate space, decoupling candidate pruning from fine-grained relevance modeling. Combined with relevance-aware training, compact document representations, and incremental index updates, this design enables weekly-or daily when needed-model refreshes. Deployed as the primary semantic retrieval path in WeChat Search alongside a lexical syntax tree, WeSearch shows consistent one-week A/B gains on corpora from hundreds of millions to billions of documents, and a one-month full-traffic A/B test confirms stable improvements of +0.68% CTR and +2.27% per-user article clicks, together with a 41% reduction in retrieval resource cost and a 19 ms reduction in graphic-text retrieval latency. WeSearch is now fully deployed in WeChat Search, serving 100% of production traffic.
Figures & tables
Figure 1: Comparison between the existing retrieval system and the proposed retrieval system. (a) The existing system combines multiple lexical and dense retrieval sources. (b) The proposed system uses model-centric retrieval as the primary semantic retrieval path and retains one syntax tree as a complementary lexical retrieval source.
Figure 2: Overview of WeSearch. Clusters first define a query-specific candidate document space, over which fine-grained document-level ranking produces the final results.
Figure 3: The offline index construction procedure.
Figure 4: Rolling mounting of fresh documents. New documents are assigned to the existing cluster space, quantized with fixed codebooks, and made visible through an atomic index update.
Figure 5: Experimental results on the Base corpus.
Clustering
Doc Memory
Recall@300
2k×1k
OPQ (32,256)
46.66%
2k×1k
OPQ (32,512)
47.10%
2k×1k
OPQ (64,256)
51.54%
10k×200
OPQ (64,256)
51.34%
2k×1k
Dense( 32 )
33.07%
Table 1: Ablation on clustering structure and document memory. a×b denotes two-level RQ-KMeans with a coarse clusters, each split into b sub-clusters. OPQ(m,K) denotes m sub-spaces with codebook size K (Sec. 3.2.2 ); Dense( 32 ) stores a 32 -dim embedding without quantization. Cluster Recall@ 10k is stable across all rows and is therefore omitted.
Method
Relevance–1
Relevance–2
Long Dwell
Effective Click
Online
0.3621
0.3087
0.4407
0.4604
WeSearch w/o features & mining
0.4072
0.3277
0.4323
0.4379
WeSearch w/o mining
0.4271
0.3865
0.4961
0.4973
WeSearch (full)
0.4344
0.3794
0.5505
0.5481
Table 2: Ablation of structured document features and training-data mining in WeSearch, measured by Recall@100. “w/o features & mining” uses only semantic embeddings and the basic relevance supervision; “w/o mining” adds structured document features; the full model further incorporates multi-source positive/negative mining.
Method
Satisfaction density
Relevance density
Online
0.1732
0.4575
WeSearch
0.1871
0.4662
WeSearch + one syntax tree
0.2088
0.4854
Table 3: Teacher-assessed high-quality result density.
Evaluation group
CTR
Base corpus
+0.27%
Expanded corpus
+0.61%
Expanded corpus with Fresh corpus
+0.53%
Long-query traffic †
+1.10%
Table 4: Relative changes in CTR in the one-week online A/B test, compared with the corresponding production baselines. The first three rows report full-traffic results under each corpus configuration. † Long-query traffic is evaluated on the Expanded corpus with Fresh corpus configuration. Bold values indicate statistically significant gains ( p<0.05 ).
Metric
Relative change
CTR
+0.68%
Dwell time †
+0.71%
Article clicks ‡
+2.27%
Table 5: Relative changes in the one-month online A/B test on the Expanded corpus with Fresh corpus under full traffic, compared with the corresponding production baseline. † Average per-user dwell time on the search results page. ‡ Per-user clicks on WeChat Official Account articles from search results. Bold values indicate statistically significant gains ( p<0.05 ).