zhuyongxin
376ad0c241
Add configurable hybrid mode on KnowledgeSearchPort that fuses dense unfiltered, dense filtered, and lexical ranks via RRF while preserving dense-compatible threshold scores. Archives Delivery 2 OpenSpec change.
1.7 KiB
1.7 KiB
Design: rag-hybrid-search-rrf
Context
- Delivery 1 archived: chunk evidenceKey, SearchPort, return caps.
- Legacy SDK path will be abandoned later; hybrid must live on SearchPort.
- Full sparse schema rebuild is operationally heavy; ship fusion first.
Decisions
D1. Hybrid = multi-path + RRF on SearchPort
When retrieval.search.mode=hybrid:
paths:
1) dense(query, filter=null) # always
2) dense(query, filter=category) # if category present
3) lexical rank over union of dense hits # sparse-lite
fuse by evidenceKey using RRF(k)
return topK fused hits
D2. RRF formula
score(d) = Σ w_i / (k + rank_i(d))
Defaults: k=60, all w_i=1.0. Optional weights via config.
D3. Score semantics
KnowledgeSearchHit.scoreremains compatible L2 distance from best dense hit for post-process thresholds.- Fused RRF score is carried in metadata (
fusedScore,fusionRanks) for trace, not as L2.
D4. Lexical path (sparse-lite)
Until BM25 schema:
- Tokenize query (simple whitespace / non-alnum split, lower-case)
- Score each candidate by term coverage over title+breadcrumb+content
- Rank candidates for RRF path only
- Not a replacement for true BM25 inverted index
D5. Serial filter retry
Lookup tool keeps low-quality unfiltered retry as safety net even in hybrid, because hybrid already includes unfiltered dense; retry remains cheap no-op when already fused well.
Non-goals now
- New Milvus collection fields
- Reindex jobs
- SDK hybridSearch API calls
Risks
- Lexical path only ranks already-recalled dense candidates → does not expand pure-term misses outside dense topK. Acceptable intermediate; true BM25 later expands recall.