feat(rag): dense+BM25 hybrid on MilvusClientV2, drop SDK path
Replace legacy MilvusServiceClient knowledge search/write with a single MilvusClientV2 hybrid store (BM25 function + dense ANN + RRFRanker). Use collection biz_hybrid and require knowledge reindex.
This commit is contained in:
@@ -0,0 +1,57 @@
|
||||
# Design: rag-bm25-hybrid-drop-sdk
|
||||
|
||||
## Decision: single backend
|
||||
|
||||
```text
|
||||
KnowledgeSearchPort
|
||||
-> MilvusHybridKnowledgeStore (MilvusClientV2 only)
|
||||
Write
|
||||
-> VectorIndexService -> MilvusHybridKnowledgeStore
|
||||
```
|
||||
|
||||
No `retrieval.vector-store.mode=sdk|spring|auto` for knowledge lookup.
|
||||
|
||||
## Schema (`milvus.collection`, default `biz_hybrid`)
|
||||
|
||||
| field | type | notes |
|
||||
|---|---|---|
|
||||
| id | VarChar PK | chunk id |
|
||||
| content | VarChar | original chunk body returned to agent |
|
||||
| search_text | VarChar + analyzer | BM25 input (title/path/content) |
|
||||
| sparse_vector | SparseFloatVector | BM25 function output |
|
||||
| vector | FloatVector | dense embedding |
|
||||
| metadata | JSON | docId, chunkIndex, category, kb_scope, ... |
|
||||
|
||||
Function: `BM25(search_text -> sparse_vector)`
|
||||
|
||||
Indexes:
|
||||
|
||||
- `vector`: IVF_FLAT / L2 (or COSINE if configured later)
|
||||
- `sparse_vector`: SPARSE_INVERTED_INDEX / BM25
|
||||
|
||||
## Hybrid query
|
||||
|
||||
```text
|
||||
AnnSearchReq(vector, FloatVec(queryEmbedding), topK, filter?)
|
||||
AnnSearchReq(sparse_vector, EmbeddedText(query), topK, filter?)
|
||||
HybridSearchReq + RRFRanker(k)
|
||||
```
|
||||
|
||||
Dense-compatible score for thresholds: if entity lacks dense distance, map fused score conservatively or re-use dense-only probe. Preferred: keep dense distance when available from a parallel dense search metadata; for hybrid hits use inverse-rank placeholder only in metadata and set score from optional dense sub-hit map.
|
||||
|
||||
Implementation approach for threshold stability:
|
||||
|
||||
1. Run hybridSearch for ordering/identity
|
||||
2. Build map evidenceKey -> dense L2 from a concurrent dense search (same filter/topK)
|
||||
3. Attach dense score onto fused hits when present; else maxL2 (low similarity) so weak BM25-only hits don't fake PRECISE
|
||||
|
||||
## Migration
|
||||
|
||||
- New collection name avoids mutating legacy `biz`
|
||||
- Operators re-run knowledge init / document reindex
|
||||
- Document in acceptance
|
||||
|
||||
## Drop SDK search
|
||||
|
||||
- Delete SDK search methods usage from knowledge path
|
||||
- `MilvusServiceClient` bean may remain temporarily only if other non-search utilities need it; prefer migrate write/delete fully to V2 and stop creating V1 client if unused
|
||||
Reference in New Issue
Block a user