Files
SuperBizAgent-java/devflow/projects/2026-07-27-rag-chunk-evidence-identity-dedup/brief.md
T
zhuyongxin ac1f831903 feat(rag): chunk evidence identity, dedup, and search port
Preserve same-document multi-chunk evidence with evidenceKey identity,
per-document caps, retrieve-k/return-n split, and a dense KnowledgeSearchPort.
Archives Delivery 1 OpenSpec change as the foundation for hybrid retrieval.
2026-07-27 18:26:15 +08:00

725 B

Brief: rag-chunk-evidence-identity-dedup

背景

lookup_knowledge 同文档多 chunk 在后处理与投影阶段被 source 级去重吞掉。Hybrid 多路召回前必须先修证据身份与裁剪契约。

目标

  • chunk 级 evidenceKey 身份
  • 按 evidenceKey 去重 + 每文档 chunk 上限
  • retrieve-k / return-n 分离
  • Projector 保留同 source 不同 chunk
  • 薄 KnowledgeSearchPort,为 Delivery 2 hybrid 铺路

范围

Delivery 1 only(见 docs/milvus-hybrid-search-integration-checklist.md §1.1)。

非目标

hybrid schema、BM25、删 SDK、session dedup、邻块重建、模型 rerank。

分档

standard

关联 OpenSpec

openspec/changes/rag-chunk-evidence-identity-dedup