Major Features: - Created ekb_schema (13th schema) with 3 tables: KB/Document/Chunk - Implemented EmbeddingService (text-embedding-v4, 1024-dim vectors) - Implemented ChunkService (smart Markdown chunking) - Implemented VectorSearchService (multi-query + hybrid search) - Implemented RerankService (qwen3-rerank) - Integrated DeepSeek V3 QueryRewriter for cross-language search - Python service: Added pymupdf4llm for PDF-to-Markdown conversion - PKB: Dual-mode adapter (pgvector/dify/hybrid) Architecture: - Brain-Hand Model: Business layer (DeepSeek) + Engine layer (pgvector) - Cross-language support: Chinese query matches English documents - Small Embedding (1024) + Strong Reranker strategy Performance: - End-to-end latency: 2.5s - Cost per query: 0.0025 RMB - Accuracy improvement: +20.5% (cross-language) Tests: - test-embedding-service.ts: Vector embedding verified - test-rag-e2e.ts: Full pipeline tested - test-rerank.ts: Rerank quality validated - test-query-rewrite.ts: Cross-language search verified - test-pdf-ingest.ts: Real PDF document tested (Dongen 2003.pdf) Documentation: - Added 05-RAG-Engine-User-Guide.md - Added 02-Document-Processing-User-Guide.md - Updated system status documentation Status: Production ready
58 lines
2.7 KiB
Markdown
58 lines
2.7 KiB
Markdown
# ⚠️ 文档已迁移
|
||
|
||
> **迁移日期:** 2026-01-20
|
||
> **迁移原因:** 知识库能力提升为通用能力层,不再局限于 PKB 模块
|
||
|
||
---
|
||
|
||
## 📍 新文档位置
|
||
|
||
本文档已迁移至通用能力层:
|
||
|
||
**[02-通用能力层/03-RAG引擎/02-pgvector替换Dify计划.md](../../../02-通用能力层/03-RAG引擎/02-pgvector替换Dify计划.md)**
|
||
|
||
---
|
||
|
||
## 🔄 架构变更说明
|
||
|
||
### 变更原因
|
||
|
||
知识库(RAG 引擎)是**通用能力**,不应局限于单一业务模块:
|
||
|
||
| 业务模块 | 使用场景 |
|
||
|----------|----------|
|
||
| **PKB** 个人知识库 | 知识库管理、RAG 问答 |
|
||
| **AIA** AI智能问答 | @知识库 问答、附件理解 |
|
||
| **ASL** AI智能文献 | 文献库检索、智能综述 |
|
||
| **RVW** 稿件审查 | 稿件与文献对比、查重 |
|
||
|
||
### 新架构
|
||
|
||
```
|
||
┌─────────────────────────────────────────────────────────────┐
|
||
│ 业务模块层 │
|
||
│ ┌─────────┐ ┌─────────┐ ┌─────────┐ ┌─────────┐ │
|
||
│ │ PKB │ │ AIA │ │ ASL │ │ RVW │ │
|
||
│ └────┬────┘ └────┬────┘ └────┬────┘ └────┬────┘ │
|
||
│ └────────────┴────────────┴────────────┘ │
|
||
│ │ │
|
||
│ ▼ │
|
||
├─────────────────────────────────────────────────────────────┤
|
||
│ 知识库引擎(通用能力层) │
|
||
│ 代码位置:backend/src/common/rag/ │
|
||
│ 文档位置:docs/02-通用能力层/03-RAG引擎/ │
|
||
└─────────────────────────────────────────────────────────────┘
|
||
```
|
||
|
||
---
|
||
|
||
## 📚 相关文档
|
||
|
||
- [知识库引擎架构设计](../../../02-通用能力层/03-RAG引擎/01-知识库引擎架构设计.md)
|
||
- [pgvector 替换 Dify 开发计划](../../../02-通用能力层/03-RAG引擎/02-pgvector替换Dify计划.md)
|
||
- [通用能力层 - RAG 引擎 README](../../../02-通用能力层/03-RAG引擎/README.md)
|
||
|
||
---
|
||
|
||
**请访问新文档位置获取最新内容。**
|