HaHafeng
40c2f8e148
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
108 lines
1.7 KiB
PowerShell
108 lines
1.7 KiB
PowerShell
# DC模块代码恢复脚本运行器
|
||
Write-Host "==================================================================================" -ForegroundColor Cyan
|
||
Write-Host "DC模块代码恢复工具" -ForegroundColor Cyan
|
||
Write-Host "==================================================================================" -ForegroundColor Cyan
|
||
|
||
# 检查Python是否安装
|
||
try {
|
||
$pythonVersion = python --version 2>&1
|
||
Write-Host "✅ Python版本: $pythonVersion" -ForegroundColor Green
|
||
} catch {
|
||
Write-Host "❌ 错误: Python未安装或不在PATH中" -ForegroundColor Red
|
||
exit 1
|
||
}
|
||
|
||
# 运行恢复脚本
|
||
Write-Host "`n📦 开始运行恢复脚本..." -ForegroundColor Yellow
|
||
|
||
$output = python recover_dc_code.py 2>&1 | Out-String
|
||
Write-Host $output
|
||
|
||
# 保存输出到文件
|
||
$output | Out-File "recovery_output.log" -Encoding UTF8
|
||
Write-Host "`n💾 输出已保存到: recovery_output.log" -ForegroundColor Green
|
||
|
||
# 检查恢复结果
|
||
if (Test-Path "recovered_dc_code") {
|
||
Write-Host "`n✅ 恢复目录已创建!" -ForegroundColor Green
|
||
Write-Host "📁 恢复的文件:" -ForegroundColor Cyan
|
||
Get-ChildItem "recovered_dc_code" | Format-Table Name, Length, LastWriteTime
|
||
} else {
|
||
Write-Host "`n⚠️ 未创建恢复目录，可能未找到DC代码" -ForegroundColor Yellow
|
||
}
|
||
|
||
Write-Host "`n==================================================================================" -ForegroundColor Cyan
|
||
Write-Host "完成！请查看 recovered_dc_code 目录" -ForegroundColor Cyan
|
||
Write-Host "==================================================================================" -ForegroundColor Cyan
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|