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
96 lines
2.1 KiB
TypeScript
96 lines
2.1 KiB
TypeScript
import { PrismaClient } from '@prisma/client';
|
|
|
|
const prisma = new PrismaClient();
|
|
|
|
async function getTableColumns(schema: string, tableName: string): Promise<any[]> {
|
|
return prisma.$queryRawUnsafe(`
|
|
SELECT column_name, data_type, is_nullable, column_default
|
|
FROM information_schema.columns
|
|
WHERE table_schema = '${schema}' AND table_name = '${tableName}'
|
|
ORDER BY ordinal_position
|
|
`);
|
|
}
|
|
|
|
async function main() {
|
|
console.log('🔍 DC 和 ASL 模块表结构对比\n');
|
|
console.log('=' .repeat(70));
|
|
|
|
// DC 模块的表
|
|
const dcTables = [
|
|
'dc_extraction_items',
|
|
'dc_extraction_tasks',
|
|
'dc_health_checks',
|
|
'dc_templates',
|
|
'dc_tool_c_ai_history',
|
|
'dc_tool_c_sessions'
|
|
];
|
|
|
|
// ASL 模块的表
|
|
const aslTables = [
|
|
'fulltext_screening_results',
|
|
'fulltext_screening_tasks',
|
|
'literatures',
|
|
'screening_projects',
|
|
'screening_results',
|
|
'screening_tasks'
|
|
];
|
|
|
|
console.log('\n📋 DC 模块 (dc_schema) 当前表结构:\n');
|
|
|
|
for (const table of dcTables) {
|
|
console.log(`\n--- dc_schema.${table} ---`);
|
|
try {
|
|
const cols = await getTableColumns('dc_schema', table);
|
|
if (cols.length === 0) {
|
|
console.log(' ❌ 表不存在');
|
|
} else {
|
|
cols.forEach((c: any) => {
|
|
console.log(` ${c.column_name}: ${c.data_type} ${c.is_nullable === 'NO' ? 'NOT NULL' : ''}`);
|
|
});
|
|
}
|
|
} catch (e) {
|
|
console.log(' ❌ 查询失败');
|
|
}
|
|
}
|
|
|
|
console.log('\n\n📋 ASL 模块 (asl_schema) 当前表结构:\n');
|
|
|
|
for (const table of aslTables) {
|
|
console.log(`\n--- asl_schema.${table} ---`);
|
|
try {
|
|
const cols = await getTableColumns('asl_schema', table);
|
|
if (cols.length === 0) {
|
|
console.log(' ❌ 表不存在');
|
|
} else {
|
|
cols.forEach((c: any) => {
|
|
console.log(` ${c.column_name}: ${c.data_type} ${c.is_nullable === 'NO' ? 'NOT NULL' : ''}`);
|
|
});
|
|
}
|
|
} catch (e) {
|
|
console.log(' ❌ 查询失败');
|
|
}
|
|
}
|
|
|
|
console.log('\n' + '=' .repeat(70));
|
|
}
|
|
|
|
main()
|
|
.catch(console.error)
|
|
.finally(() => prisma.$disconnect());
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|