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
59 lines
2.1 KiB
TypeScript
59 lines
2.1 KiB
TypeScript
import { PrismaClient } from '@prisma/client';
|
|
|
|
const prisma = new PrismaClient();
|
|
|
|
async function main() {
|
|
console.log('\n=== 各模块数据量检查 ===\n');
|
|
|
|
// 检查各个模块的数据
|
|
const queries = [
|
|
{ name: 'aia_schema.projects', sql: 'SELECT COUNT(*) as count FROM aia_schema.projects' },
|
|
{ name: 'aia_schema.conversations', sql: 'SELECT COUNT(*) as count FROM aia_schema.conversations' },
|
|
{ name: 'asl_schema.screening_projects', sql: 'SELECT COUNT(*) as count FROM asl_schema.screening_projects' },
|
|
{ name: 'asl_schema.literatures', sql: 'SELECT COUNT(*) as count FROM asl_schema.literatures' },
|
|
{ name: 'dc_schema.dc_templates', sql: 'SELECT COUNT(*) as count FROM dc_schema.dc_templates' },
|
|
{ name: 'dc_schema.dc_extraction_tasks', sql: 'SELECT COUNT(*) as count FROM dc_schema.dc_extraction_tasks' },
|
|
{ name: 'iit_schema.projects', sql: 'SELECT COUNT(*) as count FROM iit_schema.projects' },
|
|
{ name: 'pkb_schema.knowledge_bases', sql: 'SELECT COUNT(*) as count FROM pkb_schema.knowledge_bases' },
|
|
{ name: 'pkb_schema.documents', sql: 'SELECT COUNT(*) as count FROM pkb_schema.documents' },
|
|
{ name: 'platform_schema.users', sql: 'SELECT COUNT(*) as count FROM platform_schema.users' },
|
|
{ name: 'platform_schema.tenants', sql: 'SELECT COUNT(*) as count FROM platform_schema.tenants' },
|
|
{ name: 'platform_schema.departments', sql: 'SELECT COUNT(*) as count FROM platform_schema.departments' },
|
|
{ name: 'capability_schema.prompt_templates', sql: 'SELECT COUNT(*) as count FROM capability_schema.prompt_templates' },
|
|
];
|
|
|
|
for (const q of queries) {
|
|
try {
|
|
const result: any = await prisma.$queryRawUnsafe(q.sql);
|
|
console.log(`${q.name}: ${result[0].count} 条记录`);
|
|
} catch (e: any) {
|
|
console.log(`${q.name}: 查询失败 - ${e.message}`);
|
|
}
|
|
}
|
|
|
|
// 检查 platform_schema.users 的具体数据
|
|
console.log('\n=== platform_schema.users 详情 ===');
|
|
const users = await prisma.$queryRaw`SELECT id, name, phone, role, tenant_id FROM platform_schema.users;`;
|
|
console.log(users);
|
|
}
|
|
|
|
main()
|
|
.catch(console.error)
|
|
.finally(() => prisma.$disconnect());
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|