Files
AIclinicalresearch/backend/check_rvw_issue.ts
HaHafeng 40c2f8e148 feat(rag): Complete RAG engine implementation with pgvector
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
2026-01-21 20:24:29 +08:00

90 lines
2.5 KiB
TypeScript

import { PrismaClient } from '@prisma/client';
const prisma = new PrismaClient();
async function main() {
console.log('🔍 检查 RVW 模块问题\n');
// 1. 检查用户 user-mock-001 是否存在
console.log('1. 检查用户 "user-mock-001":');
const users: any[] = await prisma.$queryRaw`
SELECT id, name, email, phone, role
FROM platform_schema.users
WHERE id = 'user-mock-001' OR email LIKE '%mock%' OR name LIKE '%mock%'
`;
if (users.length === 0) {
console.log(' ❌ 用户 "user-mock-001" 不存在!');
} else {
console.log(' ✅ 找到用户:');
users.forEach(u => console.log(` ${u.id}: ${u.name} (${u.email || u.phone})`));
}
// 2. 检查所有用户
console.log('\n2. 当前所有用户:');
const allUsers: any[] = await prisma.$queryRaw`
SELECT id, name, phone, role FROM platform_schema.users
`;
allUsers.forEach(u => console.log(` - ${u.id}: ${u.name} (${u.phone}) [${u.role}]`));
// 3. 检查 rvw_schema.review_tasks 表结构
console.log('\n3. rvw_schema.review_tasks 表结构:');
const cols: any[] = await prisma.$queryRaw`
SELECT column_name, data_type, is_nullable, column_default
FROM information_schema.columns
WHERE table_schema = 'rvw_schema' AND table_name = 'review_tasks'
ORDER BY ordinal_position
`;
cols.forEach(c => {
const nullable = c.is_nullable === 'YES' ? 'NULLABLE' : 'NOT NULL';
console.log(` ${c.column_name}: ${c.data_type} ${nullable}`);
});
// 4. 检查外键约束
console.log('\n4. review_tasks 的外键约束:');
const fks: any[] = await prisma.$queryRaw`
SELECT
tc.constraint_name,
kcu.column_name,
ccu.table_schema AS foreign_table_schema,
ccu.table_name AS foreign_table_name,
ccu.column_name AS foreign_column_name
FROM information_schema.table_constraints AS tc
JOIN information_schema.key_column_usage AS kcu
ON tc.constraint_name = kcu.constraint_name
JOIN information_schema.constraint_column_usage AS ccu
ON ccu.constraint_name = tc.constraint_name
WHERE tc.constraint_type = 'FOREIGN KEY'
AND tc.table_schema = 'rvw_schema'
AND tc.table_name = 'review_tasks'
`;
if (fks.length === 0) {
console.log(' 无外键约束');
} else {
fks.forEach(fk => {
console.log(` ${fk.column_name} -> ${fk.foreign_table_schema}.${fk.foreign_table_name}.${fk.foreign_column_name}`);
});
}
}
main()
.catch(console.error)
.finally(() => prisma.$disconnect());