Files
AIclinicalresearch/backend/check_db.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

65 lines
1.5 KiB
TypeScript

import { PrismaClient } from '@prisma/client';
const prisma = new PrismaClient();
async function main() {
// 查询所有 schema
const schemas = await prisma.$queryRaw`
SELECT schema_name
FROM information_schema.schemata
WHERE schema_name NOT IN ('pg_catalog', 'information_schema', 'pg_toast')
ORDER BY schema_name;
`;
console.log('\n=== 数据库中的 Schemas ===');
console.log(schemas);
// 查询每个 schema 下的表
const tables = await prisma.$queryRaw`
SELECT table_schema, table_name
FROM information_schema.tables
WHERE table_schema NOT IN ('pg_catalog', 'information_schema', 'pg_toast')
AND table_type = 'BASE TABLE'
ORDER BY table_schema, table_name;
`;
console.log('\n=== 数据库中的所有表 ===');
console.log(tables);
// 检查 platform_schema.users 的数据量
try {
const userCount = await prisma.$queryRaw`SELECT COUNT(*) as count FROM platform_schema.users;`;
console.log('\n=== platform_schema.users 数据量 ===');
console.log(userCount);
} catch (e) {
console.log('\n=== platform_schema.users 不存在或出错 ===');
}
// 检查 public.users 的数据量
try {
const publicUserCount = await prisma.$queryRaw`SELECT COUNT(*) as count FROM public.users;`;
console.log('\n=== public.users 数据量 ===');
console.log(publicUserCount);
} catch (e) {
console.log('\n=== public.users 不存在或出错 ===');
}
}
main()
.catch(console.error)
.finally(() => prisma.$disconnect());