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
65 lines
1.5 KiB
TypeScript
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());
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|