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
82 lines
2.2 KiB
TypeScript
82 lines
2.2 KiB
TypeScript
import { PrismaClient } from '@prisma/client';
|
|
|
|
const prisma = new PrismaClient();
|
|
|
|
async function getTableColumns(schema: string, tableName: string): Promise<any[]> {
|
|
return prisma.$queryRawUnsafe(`
|
|
SELECT column_name, data_type, is_nullable
|
|
FROM information_schema.columns
|
|
WHERE table_schema = '${schema}' AND table_name = '${tableName}'
|
|
ORDER BY ordinal_position
|
|
`);
|
|
}
|
|
|
|
async function main() {
|
|
console.log('🔍 PKB、AIA、RVW 模块表结构\n');
|
|
console.log('=' .repeat(70));
|
|
|
|
// PKB 模块的表
|
|
console.log('\n📋 PKB 模块 (pkb_schema):\n');
|
|
const pkbTables = ['batch_results', 'batch_tasks', 'documents', 'knowledge_bases', 'task_templates'];
|
|
|
|
for (const table of pkbTables) {
|
|
console.log(`\n--- pkb_schema.${table} ---`);
|
|
const cols = await getTableColumns('pkb_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} ${c.is_nullable === 'NO' ? 'NOT NULL' : ''}`));
|
|
}
|
|
}
|
|
|
|
// AIA 模块的表
|
|
console.log('\n\n📋 AIA 模块 (aia_schema):\n');
|
|
const aiaTables = ['conversations', 'general_conversations', 'general_messages', 'messages', 'projects'];
|
|
|
|
for (const table of aiaTables) {
|
|
console.log(`\n--- aia_schema.${table} ---`);
|
|
const cols = await getTableColumns('aia_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} ${c.is_nullable === 'NO' ? 'NOT NULL' : ''}`));
|
|
}
|
|
}
|
|
|
|
// RVW 模块的表
|
|
console.log('\n\n📋 RVW 模块 (rvw_schema):\n');
|
|
const rvwTables = ['review_tasks'];
|
|
|
|
for (const table of rvwTables) {
|
|
console.log(`\n--- rvw_schema.${table} ---`);
|
|
const cols = await getTableColumns('rvw_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} ${c.is_nullable === 'NO' ? 'NOT NULL' : ''}`));
|
|
}
|
|
}
|
|
|
|
console.log('\n' + '=' .repeat(70));
|
|
}
|
|
|
|
main()
|
|
.catch(console.error)
|
|
.finally(() => prisma.$disconnect());
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|