feat(iit-manager): Integrate Dify knowledge base for hybrid retrieval

Completed features:
- Created Dify dataset (Dify_test0102) with 2 processed documents
- Linked test0102 project with Dify dataset ID
- Extended intent detection to recognize query_protocol intent
- Implemented queryDifyKnowledge method (semantic search Top 5)
- Integrated hybrid retrieval (REDCap data + Dify documents)
- Fixed AI hallucination bugs (intent detection + API field path)
- Developed debugging scripts
- Completed end-to-end testing (5 scenarios passed)
- Generated comprehensive documentation (600+ lines)
- Updated development plans and module status

Technical highlights:
- Single project single knowledge base architecture
- Smart routing based on user intent
- Prevent AI hallucination by injecting real data/documents
- Session memory for multi-turn conversations
- Reused LLMFactory for DeepSeek-V3 integration

Bug fixes:
- Fixed intent detection missing keywords
- Fixed Dify API response field path error

Testing: All scenarios verified in WeChat production environment

Status: Fully tested and deployed
This commit is contained in:
2026-01-04 15:44:11 +08:00
parent b47079b387
commit dfc472810b
162 changed files with 3093 additions and 62 deletions

View File

@@ -0,0 +1,105 @@
/**
* 直接查询数据库中的iit_schema.projects表结构
*/
import { PrismaClient } from '@prisma/client';
const prisma = new PrismaClient();
async function checkTableStructure() {
try {
console.log('🔍 查询 iit_schema.projects 表结构...\n');
// 1. 查询表的所有列信息
const columns = await prisma.$queryRaw<any[]>`
SELECT
column_name,
data_type,
character_maximum_length,
is_nullable,
column_default
FROM information_schema.columns
WHERE table_schema = 'iit_schema'
AND table_name = 'projects'
ORDER BY ordinal_position
`;
console.log('📋 表结构:');
console.log('='.repeat(100));
console.log(
'Column Name'.padEnd(30) +
'Data Type'.padEnd(20) +
'Nullable'.padEnd(12) +
'Default'
);
console.log('='.repeat(100));
columns.forEach(col => {
const colName = col.column_name.padEnd(30);
const dataType = (col.data_type +
(col.character_maximum_length ? `(${col.character_maximum_length})` : '')
).padEnd(20);
const nullable = (col.is_nullable === 'YES' ? 'YES' : 'NO').padEnd(12);
const defaultVal = col.column_default || '';
console.log(`${colName}${dataType}${nullable}${defaultVal}`);
});
console.log('='.repeat(100));
console.log(`\n总计: ${columns.length} 个字段\n`);
// 2. 检查是否存在 dify 相关字段
const difyColumns = columns.filter(col =>
col.column_name.toLowerCase().includes('dify')
);
if (difyColumns.length > 0) {
console.log('✅ 找到Dify相关字段');
difyColumns.forEach(col => {
console.log(` - ${col.column_name} (${col.data_type}, nullable: ${col.is_nullable})`);
});
} else {
console.log('❌ 未找到Dify相关字段');
}
console.log('');
// 3. 查询test0102项目的当前数据
console.log('📊 查询test0102项目的当前配置...\n');
const projects = await prisma.$queryRaw<any[]>`
SELECT
id,
name,
redcap_project_id,
redcap_url,
dify_dataset_id,
status,
created_at
FROM iit_schema.projects
WHERE redcap_project_id = '16'
`;
if (projects.length > 0) {
console.log('✅ test0102项目信息');
const project = projects[0];
console.log(` ID: ${project.id}`);
console.log(` 名称: ${project.name}`);
console.log(` REDCap项目ID: ${project.redcap_project_id}`);
console.log(` REDCap URL: ${project.redcap_url}`);
console.log(` Dify Dataset ID: ${project.dify_dataset_id || '(未设置)'}`);
console.log(` 状态: ${project.status}`);
console.log(` 创建时间: ${project.created_at}`);
} else {
console.log('❌ 未找到test0102项目');
}
console.log('');
} catch (error) {
console.error('❌ 查询失败:', error);
} finally {
await prisma.$disconnect();
}
}
checkTableStructure();