feat: knowledge-base code review fixes + question bank cleanup
- 🔴 searchKnowledge: 移除随机mock向量，使用真实embedding - 🔴 userId: 改为NOT NULL，清理遗留调试注释 - 🟡 文件移动事务安全：先移文件再创DB记录 - 🟡 Ollama嵌入并行化：串行→Promise.allSettled - 🟡 三处重复降级代码提取为processChunksOneByOne（~200行→30行） - 🟡 Chunk换算根据CJK比例动态调整（英4x/中2x/日2x） - 🟡 findAll添加分页参数 - 🔵 清理冗余动态import、findByIds→findBy、日文标点补充 - chore: question-bank cleanup (删除47道概念/重复/ADV题) - chore: qa-assessment-flow (Phase 1+2全量测试14项通过) - fix: shuffleArray接收返回值（三处调用点） Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Developer
@@ -0,0 +1,145 @@
|
||||
/**
|
||||
* 清理题库中不符合"简单、应用为主"的题目
|
||||
*
|
||||
* 删除规则：
|
||||
* 1. 纯概念/定义/术语类题目（考"什么是XX"而不是"遇到XX该怎么做"）
|
||||
* 2. 分类/层级背诵题（考"L1级别要求什么"等）
|
||||
* 3. 完全重复的题目
|
||||
* 4. 大量高度雷同的场景题（保留2-3个最佳，删除其余）
|
||||
*
|
||||
* 运行: node server/scripts/cleanup-question-bank.cjs
|
||||
*/
|
||||
const D = require('better-sqlite3');
|
||||
const path = require('path');
|
||||
const db = new D(path.join(__dirname, '../data/metadata.db'));
|
||||
const BANK = '984632e0-b35d-486d-9a19-27a14845db37';
|
||||
|
||||
// Helper: find item ID by partial text match
|
||||
function findIds(textLike) {
|
||||
return db.prepare("SELECT id, question_text, questionType FROM question_bank_items WHERE bank_id=? AND question_text LIKE ? ORDER BY ROWID").all(BANK, textLike);
|
||||
}
|
||||
|
||||
function del(id, reason) {
|
||||
const item = db.prepare("SELECT question_text, dimension, questionType FROM question_bank_items WHERE id=?").get(id);
|
||||
if (!item) { console.log(' ⚠️ 未找到:', id.substring(0,8)); return; }
|
||||
db.prepare("DELETE FROM question_bank_items WHERE id=?").run(id);
|
||||
console.log(` 🗑️ ${item.questionType} ${item.dimension} | ${reason} | ${item.question_text.replace(/\n/g,' ').substring(0,60)}`);
|
||||
}
|
||||
|
||||
let total = 0;
|
||||
function d(id, reason) { del(id, reason); total++; }
|
||||
|
||||
console.log('=== 清理题库 ===\n');
|
||||
|
||||
// ═══════════════ DEV_PATTERN ═══════════════
|
||||
console.log('--- DEV_PATTERN: 概念/术语题 ---');
|
||||
|
||||
// 概念定义：SDD/Vibe Coding/Flow State/L1级别
|
||||
d('0b00ac95-0000-0000-0000-000000000000', ''); // placeholder — use LIKE instead
|
||||
|
||||
// Since UUIDs are random, use text search
|
||||
const devPatternConcepts = [
|
||||
{ like: '%瀑布开发和敏捷开发的核心区别%', reason: '概念对比：瀑布vs敏捷' },
|
||||
{ like: '%规范驱动开发%核心思想%', reason: '概念定义：SDD核心思想' },
|
||||
{ like: '%Vibe Coding（氛围编程）是一种什么样的编程方式%', reason: '概念定义：Vibe Coding是什么' },
|
||||
{ like: '%Flow State（心流状态）的核心特征%', reason: '概念定义：Flow State特征' },
|
||||
{ like: '%Vibe Coding中人和AI的分工应该是%', reason: '概念定义：Vibe Coding分工' },
|
||||
{ like: '%SDD中的"规范"应该是什么样的%', reason: 'ADV概念：SDD规范' },
|
||||
{ like: '%当你一直按Tab接受AI代码却不看%', reason: 'ADV术语：Vibe Coding挂机' },
|
||||
{ like: '%"概率性"的，这意味着什么%', reason: 'ADV理论：概率性' },
|
||||
{ like: '%L1级别的AI开发范式维度要求%', reason: '分类背诵：L1级别' },
|
||||
{ like: '%请简述规范驱动开发%典型流程%', reason: '概念阐述：SDD流程' },
|
||||
{ like: '%Vibe Coding有助于接近Flow State%三个核心条件%', reason: '概念阐述：Vibe Coding+Flow State' },
|
||||
{ like: '%从确定性到概率性%这一变化对开发流程%', reason: 'ADV理论：确定性到概率性' },
|
||||
];
|
||||
|
||||
for (const c of devPatternConcepts) {
|
||||
const items = findIds(c.like);
|
||||
for (const item of items) d(item.id, c.reason);
|
||||
}
|
||||
|
||||
// DEV_PATTERN duplicates
|
||||
const devPatternDups = [
|
||||
{ like1: '%你和AI分工完成一个功能：你负责设计，AI负责编码%', like2: '%', reason: '重复：责任划分' },
|
||||
];
|
||||
const dup1 = findIds('你和AI分工完成一个功能：你负责设计，AI负责编码');
|
||||
// Keep first, delete rest
|
||||
for (let i = 1; i < dup1.length; i++) d(dup1[i].id, '重复：责任划分');
|
||||
|
||||
const dup2 = findIds('你和同事用AI一起开发一个功能。同事直接提交了AI生成的代码没有审查');
|
||||
for (let i = 1; i < dup2.length; i++) d(dup2[i].id, '重复：同事提交没审查');
|
||||
|
||||
// ═══════════════ LLM ═══════════════
|
||||
console.log('\n--- LLM: 概念/原理题 ---');
|
||||
|
||||
const llmConcepts = [
|
||||
{ like: 'AI的工作原理是根据上文猜下文%', reason: '原理：AI工作机制' },
|
||||
{ like: 'AI的"幻觉"是指AI会编造%', reason: '定义：幻觉术语' },
|
||||
{ like: 'AI训练数据的截止日期意味着%', reason: '原理：训练数据截止' },
|
||||
{ like: 'AI有时会编造看似合理但实际不存在的信息，这被称为"幻觉"%', reason: '定义：幻觉术语(重复)' },
|
||||
{ like: 'AI的知识训练数据只截止到%', reason: '原理：知识截止' },
|
||||
{ like: 'AI不知道自己的知识边界%', reason: '原理：AI知识边界' },
|
||||
{ like: '以下哪个是AI的固有问题%', reason: '列举：AI固有问题' },
|
||||
{ like: 'AI说了一段话，听起来很有道理，但你查了资料发现它说的内容不存在。这是什么现象%', reason: '定义：这是什么现象' },
|
||||
{ like: '%传统AI（判别式）和生成式AI的核心差异%', reason: 'ADV概念：判别式vs生成式' },
|
||||
{ like: 'AI的"上下文有限"是指什么问题%', reason: '定义：上下文有限' },
|
||||
];
|
||||
|
||||
for (const c of llmConcepts) {
|
||||
const items = findIds(c.like);
|
||||
for (const item of items) d(item.id, c.reason);
|
||||
}
|
||||
|
||||
// LLM MC: 11 hallucination scenario duplicates — keep 2 (第一个+搜索引擎), delete rest
|
||||
const hallMC = db.prepare("SELECT id, question_text FROM question_bank_items WHERE bank_id=? AND dimension=? AND questionType=? AND question_text LIKE '%场景%' AND (question_text LIKE '%fetchUser%' OR question_text LIKE '%validateUser%' OR question_text LIKE '%sendWelcome%') ORDER BY ROWID").all(BANK, 'LLM', 'MULTIPLE_CHOICE');
|
||||
console.log(`\n--- LLM MC: 幻觉场景重复 (${hallMC.length} total, keep 2) ---`);
|
||||
for (let i = 2; i < hallMC.length; i++) {
|
||||
d(hallMC[i].id, '重复：幻觉场景MC #' + (i+1));
|
||||
}
|
||||
|
||||
// LLM SA: 5页文档场景 duplicates — keep first (cleanest), delete rest
|
||||
const sa5 = db.prepare("SELECT id, question_text FROM question_bank_items WHERE bank_id=? AND dimension=? AND questionType=? AND question_text LIKE '%5页%' ORDER BY ROWID").all(BANK, 'LLM', 'SHORT_ANSWER');
|
||||
console.log(`\n--- LLM SA: 5页文档场景重复 (${sa5.length} total, keep 1) ---`);
|
||||
for (let i = 1; i < sa5.length; i++) {
|
||||
d(sa5[i].id, '重复：5页文档SA #' + (i+1));
|
||||
}
|
||||
|
||||
// ═══════════════ PROMPT ═══════════════
|
||||
console.log('\n--- PROMPT: 分类背诵题 ---');
|
||||
const promptConcepts = [
|
||||
{ like: 'L1级别的技术能力维度要求是什么%', reason: '分类背诵：L1维度' },
|
||||
];
|
||||
for (const c of promptConcepts) {
|
||||
const items = findIds(c.like);
|
||||
for (const item of items) d(item.id, c.reason);
|
||||
}
|
||||
|
||||
// ═══════════════ WORK_CAPABILITY ═══════════════
|
||||
console.log('\n--- WORK_CAPABILITY: 概念/分类题 ---');
|
||||
const wcConcepts = [
|
||||
{ like: '%"负责任AI"的组织原则中，"问责制"对员工的要求是什么%', reason: '概念：负责任AI问责制' },
|
||||
{ like: '%智能体（Agent）与传统聊天AI最本质的区别是什么%', reason: 'ADV概念：Agent vs 聊天AI' },
|
||||
{ like: '%智能体安全控制原则中"最小权限"是指什么%', reason: 'ADV概念：最小权限' },
|
||||
{ like: '请简述AI的四个固有问题%', reason: '列举：AI四个固有问题' },
|
||||
{ like: '数据分为"绝密""机密""公开"三个级别%', reason: '分类：数据分级' },
|
||||
{ like: '%智能体安全的四条控制原则是什么%', reason: 'ADV列举：四条控制原则' },
|
||||
];
|
||||
for (const c of wcConcepts) {
|
||||
const items = findIds(c.like);
|
||||
for (const item of items) d(item.id, c.reason);
|
||||
}
|
||||
|
||||
// WORK_CAPABILITY duplicate
|
||||
const wcDups = findIds('你正在使用AI助手分析一份包含客户信息的Excel表格');
|
||||
for (let i = 1; i < wcDups.length; i++) d(wcDups[i].id, '重复：客户Excel场景');
|
||||
|
||||
// ═══════════════ Summary ═══════════════
|
||||
const remaining = db.prepare('SELECT COUNT(*) c FROM question_bank_items WHERE bank_id=?').get(BANK);
|
||||
console.log(`\n${'═'.repeat(50)}`);
|
||||
console.log(` 删除: ${total} 题`);
|
||||
console.log(` 剩余: ${remaining.c} 题（原 ${remaining.c + total} 题）`);
|
||||
console.log(`\n 各维度分布:`);
|
||||
const byDim = db.prepare('SELECT dimension, questionType, COUNT(*) c FROM question_bank_items WHERE bank_id=? GROUP BY dimension, questionType ORDER BY dimension, questionType').all(BANK);
|
||||
byDim.forEach(r => console.log(` ${r.dimension} ${r.questionType}: ${r.c}`));
|
||||
|
||||
db.close();
|
||||
Reference in New Issue
Block a user