HaHafeng
beb7f7f559
Core Components: - PDFStorageService with Dify/OSS adapters - LLM12FieldsService with Nougat-first + dual-model + 3-layer JSON parsing - PromptBuilder for dynamic prompt assembly - MedicalLogicValidator with 5 rules + fault tolerance - EvidenceChainValidator for citation integrity - ConflictDetectionService for dual-model comparison Prompt Engineering: - System Prompt (6601 chars, Section-Aware strategy) - User Prompt template (PICOS context injection) - JSON Schema (12 fields constraints) - Cochrane standards (not loaded in MVP) Key Innovations: - 3-layer JSON parsing (JSON.parse + json-repair + code block extraction) - Promise.allSettled for dual-model fault tolerance - safeGetFieldValue for robust field extraction - Mixed CN/EN token calculation Integration Tests: - integration-test.ts (full test) - quick-test.ts (quick test) - cached-result-test.ts (fault tolerance test) Documentation Updates: - Development record (Day 2-3 summary) - Quality assurance strategy (full-text screening) - Development plan (progress update) - Module status (v1.1 update) - Technical debt (10 new items) Test Results: - JSON parsing success rate: 100% - Medical logic validation: 5/5 passed - Dual-model parallel processing: OK - Cost per PDF: CNY 0.10 Files: 238 changed, 14383 insertions(+), 32 deletions(-) Docs: docs/03-涓氬姟妯″潡/ASL-AI鏅鸿兘鏂囩尞/05-寮€鍙戣褰?2025-11-22_Day2-Day3_LLM鏈嶅姟涓庨獙璇佺郴缁熷紑鍙?md
106 lines
3.4 KiB
TypeScript
106 lines
3.4 KiB
TypeScript
/**
|
||
* LLM模型验证脚本
|
||
* 用于验证实际接入的是哪个版本的模型
|
||
*/
|
||
|
||
import { LLMFactory } from '../src/common/llm/adapters/LLMFactory.js';
|
||
import { logger } from '../src/common/logging/index.js';
|
||
|
||
const TEST_PROMPT = "请用一句话简单介绍你自己，包括你的模型名称和版本。";
|
||
|
||
async function verifyModel(modelType: string, expectedModel: string) {
|
||
console.log(`\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━`);
|
||
console.log(`🔍 验证模型: ${modelType}`);
|
||
console.log(`━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━`);
|
||
|
||
try {
|
||
const adapter = LLMFactory.getAdapter(modelType as any);
|
||
console.log(`✅ 适配器创建成功`);
|
||
console.log(` 模型名称: ${adapter.modelName}`);
|
||
console.log(` 期望模型: ${expectedModel}`);
|
||
console.log(` 匹配状态: ${adapter.modelName === expectedModel ? '✅ 正确' : '❌ 不匹配'}`);
|
||
|
||
console.log(`\n🚀 发送测试请求...`);
|
||
const startTime = Date.now();
|
||
|
||
const response = await adapter.chat([
|
||
{ role: 'user', content: TEST_PROMPT }
|
||
]);
|
||
|
||
const duration = Date.now() - startTime;
|
||
|
||
console.log(`\n📊 响应结果:`);
|
||
console.log(` 实际返回模型: ${response.model}`);
|
||
console.log(` 响应时间: ${duration}ms`);
|
||
console.log(` Token使用:`);
|
||
console.log(` - 输入: ${response.usage?.promptTokens || 0}`);
|
||
console.log(` - 输出: ${response.usage?.completionTokens || 0}`);
|
||
console.log(` - 总计: ${response.usage?.totalTokens || 0}`);
|
||
console.log(`\n💬 模型回复:`);
|
||
console.log(` "${response.content}"`);
|
||
|
||
// 验证是否匹配
|
||
if (response.model === expectedModel) {
|
||
console.log(`\n✅ 验证通过！实际调用的就是 ${expectedModel}`);
|
||
return true;
|
||
} else {
|
||
console.log(`\n⚠️ 警告！期望 ${expectedModel}，实际返回 ${response.model}`);
|
||
return false;
|
||
}
|
||
|
||
} catch (error) {
|
||
console.error(`\n❌ 验证失败:`, error);
|
||
return false;
|
||
}
|
||
}
|
||
|
||
async function main() {
|
||
console.log('\n🔬 ASL模块LLM模型验证工具');
|
||
console.log('=' .repeat(60));
|
||
console.log('用途: 验证实际接入的模型版本是否正确\n');
|
||
|
||
const models = [
|
||
{ type: 'deepseek-v3', expected: 'deepseek-chat', description: 'DeepSeek-V3' },
|
||
{ type: 'qwen3-72b', expected: 'qwen-max', description: 'Qwen最新最强模型' },
|
||
];
|
||
|
||
const results: { model: string; passed: boolean }[] = [];
|
||
|
||
for (const model of models) {
|
||
const passed = await verifyModel(model.type, model.expected);
|
||
results.push({ model: model.description, passed });
|
||
|
||
// 避免API限流
|
||
await new Promise(resolve => setTimeout(resolve, 2000));
|
||
}
|
||
|
||
// 总结
|
||
console.log('\n\n' + '='.repeat(60));
|
||
console.log('📊 验证总结');
|
||
console.log('='.repeat(60));
|
||
|
||
results.forEach(r => {
|
||
console.log(`${r.passed ? '✅' : '❌'} ${r.model}: ${r.passed ? '通过' : '未通过'}`);
|
||
});
|
||
|
||
const allPassed = results.every(r => r.passed);
|
||
|
||
if (allPassed) {
|
||
console.log('\n🎉 所有模型验证通过！');
|
||
} else {
|
||
console.log('\n⚠️ 部分模型验证未通过，请检查配置！');
|
||
}
|
||
|
||
console.log('='.repeat(60) + '\n');
|
||
}
|
||
|
||
main().catch(console.error);
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|