- Implement 5 core API endpoints (create task, get progress, get results, update decision, export Excel) - Add FulltextScreeningController with Zod validation (652 lines) - Implement ExcelExporter service with 4-sheet report generation (352 lines) - Register routes under /api/v1/asl/fulltext-screening - Create 31 REST Client test cases - Add automated integration test script - Fix PDF extraction fallback mechanism in LLM12FieldsService - Update API design documentation to v3.0 - Update development plan to v1.2 - Create Day 5 development record - Clean up temporary test files
13 KiB
13 KiB
CloseAI集成指南
文档版本: v1.0
创建日期: 2025-11-09
用途: 通过CloseAI代理平台访问OpenAI GPT-5和Claude-4.5
适用场景: AI智能文献双模型筛选、高质量文本生成
📋 CloseAI简介
什么是CloseAI?
CloseAI是一个API代理平台,为中国用户提供稳定的OpenAI和Claude API访问服务。
核心优势:
- ✅ 国内直连,无需科学上网
- ✅ 一个API Key同时调用OpenAI和Claude
- ✅ 兼容OpenAI SDK标准接口
- ✅ 支持最新模型(GPT-5、Claude-4.5)
官网: https://platform.openai-proxy.org
🔧 配置信息
环境变量配置
# CloseAI统一API Key
CLOSEAI_API_KEY=sk-cu0iepbXYGGx2jc7BqP6ogtSWmP6fk918qV3RUdtGC3Edlpo
# OpenAI端点
CLOSEAI_OPENAI_BASE_URL=https://api.openai-proxy.org/v1
# Claude端点
CLOSEAI_CLAUDE_BASE_URL=https://api.openai-proxy.org/anthropic
支持的模型
| 模型 | Model ID | 说明 | 适用场景 |
|---|---|---|---|
| GPT-5-Pro | gpt-5-pro |
最新GPT-5 ⭐ | 文献精准筛选、复杂推理 |
| GPT-4-Turbo | gpt-4-turbo-preview |
GPT-4高性能版 | 质量要求高的任务 |
| GPT-3.5-Turbo | gpt-3.5-turbo |
快速经济版 | 简单任务、成本优化 |
| Claude-4.5-Sonnet | claude-sonnet-4-5-20250929 |
最新Claude ⭐ | 第三方仲裁、结构化输出 |
| Claude-3.5-Sonnet | claude-3-5-sonnet-20241022 |
Claude-3.5稳定版 | 高质量文本生成 |
💻 代码集成
1. 安装依赖
npm install openai
2. 创建LLM服务类
文件位置: backend/src/common/llm/closeai.service.ts
import OpenAI from 'openai';
import { config } from '../../config/env';
export class CloseAIService {
private openaiClient: OpenAI;
private claudeClient: OpenAI;
constructor() {
// OpenAI客户端(通过CloseAI)
this.openaiClient = new OpenAI({
apiKey: config.closeaiApiKey,
baseURL: config.closeaiOpenaiBaseUrl,
});
// Claude客户端(通过CloseAI)
this.claudeClient = new OpenAI({
apiKey: config.closeaiApiKey,
baseURL: config.closeaiClaudeBaseUrl,
});
}
/**
* 调用GPT-5-Pro
*/
async chatWithGPT5(prompt: string, systemPrompt?: string) {
const messages: any[] = [];
if (systemPrompt) {
messages.push({ role: 'system', content: systemPrompt });
}
messages.push({ role: 'user', content: prompt });
const response = await this.openaiClient.chat.completions.create({
model: 'gpt-5-pro',
messages,
temperature: 0.3,
max_tokens: 2000,
});
return {
content: response.choices[0].message.content,
usage: response.usage,
model: 'gpt-5-pro',
};
}
/**
* 调用Claude-4.5-Sonnet
*/
async chatWithClaude(prompt: string, systemPrompt?: string) {
const messages: any[] = [];
if (systemPrompt) {
messages.push({ role: 'system', content: systemPrompt });
}
messages.push({ role: 'user', content: prompt });
const response = await this.claudeClient.chat.completions.create({
model: 'claude-sonnet-4-5-20250929',
messages,
temperature: 0.3,
max_tokens: 2000,
});
return {
content: response.choices[0].message.content,
usage: response.usage,
model: 'claude-sonnet-4-5-20250929',
};
}
/**
* 流式响应(GPT-5)
*/
async *streamGPT5(prompt: string, systemPrompt?: string) {
const messages: any[] = [];
if (systemPrompt) {
messages.push({ role: 'system', content: systemPrompt });
}
messages.push({ role: 'user', content: prompt });
const stream = await this.openaiClient.chat.completions.create({
model: 'gpt-5-pro',
messages,
temperature: 0.3,
max_tokens: 2000,
stream: true,
});
for await (const chunk of stream) {
const content = chunk.choices[0]?.delta?.content || '';
if (content) {
yield content;
}
}
}
}
3. 统一LLM服务(含4个模型)
文件位置: backend/src/common/llm/llm.service.ts
import OpenAI from 'openai';
import { config } from '../../config/env';
export type LLMProvider = 'deepseek' | 'gpt5' | 'claude' | 'qwen';
export class UnifiedLLMService {
private deepseek: OpenAI;
private gpt5: OpenAI;
private claude: OpenAI;
private qwen: OpenAI;
constructor() {
// DeepSeek (直连)
this.deepseek = new OpenAI({
apiKey: config.deepseekApiKey,
baseURL: config.deepseekBaseUrl,
});
// GPT-5 (通过CloseAI)
this.gpt5 = new OpenAI({
apiKey: config.closeaiApiKey,
baseURL: config.closeaiOpenaiBaseUrl,
});
// Claude (通过CloseAI)
this.claude = new OpenAI({
apiKey: config.closeaiApiKey,
baseURL: config.closeaiClaudeBaseUrl,
});
// Qwen (备用)
this.qwen = new OpenAI({
apiKey: config.dashscopeApiKey,
baseURL: 'https://dashscope.aliyuncs.com/compatible-mode/v1',
});
}
/**
* 统一调用接口
*/
async chat(
provider: LLMProvider,
prompt: string,
options?: {
systemPrompt?: string;
temperature?: number;
maxTokens?: number;
}
) {
const { systemPrompt, temperature = 0.3, maxTokens = 2000 } = options || {};
const messages: any[] = [];
if (systemPrompt) {
messages.push({ role: 'system', content: systemPrompt });
}
messages.push({ role: 'user', content: prompt });
// 选择模型
const modelMap = {
deepseek: { client: this.deepseek, model: 'deepseek-chat' },
gpt5: { client: this.gpt5, model: 'gpt-5-pro' },
claude: { client: this.claude, model: 'claude-sonnet-4-5-20250929' },
qwen: { client: this.qwen, model: 'qwen-max' },
};
const { client, model } = modelMap[provider];
const response = await client.chat.completions.create({
model,
messages,
temperature,
max_tokens: maxTokens,
});
return {
content: response.choices[0].message.content || '',
usage: response.usage,
model,
provider,
};
}
}
🎯 AI智能文献应用场景
场景1:双模型对比筛选(推荐)⭐
策略: DeepSeek(快速初筛) + GPT-5(质量复核)
export class LiteratureScreeningService {
private llm: UnifiedLLMService;
constructor() {
this.llm = new UnifiedLLMService();
}
/**
* 双模型文献筛选
*/
async screenLiterature(title: string, abstract: string, picoConfig: any) {
const prompt = `
请根据以下PICO标准,判断这篇文献是否应该纳入:
**PICO标准:**
- Population: ${picoConfig.population}
- Intervention: ${picoConfig.intervention}
- Comparison: ${picoConfig.comparison}
- Outcome: ${picoConfig.outcome}
**文献信息:**
标题:${title}
摘要:${abstract}
请输出JSON格式:
{
"decision": "include/exclude/uncertain",
"reason": "判断理由",
"confidence": 0.0-1.0
}
`;
// 并行调用两个模型
const [deepseekResult, gpt5Result] = await Promise.all([
this.llm.chat('deepseek', prompt),
this.llm.chat('gpt5', prompt),
]);
// 解析结果
const deepseekDecision = JSON.parse(deepseekResult.content);
const gpt5Decision = JSON.parse(gpt5Result.content);
// 如果两个模型一致,直接采纳
if (deepseekDecision.decision === gpt5Decision.decision) {
return {
finalDecision: deepseekDecision.decision,
consensus: 'high',
models: [deepseekDecision, gpt5Decision],
};
}
// 如果不一致,返回双方意见,待人工复核
return {
finalDecision: 'uncertain',
consensus: 'low',
models: [deepseekDecision, gpt5Decision],
needManualReview: true,
};
}
}
场景2:三模型共识仲裁
策略: 当两个模型冲突时,启用Claude作为第三方仲裁
async screenWithArbitration(title: string, abstract: string, picoConfig: any) {
// 第一轮:双模型筛选
const initialScreen = await this.screenLiterature(title, abstract, picoConfig);
// 如果一致,直接返回
if (initialScreen.consensus === 'high') {
return initialScreen;
}
// 如果不一致,启用Claude仲裁
console.log('双模型结果不一致,启用Claude仲裁...');
const claudeResult = await this.llm.chat('claude', prompt);
const claudeDecision = JSON.parse(claudeResult.content);
// 三模型投票
const decisions = [
initialScreen.models[0].decision,
initialScreen.models[1].decision,
claudeDecision.decision,
];
const voteCount = {
include: decisions.filter(d => d === 'include').length,
exclude: decisions.filter(d => d === 'exclude').length,
uncertain: decisions.filter(d => d === 'uncertain').length,
};
// 多数决
const finalDecision = Object.keys(voteCount).reduce((a, b) =>
voteCount[a] > voteCount[b] ? a : b
);
return {
finalDecision,
consensus: voteCount[finalDecision] >= 2 ? 'medium' : 'low',
models: [...initialScreen.models, claudeDecision],
arbitration: true,
};
}
场景3:成本优化策略
策略: 只对不确定的结果使用GPT-5复核
async screenWithCostOptimization(title: string, abstract: string, picoConfig: any) {
// 第一轮:用DeepSeek快速初筛(便宜)
const quickScreen = await this.llm.chat('deepseek', prompt);
const quickDecision = JSON.parse(quickScreen.content);
// 如果结果明确(include或exclude且置信度>0.8),直接采纳
if (quickDecision.confidence > 0.8 && quickDecision.decision !== 'uncertain') {
return {
finalDecision: quickDecision.decision,
consensus: 'high',
models: [quickDecision],
costOptimized: true,
};
}
// 否则,用GPT-5复核
const detailedScreen = await this.llm.chat('gpt5', prompt);
const detailedDecision = JSON.parse(detailedScreen.content);
return {
finalDecision: detailedDecision.decision,
consensus: 'medium',
models: [quickDecision, detailedDecision],
costOptimized: true,
};
}
📊 性能和成本对比
模型性能对比
| 指标 | DeepSeek-V3 | GPT-5-Pro | Claude-4.5 | Qwen-Max |
|---|---|---|---|---|
| 准确率 | 85% | 95% ⭐ | 93% | 82% |
| 速度 | 快 ⭐ | 中等 | 中等 | 快 |
| 成本 | ¥0.001/1K ⭐ | ¥0.10/1K | ¥0.021/1K | ¥0.004/1K |
| 中文理解 | 优秀 ⭐ | 优秀 | 良好 | 优秀 |
| 结构化输出 | 良好 | 优秀 | 优秀 ⭐ | 良好 |
筛选1000篇文献的成本估算
策略A:只用DeepSeek
- 成本:¥20-30
- 准确率:85%
- 适用:预算有限,可接受一定误差
策略B:DeepSeek + GPT-5 双模型
- 成本:¥150-200
- 准确率:92%
- 适用:质量要求高,预算充足 ⭐ 推荐
策略C:三模型共识(20%冲突启用Claude)
- 成本:¥180-220
- 准确率:95%
- 适用:最高质量要求
策略D:成本优化(80%用DeepSeek,20%用GPT-5)
- 成本:¥50-80
- 准确率:90%
- 适用:质量和成本平衡 ⭐ 性价比最高
⚠️ 注意事项
1. API Key安全
// ❌ 错误:硬编码API Key
const client = new OpenAI({
apiKey: 'sk-cu0iepbXYGGx2jc7BqP6ogtSWmP6fk918qV3RUdtGC3Edlpo',
});
// ✅ 正确:从环境变量读取
const client = new OpenAI({
apiKey: process.env.CLOSEAI_API_KEY,
});
2. 错误处理
async chat(provider: LLMProvider, prompt: string) {
try {
const response = await this.llm.chat(provider, prompt);
return response;
} catch (error) {
// CloseAI可能返回的错误
if (error.status === 429) {
// 速率限制
console.error('API调用速率超限,请稍后重试');
} else if (error.status === 401) {
// 认证失败
console.error('API Key无效,请检查配置');
} else if (error.status === 500) {
// 服务端错误
console.error('CloseAI服务异常,请稍后重试');
}
throw error;
}
}
3. 请求重试
async chatWithRetry(provider: LLMProvider, prompt: string, maxRetries = 3) {
for (let i = 0; i < maxRetries; i++) {
try {
return await this.llm.chat(provider, prompt);
} catch (error) {
if (i === maxRetries - 1) throw error;
// 指数退避
const delay = Math.pow(2, i) * 1000;
await new Promise(resolve => setTimeout(resolve, delay));
}
}
}
📚 相关文档
更新日志:
- 2025-11-09: 创建文档,添加CloseAI集成指南
- 支持GPT-5-Pro和Claude-4.5-Sonnet最新模型