- Add platform infrastructure chapter to frontend-backend architecture design - Update system architecture document with 6 new infrastructure modules - Update AI onboarding guide with infrastructure overview - Link to backend/src/common/README.md for detailed usage guide Key Updates: - Storage service (LocalAdapter + OSSAdapter) - Logging system (Winston + JSON format) - Cache service (Memory + Redis) - Async job queue (Memory + Database) - Health check endpoints - Monitoring metrics - Database connection pool - Environment config management All modules support zero-code switching between local and cloud environments. Related: #Platform-Infrastructure
13 KiB
13 KiB
[AI对接] LLM网关快速上下文
阅读时间: 5分钟 | Token消耗: ~2000 tokens
层级: L2 | 优先级: P0 ⭐⭐⭐⭐⭐
前置阅读: 02-通用能力层/[AI对接] 通用能力快速上下文.md
📋 能力定位
LLM大模型网关是整个平台的AI调用中枢,是商业模式的技术基础。
为什么是P0优先级:
- 71%的业务模块依赖(5个模块:AIA、ASL、PKB、DC、RVW)
- ASL模块开发的前置条件
- 商业模式的技术基础(Feature Flag + 成本控制)
状态: ❌ 待实现
建议时间: ASL Week 1(Day 1-3)同步开发
🎯 核心功能
1. 根据用户版本选择模型 ⭐⭐⭐⭐⭐
商业价值:
专业版(¥99/月)→ DeepSeek-V3(¥1/百万tokens)
高级版(¥299/月)→ DeepSeek + Qwen3-72B(¥5/百万tokens)
旗舰版(¥999/月)→ 全部模型(含Claude/GPT)
实现方式:
// 查询用户Feature Flag
const userFlags = await featureFlagService.getUserFlags(userId);
// 根据Feature Flag选择可用模型
if (requestModel === 'claude-3.5' && !userFlags.includes('claude_access')) {
throw new Error('您的套餐不支持Claude模型,请升级到旗舰版');
}
// 或自动降级
if (!userFlags.includes('claude_access')) {
model = 'deepseek-v3'; // 自动降级到DeepSeek
}
2. 统一调用接口 ⭐⭐⭐⭐⭐
问题: 不同LLM厂商API格式不同
- OpenAI格式
- Anthropic格式
- 国产大模型格式(DeepSeek、Qwen)
解决方案: 统一接口 + 适配器模式
// 业务模块统一调用
const response = await llmGateway.chat({
userId: 'user123',
modelType: 'deepseek-v3', // 或 'qwen3', 'claude-3.5'
messages: [
{ role: 'user', content: '帮我分析这篇文献...' }
],
stream: false
});
// LLM网关内部:
// 1. 检查用户权限(Feature Flag)
// 2. 检查配额
// 3. 选择对应的适配器
// 4. 调用API
// 5. 记录成本
// 6. 返回统一格式
3. 成本控制 ⭐⭐⭐⭐
核心需求:
- 每个用户有月度配额
- 超出配额自动限流
- 实时成本统计
实现:
// 调用前检查配额
async function checkQuota(userId: string): Promise<boolean> {
const usage = await getMonthlyUsage(userId);
const quota = await getUserQuota(userId);
if (usage.tokenCount >= quota.maxTokens) {
throw new QuotaExceededError('您的月度配额已用完,请升级套餐');
}
return true;
}
// 调用后记录成本
async function recordUsage(userId: string, usage: {
modelType: string;
tokenCount: number;
cost: number;
}) {
await db.llmUsage.create({
userId,
modelType,
inputTokens: usage.tokenCount,
cost: usage.cost,
timestamp: new Date()
});
}
4. 流式/非流式统一处理 ⭐⭐⭐
场景:
- AIA智能问答 → 需要流式输出(实时显示)
- ASL文献筛选 → 非流式(批量处理)
统一接口:
interface ChatOptions {
userId: string;
modelType: ModelType;
messages: Message[];
stream: boolean; // 是否流式输出
temperature?: number;
maxTokens?: number;
}
// 流式
const stream = await llmGateway.chat({ ...options, stream: true });
for await (const chunk of stream) {
console.log(chunk.content);
}
// 非流式
const response = await llmGateway.chat({ ...options, stream: false });
console.log(response.content);
🏗️ 技术架构
目录结构
backend/src/modules/llm-gateway/
├── controllers/
│ └── llmController.ts # HTTP接口
├── services/
│ ├── llmGatewayService.ts # 核心服务 ⭐
│ ├── featureFlagService.ts # Feature Flag查询
│ ├── quotaService.ts # 配额管理
│ └── usageService.ts # 使用统计
├── adapters/ # 适配器模式 ⭐
│ ├── baseAdapter.ts
│ ├── deepseekAdapter.ts
│ ├── qwenAdapter.ts
│ ├── claudeAdapter.ts
│ └── openaiAdapter.ts
├── types/
│ └── llm.types.ts
└── routes/
└── llmRoutes.ts
核心类设计
1. LLMGatewayService(核心)
class LLMGatewayService {
private adapters: Map<ModelType, BaseLLMAdapter>;
async chat(options: ChatOptions): Promise<ChatResponse | AsyncIterator> {
// 1. 验证用户权限(Feature Flag)
await this.checkAccess(options.userId, options.modelType);
// 2. 检查配额
await quotaService.checkQuota(options.userId);
// 3. 选择适配器
const adapter = this.adapters.get(options.modelType);
// 4. 调用LLM API
const response = await adapter.chat(options);
// 5. 记录使用量
await usageService.record({
userId: options.userId,
modelType: options.modelType,
tokenCount: response.tokenUsage,
cost: this.calculateCost(options.modelType, response.tokenUsage)
});
// 6. 返回结果
return response;
}
private calculateCost(modelType: ModelType, tokens: number): number {
const prices = {
'deepseek-v3': 0.000001, // ¥1/百万tokens
'qwen3-72b': 0.000005, // ¥5/百万tokens
'claude-3.5': 0.00003 // $15/百万tokens ≈ ¥0.0003/千tokens
};
return tokens * prices[modelType];
}
}
2. BaseLLMAdapter(适配器基类)
abstract class BaseLLMAdapter {
abstract chat(options: ChatOptions): Promise<ChatResponse>;
abstract chatStream(options: ChatOptions): AsyncIterator<ChatChunk>;
protected abstract buildRequest(options: ChatOptions): any;
protected abstract parseResponse(response: any): ChatResponse;
}
3. DeepSeekAdapter(实现示例)
class DeepSeekAdapter extends BaseLLMAdapter {
private apiKey: string;
private baseUrl = 'https://api.deepseek.com/v1';
async chat(options: ChatOptions): Promise<ChatResponse> {
const request = this.buildRequest(options);
const response = await fetch(`${this.baseUrl}/chat/completions`, {
method: 'POST',
headers: {
'Authorization': `Bearer ${this.apiKey}`,
'Content-Type': 'application/json'
},
body: JSON.stringify(request)
});
const data = await response.json();
return this.parseResponse(data);
}
protected buildRequest(options: ChatOptions) {
return {
model: 'deepseek-chat',
messages: options.messages,
temperature: options.temperature || 0.7,
max_tokens: options.maxTokens || 4096,
stream: options.stream || false
};
}
protected parseResponse(response: any): ChatResponse {
return {
content: response.choices[0].message.content,
tokenUsage: response.usage.total_tokens,
finishReason: response.choices[0].finish_reason
};
}
}
📊 数据库设计
platform_schema.llm_usage
CREATE TABLE platform_schema.llm_usage (
id SERIAL PRIMARY KEY,
user_id INTEGER REFERENCES platform_schema.users(id),
model_type VARCHAR(50) NOT NULL, -- 'deepseek-v3', 'qwen3', 'claude-3.5'
input_tokens INTEGER NOT NULL,
output_tokens INTEGER NOT NULL,
total_tokens INTEGER NOT NULL,
cost DECIMAL(10, 6) NOT NULL, -- 实际成本(人民币)
request_id VARCHAR(100), -- LLM API返回的request_id
module VARCHAR(50), -- 哪个模块调用的:'AIA', 'ASL', 'PKB'等
created_at TIMESTAMP DEFAULT NOW(),
INDEX idx_user_created (user_id, created_at),
INDEX idx_module (module)
);
platform_schema.llm_quotas
CREATE TABLE platform_schema.llm_quotas (
id SERIAL PRIMARY KEY,
user_id INTEGER REFERENCES platform_schema.users(id) UNIQUE,
monthly_token_limit INTEGER NOT NULL, -- 月度token配额
monthly_cost_limit DECIMAL(10, 2), -- 月度成本上限(可选)
reset_day INTEGER DEFAULT 1, -- 每月重置日期(1-28)
created_at TIMESTAMP DEFAULT NOW(),
updated_at TIMESTAMP DEFAULT NOW()
);
📋 API端点
1. 聊天接口(非流式)
POST /api/v1/llm/chat
Request:
{
"modelType": "deepseek-v3",
"messages": [
{ "role": "user", "content": "分析这篇文献..." }
],
"temperature": 0.7,
"maxTokens": 4096
}
Response:
{
"content": "根据文献内容分析...",
"tokenUsage": {
"input": 150,
"output": 500,
"total": 650
},
"cost": 0.00065,
"modelType": "deepseek-v3"
}
2. 聊天接口(流式)
POST /api/v1/llm/chat/stream
Request: 同上 + "stream": true
Response: Server-Sent Events (SSE)
data: {"chunk": "根据", "tokenUsage": 1}
data: {"chunk": "文献", "tokenUsage": 1}
...
data: {"done": true, "totalTokens": 650, "cost": 0.00065}
3. 查询配额
GET /api/v1/llm/quota
Response:
{
"monthlyLimit": 1000000,
"used": 245000,
"remaining": 755000,
"resetDate": "2025-12-01"
}
4. 使用统计
GET /api/v1/llm/usage?startDate=2025-11-01&endDate=2025-11-30
Response:
{
"totalTokens": 245000,
"totalCost": 1.23,
"byModel": {
"deepseek-v3": { "tokens": 200000, "cost": 0.20 },
"qwen3-72b": { "tokens": 45000, "cost": 0.23 }
},
"byModule": {
"AIA": 100000,
"ASL": 120000,
"PKB": 25000
}
}
⚠️ 关键技术难点
1. 流式输出的实现
技术方案: Server-Sent Events (SSE)
// 后端(Fastify)
app.post('/api/v1/llm/chat/stream', async (req, reply) => {
reply.raw.setHeader('Content-Type', 'text/event-stream');
reply.raw.setHeader('Cache-Control', 'no-cache');
reply.raw.setHeader('Connection', 'keep-alive');
const stream = await llmGateway.chatStream(req.body);
for await (const chunk of stream) {
reply.raw.write(`data: ${JSON.stringify(chunk)}\n\n`);
}
reply.raw.end();
});
// 前端(React)
const eventSource = new EventSource('/api/v1/llm/chat/stream');
eventSource.onmessage = (event) => {
const data = JSON.parse(event.data);
setMessages(prev => [...prev, data.chunk]);
};
2. 错误处理和重试
async function chatWithRetry(options: ChatOptions, maxRetries = 3) {
for (let i = 0; i < maxRetries; i++) {
try {
return await llmGateway.chat(options);
} catch (error) {
if (error.code === 'RATE_LIMIT' && i < maxRetries - 1) {
await sleep(2000 * (i + 1)); // 指数退避
continue;
}
throw error;
}
}
}
3. Token计数(精确计费)
问题: 不同模型的tokenizer不同
解决方案:
- 使用各厂商提供的API返回值(最准确)
- 备用方案:tiktoken库(OpenAI tokenizer)
import { encoding_for_model } from 'tiktoken';
function estimateTokens(text: string, model: string): number {
const encoder = encoding_for_model(model);
const tokens = encoder.encode(text);
encoder.free();
return tokens.length;
}
📅 开发计划(3天)
Day 1:基础架构(6-8小时)
- 创建目录结构
- 实现BaseLLMAdapter抽象类
- 实现DeepSeekAdapter
- 数据库表创建(llm_usage, llm_quotas)
- 基础API端点(非流式)
Day 2:核心功能(6-8小时)
- Feature Flag集成
- 配额检查和记录
- 实现QwenAdapter
- 错误处理和重试机制
- 单元测试
Day 3:流式输出 + 优化(6-8小时)
- 实现流式输出(SSE)
- 前端SSE接收处理
- 成本统计API
- 配额查询API
- 集成测试
- 文档完善
✅ 开发检查清单
开始前确认:
- Feature Flag表已创建(platform_schema.feature_flags)
- 用户表已有version字段(professional/premium/enterprise)
- 各LLM厂商API Key已配置
- Prisma Schema已更新
开发中:
- 每个适配器都有完整的错误处理
- 所有LLM调用都记录到llm_usage表
- 配额检查在每次调用前执行
- 流式和非流式都已测试
完成后:
- ASL模块可以成功调用LLM网关
- ADMIN可以查看用户LLM使用统计
- 配额超限会正确拒绝请求
🔗 相关文档
依赖:
- 用户与权限中心(UAM) - Feature Flag
- 运营管理端 - LLM模型管理
被依赖:
最后更新: 2025-11-06
维护人: 技术架构师
优先级: P0 ⭐⭐⭐⭐⭐