Workers AI 配置说明

# Workers AI 配置 ## wrangler.jsonc c { "name": "my-ai-worker", "main": "src/index.ts", "compatibility_date": "2024-01-01", "ai": { "binding": "AI" } } ## TypeScript bash npm install --save-dev @cloudflare/workers-types typescript interface Env { AI: Ai; } export default { async fetch(request: Request, env: Env) { const response = await env.AI.run('@cf/meta/llama-3.1-8b-instruct', { messages: [{ role: 'user', content: 'Hello' }] }); return Response.json(response); } }; ## 本地开发 bash wrangler dev --remote # AI 必需 - 不支持本地推理 ## REST API typescript const response = await fetch( `https://api.cloudflare.com/client/v4/accounts/${ACCOUNT_ID}/ai/run/@cf/meta/llama-3.1-8b-instruct`, { method: 'POST', headers: { 'Authorization': `Bearer ${API_TOKEN}` }, body: JSON.stringify({ messages: [{ role: 'user', content: 'Hello' }] }) } ); 在 dash.cloudflare.com/profile/api-tokens 创建 API 令牌 (Workers AI - 读取权限) ## SDK 兼容性 **OpenAI SDK:** typescript import OpenAI from 'openai'; const client = new OpenAI({ apiKey: env.CLOUDFLARE_API_TOKEN, baseURL: `https://api.cloudflare.com/client/v4/accounts/${env.ACCOUNT_ID}/ai/v1` }); ## 多模型设置 typescript const MODELS = { chat: '@cf/meta/llama-3.1-8b-instruct', embed: '@cf/baai/bge-base-en-v1.5', image: '@cf/stabilityai/stable-diffusion-xl-base-1.0' }; ## RAG 设置 (配合 Vectorize) c { "ai": { "binding": "AI" }, "vectorize": { "bindings": [{ "binding": "VECTORIZE", "index_name": "embeddings-index" }] } } ## 故障排除 | 错误 | 修复 | |-------|-----| | `env.AI is undefined` | 检查 wrangler.jsonc 中的 `ai` 绑定 | | 本地 AI 不工作 | 使用 `wrangler dev --remote` | | 找不到类型 'Ai' | 安装 `@cloudflare/workers-types` | | @cloudflare/ai 包错误 | 不要安装 - 使用原生绑定 |