Vercel AI SDK

Workers AI 可与 Vercel AI SDK ↗ 配合用于 JavaScript 和 TypeScript 代码库。

设置

安装 workers-ai-provider provider ↗：

npm i workers-ai-provider

yarn add workers-ai-provider

pnpm add workers-ai-provider

bun add workers-ai-provider

然后，在 Workers 项目的 Wrangler 文件中添加 AI 绑定（binding）：

[ai]
binding = "AI"

模型

AI SDK 可配置为使用任意 AI 模型。

import { createWorkersAI } from "workers-ai-provider";

const workersai = createWorkersAI({ binding: env.AI });

// Choose any model: https://developers.cloudflare.com/workers-ai/models/
const model = workersai("@cf/meta/llama-3.1-8b-instruct", {});

生成文本

选择模型后，你可以根据给定 prompt 生成文本。

import { createWorkersAI } from 'workers-ai-provider';
import { generateText } from 'ai';

type Env = {
  AI: Ai;
};

export default {
  async fetch(_: Request, env: Env) {
    const workersai = createWorkersAI({ binding: env.AI });
    const result = await generateText({
      model: workersai('@cf/meta/llama-2-7b-chat-int8'),
      prompt: 'Write a 50-word essay about hello world.',
    });

    return new Response(result.text);
  },
};

流式文本

对于较长的响应，考虑流式传输响应，在生成过程中逐步提供内容。

import { createWorkersAI } from 'workers-ai-provider';
import { streamText } from 'ai';

type Env = {
  AI: Ai;
};

export default {
  async fetch(_: Request, env: Env) {
    const workersai = createWorkersAI({ binding: env.AI });
    const result = streamText({
      model: workersai('@cf/meta/llama-2-7b-chat-int8'),
      prompt: 'Write a 50-word essay about hello world.',
    });

    return result.toTextStreamResponse({
      headers: {
        // add these headers to ensure that the
        // response is chunked and streamed
        'Content-Type': 'text/x-unknown',
        'content-encoding': 'identity',
        'transfer-encoding': 'chunked',
      },
    });
  },
};

生成结构化对象

你可以提供 Zod schema 来生成结构化 JSON 响应。

import { createWorkersAI } from 'workers-ai-provider';
import { generateObject } from 'ai';
import { z } from 'zod';

type Env = {
  AI: Ai;
};

export default {
  async fetch(_: Request, env: Env) {
    const workersai = createWorkersAI({ binding: env.AI });
    const result = await generateObject({
      model: workersai('@cf/meta/llama-3.1-8b-instruct'),
      prompt: 'Generate a Lasagna recipe',
      schema: z.object({
        recipe: z.object({
          ingredients: z.array(z.string()),
          description: z.string(),
        }),
      }),
    });

    return Response.json(result.object);
  },
};