快速入门 · Cloudflare Workers AI docs

本指南将指导你设置并部署第一个带嵌入式 function calling 的 Workers AI 项目。你将使用 Workers、Workers AI 绑定（binding）、ai-utils 包 ↗ 和大型语言模型（LLM），在 Cloudflare 全球网络上部署你的第一个 AI 驱动应用。

1. 创建带 Workers AI 的 Worker 项目

按照 Workers AI 快速入门指南执行至第 2 步。

2. 安装额外的 npm 包

接下来，在项目仓库中运行以下命令安装 Worker AI 工具包。

npm i @cloudflare/ai-utils

yarn add @cloudflare/ai-utils

pnpm add @cloudflare/ai-utils

bun add @cloudflare/ai-utils

3. 添加 Workers AI 嵌入式 function calling

将应用目录中的 index.ts 文件更新为以下代码：

index.jsjs

import { runWithTools } from "@cloudflare/ai-utils";

export default {
	async fetch(request, env, ctx) {
		// Define function
		const sum = (args) => {
			const { a, b } = args;
			return Promise.resolve((a + b).toString());
		};
		// Run AI inference with function calling
		const response = await runWithTools(
			env.AI,
			// Model with function calling support
			"@hf/nousresearch/hermes-2-pro-mistral-7b",
			{
				// Messages
				messages: [
					{
						role: "user",
						content: "What the result of 123123123 + 10343030?",
					},
				],
				// Definition of available tools the AI model can leverage
				tools: [
					{
						name: "sum",
						description: "Sum up two numbers and returns the result",
						parameters: {
							type: "object",
							properties: {
								a: { type: "number", description: "the first number" },
								b: { type: "number", description: "the second number" },
							},
							required: ["a", "b"],
						},
						// reference to previously defined function
						function: sum,
					},
				],
			},
		);
		return new Response(JSON.stringify(response));
	},
};

index.tsts

import { runWithTools } from "@cloudflare/ai-utils";

type Env = {
	AI: Ai;
};

export default {
	async fetch(request, env, ctx) {
		// Define function
		const sum = (args: { a: number; b: number }): Promise<string> => {
			const { a, b } = args;
			return Promise.resolve((a + b).toString());
		};
		// Run AI inference with function calling
		const response = await runWithTools(
			env.AI,
			// Model with function calling support
			"@hf/nousresearch/hermes-2-pro-mistral-7b",
			{
				// Messages
				messages: [
					{
						role: "user",
						content: "What the result of 123123123 + 10343030?",
					},
				],
				// Definition of available tools the AI model can leverage
				tools: [
					{
						name: "sum",
						description: "Sum up two numbers and returns the result",
						parameters: {
							type: "object",
							properties: {
								a: { type: "number", description: "the first number" },
								b: { type: "number", description: "the second number" },
							},
							required: ["a", "b"],
						},
						// reference to previously defined function
						function: sum,
					},
				],
			},
		);
		return new Response(JSON.stringify(response));
	},
} satisfies ExportedHandler<Env>;

此示例通过 import { runWithTools} from "@cloudflare/ai-utils" 导入工具，并遵循下方 API 参考。

此外，在本示例中我们定义并描述 LLM 可用于响应用户查询的 tool 列表。此处列表仅包含一个 tool，即 sum 函数。

由 runWithTools 函数抽象，将发生以下步骤：

sequenceDiagram
    participant Worker as Worker
    participant WorkersAI as Workers AI

    Worker->>+WorkersAI: Send messages, function calling prompt, and available tools
    WorkersAI->>+Worker: Select tools and arguments for function calling
    Worker-->>-Worker: Execute function
    Worker-->>+WorkersAI: Send messages, function calling prompt and function result
    WorkersAI-->>-Worker: Send response incorporating function output

ai-utils 包 也在 Github ↗ 开源。

4. 本地开发与部署

按照 Workers AI 快速入门指南的第 4 和第 5 步进行本地开发和部署。

API 参考

更多详情，请参阅 API 参考。