ai-model-wechat

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

When to use this skill

何时使用此Skill

Use this skill for calling AI models in WeChat Mini Program using

wx.cloud.extend.AI

Use it when you need to:

Integrate AI text generation in a Mini Program
Stream AI responses with callback support
Call Hunyuan models from WeChat environment

Do NOT use for:

Browser/Web apps → use
```
ai-model-web
```
skill
Node.js backend or cloud functions → use
```
ai-model-nodejs
```
skill
Image generation → use
```
ai-model-nodejs
```
skill (not available in Mini Program)
HTTP API integration → use
```
http-api
```
skill

此Skill适用于通过

wx.cloud.extend.AI

在微信小程序中调用AI模型。

适用于以下场景：

在小程序中集成AI文本生成功能
通过回调支持流式获取AI响应
在微信环境中调用Hunyuan模型

不适用于以下场景：

浏览器/网页应用 → 使用
```
ai-model-web
```
Skill
Node.js后端或云函数 → 使用
```
ai-model-nodejs
```
Skill
图像生成 → 使用
```
ai-model-nodejs
```
Skill（小程序暂不支持）
HTTP API集成 → 使用
```
http-api
```
Skill

Available Providers and Models

可用的服务商与模型

CloudBase provides these built-in providers and models:

Provider Models Recommended

Provider	Models	Recommended
`hunyuan-exp`	`hunyuan-turbos-latest` , `hunyuan-t1-latest` , `hunyuan-2.0-thinking-20251109` , `hunyuan-2.0-instruct-20251111`	✅ `hunyuan-2.0-instruct-20251111`
`deepseek`	`deepseek-r1-0528` , `deepseek-v3-0324` , `deepseek-v3.2`	✅ `deepseek-v3.2`

hunyuan-exp

hunyuan-turbos-latest

hunyuan-t1-latest

hunyuan-2.0-thinking-20251109

hunyuan-2.0-instruct-20251111

✅

hunyuan-2.0-instruct-20251111

deepseek

deepseek-r1-0528

deepseek-v3-0324

deepseek-v3.2

✅

deepseek-v3.2

CloudBase提供以下内置服务商和模型：

服务商模型推荐使用

服务商	模型	推荐使用
`hunyuan-exp`	`hunyuan-turbos-latest` , `hunyuan-t1-latest` , `hunyuan-2.0-thinking-20251109` , `hunyuan-2.0-instruct-20251111`	✅ `hunyuan-2.0-instruct-20251111`
`deepseek`	`deepseek-r1-0528` , `deepseek-v3-0324` , `deepseek-v3.2`	✅ `deepseek-v3.2`

hunyuan-exp

hunyuan-turbos-latest

hunyuan-t1-latest

hunyuan-2.0-thinking-20251109

hunyuan-2.0-instruct-20251111

✅

hunyuan-2.0-instruct-20251111

deepseek

deepseek-r1-0528

deepseek-v3-0324

deepseek-v3.2

✅

deepseek-v3.2

Prerequisites

前置条件

WeChat base library 3.7.1+
No extra SDK installation needed

微信基础库 3.7.1+
无需额外安装SDK

Initialization

初始化

// app.js
App({
  onLaunch: function() {
    wx.cloud.init({ env: "<YOUR_ENV_ID>" });
  }
})

// app.js
App({
  onLaunch: function() {
    wx.cloud.init({ env: "<YOUR_ENV_ID>" });
  }
})

generateText() - Non-streaming

generateText() - 非流式调用

⚠️ Different from JS/Node SDK: Return value is raw model response.

const model = wx.cloud.extend.AI.createModel("hunyuan-exp");

const res = await model.generateText({
  model: "hunyuan-2.0-instruct-20251111",  // Recommended model
  messages: [{ role: "user", content: "你好" }],
});

// ⚠️ Return value is RAW model response, NOT wrapped like JS/Node SDK
console.log(res.choices[0].message.content);  // Access via choices array
console.log(res.usage);                        // Token usage

⚠️ 与JS/Node SDK的区别： 返回值为模型原始响应。

const model = wx.cloud.extend.AI.createModel("hunyuan-exp");

const res = await model.generateText({
  model: "hunyuan-2.0-instruct-20251111",  // 推荐使用的模型
  messages: [{ role: "user", content: "你好" }],
});

// ⚠️ 返回值为模型原始响应，并非像JS/Node SDK那样经过包装
console.log(res.choices[0].message.content);  // 通过choices数组访问结果
console.log(res.usage);                        // 查看Token使用情况

streamText() - Streaming

streamText() - 流式调用

⚠️ Different from JS/Node SDK: Must wrap parameters in

data

object, supports callbacks.

const model = wx.cloud.extend.AI.createModel("hunyuan-exp");

// ⚠️ Parameters MUST be wrapped in `data` object
const res = await model.streamText({
  data: {                              // ⚠️ Required wrapper
    model: "hunyuan-2.0-instruct-20251111",  // Recommended model
    messages: [{ role: "user", content: "hi" }]
  },
  onText: (text) => {                  // Optional: incremental text callback
    console.log("New text:", text);
  },
  onEvent: ({ data }) => {             // Optional: raw event callback
    console.log("Event:", data);
  },
  onFinish: (fullText) => {            // Optional: completion callback
    console.log("Done:", fullText);
  }
});

// Async iteration also available
for await (let str of res.textStream) {
  console.log(str);
}

// Check for completion with eventStream
for await (let event of res.eventStream) {
  console.log(event);
  if (event.data === "[DONE]") {       // ⚠️ Check for [DONE] to stop
    break;
  }
}

⚠️ 与JS/Node SDK的区别： 必须将参数包装在

data

对象中，支持回调函数。

const model = wx.cloud.extend.AI.createModel("hunyuan-exp");

// ⚠️ 参数必须包装在`data`对象中
const res = await model.streamText({
  data: {                              // ⚠️ 必填的包装对象
    model: "hunyuan-2.0-instruct-20251111",  // 推荐使用的模型
    messages: [{ role: "user", content: "hi" }]
  },
  onText: (text) => {                  // 可选：增量文本回调
    console.log("New text:", text);
  },
  onEvent: ({ data }) => {             // 可选：原始事件回调
    console.log("Event:", data);
  },
  onFinish: (fullText) => {            // 可选：完成回调
    console.log("Done:", fullText);
  }
});

// 也支持异步迭代
for await (let str of res.textStream) {
  console.log(str);
}

// 通过eventStream检查调用是否完成
for await (let event of res.eventStream) {
  console.log(event);
  if (event.data === "[DONE]") {       // ⚠️ 检测[DONE]以停止迭代
    break;
  }
}

API Comparison: JS/Node SDK vs WeChat Mini Program

API对比：JS/Node SDK vs 微信小程序

Feature	JS/Node SDK	WeChat Mini Program
Namespace	`app.ai()`	`wx.cloud.extend.AI`
generateText params	Direct object	Direct object
generateText return	`{ text, usage, messages }`	Raw: `{ choices, usage }`
streamText params	Direct object	⚠️ Wrapped in `data: {...}`
streamText return	`{ textStream, dataStream }`	`{ textStream, eventStream }`
Callbacks	Not supported	`onText` , `onEvent` , `onFinish`
Image generation	Node SDK only	Not available

功能	JS/Node SDK	微信小程序
命名空间	`app.ai()`	`wx.cloud.extend.AI`
generateText参数	直接传入对象	直接传入对象
generateText返回值	`{ text, usage, messages }`	原始格式： `{ choices, usage }`
streamText参数	直接传入对象	⚠️ 必须包装在 `data: {...}` 中
streamText返回值	`{ textStream, dataStream }`	`{ textStream, eventStream }`
回调函数	不支持	`onText` , `onEvent` , `onFinish`
图像生成	仅Node SDK支持	暂不支持

Type Definitions

类型定义

streamText() Input

streamText() 输入参数

interface WxStreamTextInput {
  data: {                              // ⚠️ Required wrapper object
    model: string;
    messages: Array<{
      role: "user" | "system" | "assistant";
      content: string;
    }>;
  };
  onText?: (text: string) => void;     // Incremental text callback
  onEvent?: (prop: { data: string }) => void;  // Raw event callback
  onFinish?: (text: string) => void;   // Completion callback
}

interface WxStreamTextInput {
  data: {                              // ⚠️ 必填的包装对象
    model: string;
    messages: Array<{
      role: "user" | "system" | "assistant";
      content: string;
    }>;
  };
  onText?: (text: string) => void;     // 增量文本回调
  onEvent?: (prop: { data: string }) => void;  // 原始事件回调
  onFinish?: (text: string) => void;   // 完成回调
}

streamText() Return

streamText() 返回值

interface WxStreamTextResult {
  textStream: AsyncIterable<string>;   // Incremental text stream
  eventStream: AsyncIterable<{         // Raw event stream
    event?: unknown;
    id?: unknown;
    data: string;                      // "[DONE]" when complete
  }>;
}

interface WxStreamTextResult {
  textStream: AsyncIterable<string>;   // 增量文本流
  eventStream: AsyncIterable<{         // 原始事件流
    event?: unknown;
    id?: unknown;
    data: string;                      // 完成时返回"[DONE]"
  }>;
}

generateText() Return

generateText() 返回值

// Raw model response (OpenAI-compatible format)
interface WxGenerateTextResponse {
  id: string;
  object: "chat.completion";
  created: number;
  model: string;
  choices: Array<{
    index: number;
    message: {
      role: "assistant";
      content: string;
    };
    finish_reason: string;
  }>;
  usage: {
    prompt_tokens: number;
    completion_tokens: number;
    total_tokens: number;
  };
}

// 模型原始响应（兼容OpenAI格式）
interface WxGenerateTextResponse {
  id: string;
  object: "chat.completion";
  created: number;
  model: string;
  choices: Array<{
    index: number;
    message: {
      role: "assistant";
      content: string;
    };
    finish_reason: string;
  }>;
  usage: {
    prompt_tokens: number;
    completion_tokens: number;
    total_tokens: number;
  };
}

Best Practices

最佳实践

Check base library version - Ensure 3.7.1+ for AI support
Use callbacks for UI updates -
```
onText
```
is great for real-time display
Check for [DONE] - When using
```
eventStream
```
, check
```
event.data === "[DONE]"
```
to stop
Handle errors gracefully - Wrap AI calls in try/catch
Remember the
data
wrapper - streamText params must be wrapped in
```
data: {...}
```

检查基础库版本 - 确保使用3.7.1及以上版本以支持AI功能
使用回调更新UI -
```
onText
```
非常适合实时显示响应内容
检测[DONE]标识 - 使用
```
eventStream
```
时，通过
```
event.data === "[DONE]"
```
判断是否完成
优雅处理错误 - 将AI调用代码包裹在try/catch块中
记得使用data包装 - streamText的参数必须包裹在
```
data: {...}
```
中