Skip to main content

Mini Program Integration

WeChat Mini Programs call CloudBase AI models via wx.cloud.extend.AI, with no additional SDK installation required.

Prerequisites​

Initialization​

Initialize CloudBase in app.js:

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

Text Generation​

generateText() - Non-streaming​

Returns the complete result at once, suitable for short text generation.

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

const res = await model.generateText({
  model: "hunyuan-turbos-latest",
  messages: [{ role: "user", content: "Introduce Li Bai" }],
});

// The return value is the raw model response
console.log(res.choices[0].message.content);
console.log(res.usage); // { prompt_tokens, completion_tokens, total_tokens }

Return Value​

interface GenerateTextResponse {
  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;
  };
}

streamText() - Streaming​

Returns text in a stream, suitable for real-time conversations and long text generation.

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

const res = await model.streamText({
  data: {
    model: "hunyuan-turbos-latest",
    messages: [{ role: "user", content: "Introduce Li Bai" }],
  }
});

// Use textStream to get incremental text
for await (const text of res.textStream) {
  console.log("Text chunk:", text);
}

Parameters​

ParameterTypeRequiredDescription
dataobjectYesRequest parameters, containing model and messages
data.modelstringYesModel name
data.messagesarrayYesMessage list

Return Value​

PropertyTypeDescription
textStreamAsyncIterable\<string>Incremental text stream
eventStreamAsyncIterable\<object>Raw event stream (includes metadata)

Detecting Stream End​

Use eventStream to get full event information. The stream ends when [DONE] is returned:

for await (const event of res.eventStream) {
  console.log(event);
  if (event.data === "[DONE]") {
    break;
  }
}

Complete Example​

Chat Page​

Page({
  data: {
    messages: [],
    inputValue: "",
    isLoading: false
  },

  async sendMessage() {
    const { inputValue, messages } = this.data;
    if (!inputValue.trim() || this.data.isLoading) return;

    // Add user message
    const userMessage = { role: "user", content: inputValue };
    const newMessages = [...messages, userMessage];

    this.setData({
      messages: [...newMessages, { role: "assistant", content: "" }],
      inputValue: "",
      isLoading: true
    });

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

      const res = await model.streamText({
        data: {
          model: "hunyuan-turbos-latest",
          messages: newMessages,
        }
      });

      // Use textStream to progressively update the UI
      for await (const text of res.textStream) {
        assistantContent += text;
        this.setData({
          messages: [
            ...newMessages,
            { role: "assistant", content: assistantContent }
          ]
        });
      }
    } catch (error) {
      console.error("Call failed:", error);
      wx.showToast({ title: "Request failed", icon: "error" });
    } finally {
      this.setData({ isLoading: false });
    }
  }
});

Differences from Web SDK​

FeatureMini ProgramWeb SDK
Namespacewx.cloud.extend.AIapp.ai()
Parameter formatstreamText wrapped in data object, generateText passed directlyPassed directly
Return valueRaw response { choices, usage }Wrapped { text, usage, messages }
Image generationNot supportedSupported