WeChat Mini Program Basic Library API

Starting from version 3.7.1, WeChat Mini Program's basic library includes built-in CloudBase AI+ capabilities that developers can access directly through wx.cloud.extend.AI.

Initialization

Before using the basic library's AI+ capabilities, you need to initialize with the CloudBase environment.

wx.cloud.init({
  env: "your-env-id"
});

After initialization, you can use CloudBase AI+ capabilities through wx.cloud.extend.AI.

Large Models

AI.createModel()

Creates a specified AI model.

Usage Example

const model = wx.cloud.extend.AI.createModel("cloudbase");

Type Declaration

function createModel(model: string): ChatModel;

Returns an object that provides AI text generation capability.

ChatModel.streamText()

Call large models with streaming to generate text. During streaming calls, generated text and other response data are returned via SSE. This interface provides different levels of encapsulation for SSE, allowing developers to obtain text streams and complete data streams according to actual needs.

Usage Example

const hy = wx.cloud.extend.AI.createModel("cloudbase"); // Create model
const res = await hy.streamText({
  data: {
    model: "hy3-preview",
    messages: [
      {
        role: "user",
        content: "hi"
      }
    ]
  }
});

for await (let str of res.textStream) {
  console.log(str); // Print generated text
}
for await (let event of res.eventStream) {
  console.log(event); // Print complete data for each return

  // When the large model finishes transmitting, it usually sends [DONE] data, you can stop the loop after that
  if (event.data === "[DONE]") {
    break;
  }
}

Type Declaration

function streamText(props: StreamTextInput): Promise<StreamTextResult>;

interface StreamTextResult {
  eventStream: EventStream;
  textStream: TextStream;
}

interface StreamTextInput {
  data: unknown;
  onEvent?: OnEvent;
  onText?: OnText;
  onFinish?: OnFinish;
}

interface OnEvent {
  (prop: { data: string }): unknown;
}

interface OnText {
  (text: string): unknown;
}

interface OnFinish {
  (text: string): unknown;
}

interface EventStream {
  [Symbol.asyncIterator](): AsyncIterator<{
    event?: unknown;
    id?: unknown;
    data: string;
  }>;
}

interface TextStream {
  [Symbol.asyncIterator](): AsyncIterator<string>;
}

Parameters

Parameter Name	Required	Type	Example	Description
props.data	Yes	unknown	{model: "deepseek-v4-flash", messages: [{ role: "user", content: "Hello, introduce Li Bai" }]}	Parameters for calling each large model differ. Pass the correct parameters according to the actual model being called.
props.tools	No	object	--	Tool calling related parameters
props.tools.autoExecute	No	boolean	true	Whether to automatically call tools, default true
props.tools.maxStep	No	number	10	Maximum times to auto-execute, default 10
props.tools.list	No	Array	--	Tool list
props.tools.list[n].name	Yes	string	"get_weather"	Tool name
props.tools.list[n].description	No	string	Returns temperature information for a city on a specific day. Example: get_weather({city: 'Beijing',date: '03-19'})	Tool description
props.tools.list[n].fn	Yes	function	({ city, date }) => city + " on " + date + " temperature is: " + (20 + (Math.random() * 10))	Callback function executed by the tool
props.tools.list[n].parameters	No	{"type":"object","properties":{"city":{"type":"string","description":"city to query"},"date":{"type":"string","description":"date to query"}},"required":["city","date"]}	--	Schema definition for input parameters of the tool execution callback function
props.tools.onToolEvent	No	function	console.warn	Listen for events when the large model executes tool_call
props.onText	No	(text: string) => unknown;	(text) => console.log(text)	Callback function triggered when new text is received, parameter is incremental text
props.onEvent	No	(prop: { data: string }) => unknown;	({data}) => console.log(data)	Callback function triggered when new event is received, parameter is event, prop.data is the data contained in this event
props.onFinish	No	(text: string) => unknown;	(text) => console.log(text)	Callback function triggered when this call is completely finished, parameter is the complete text returned by this call

Return Value

StreamTextResult Property	Type	Description
textStream	AsyncIterable<string>	Streamed large model generated text. Refer to usage examples to get incremental generated text.
eventStream	AsyncIterable<{data: string, event?: unknown, id?: unknown}>	Streamed large model response data. Can get incremental data generated. Since different model responses vary, use reasonably based on actual situation.

ChatModel.generateText()

Call large models to generate text.

Usage Example

const hy = wx.cloud.extend.AI.createModel("cloudbase"); // Create model
const res = await hy.generateText({
  model: "hy3-preview",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(res);
// {
//   "id": "27dae91f4e9a4777782c61f89acf8ea4",
//   "object": "chat.completion",
//   "created": 1737602298,
//   "model": "hy3-preview",
//   "system_fingerprint": "",
//   "choices": [
//     {
//       "index": 0,
//       "message": {
//         "role": "assistant",
//         "content": "Hello! Nice to chat with you. Is there anything I can help you with? Whether it's about life, work, learning or other aspects, I'll try my best to help you."
//       },
//       "finish_reason": "stop"
//     }
//   ],
//   "usage": {
//     "prompt_tokens": 3,
//     "completion_tokens": 33,
//     "total_tokens": 36
//   },
//   "note": "The above content is AI generated, does not represent the developer's position, please do not delete or modify this mark"
// }
console.log(res.choices[0].message.content);
// Hello! Nice to chat with you. Is there anything I can help you with? Whether it's about life, work, learning or other aspects, I'll try my best to help you.

Type Declaration

function generateText(data: unknown): Promise<unknown>;

Parameters

Parameter Name	Required	Type	Example	Description
data	Yes	unknown	{model: "deepseek-v4-flash", messages: [{ role: "user", content: "Hello, introduce Li Bai" }]}	Parameters for calling each large model differ. Pass the correct parameters according to the actual model being called.

Return Value

This interface directly returns the actual response from calling the large model. You need to parse the needed data according to the actual response content. See the usage example above.

Agent

AI.bot.get()

Get information about an Agent.

Usage Example

await wx.cloud.extend.AI.bot.get({ botId: "botId-xxx" });

Type Declaration

function get(props: { botId: string });

Parameters

Parameter Name	Required	Type	Description
props.botId	Yes	string	The id of the Agent to get information about

Return Value

Property Name	Type	Example	Description
botId	string	"bot-27973647"	Agent ID
name	string	"Translation"	Agent name
introduction	string		Agent introduction
welcomeMessage	string		Agent welcome message
avatar	string		Agent avatar link
background	string		Agent chat background image link
isNeedRecommend	boolean		Whether Agent recommends questions after answering
type	string		Agent type

AI.bot.list()

Get information about multiple Agents in bulk.

Usage Example

await wx.cloud.extend.AI.bot.list({
  pageNumber: 1,
  pageSize: 10,
  name: "",
  enable: true,
  information: "",
  introduction: "",
});

Type Declaration

function list(props: {
  name: string;
  introduction: string;
  information: string;
  enable: boolean;
  pageSize: number;
  pageNumber: number;
});

Parameters

Parameter Name	Required	Type	Description
props.pageNumber	Yes	number	Page number
props.pageSize	Yes	number	Page size
props.enable	Yes	boolean	Whether Agent is enabled
props.name	Yes	string	Agent name for fuzzy query
props.information	Yes	string	Agent information for fuzzy query
props.introduction	Yes	string	Agent introduction for fuzzy query

Return Value

Property Name	Type	Example	Description
total	number	---	Total number of Agents
botList	Array<object>		Agent list
botList[n].botId	string	"bot-27973647"	Agent ID
botList[n].name	string	"Translation"	Agent name
botList[n].introduction	string		Agent introduction
botList[n].welcomeMessage	string		Agent welcome message
botList[n].avatar	string		Agent avatar link
botList[n].background	string		Agent chat background image link
botList[n].isNeedRecommend	boolean		Whether Agent recommends questions after answering
botList[n].type	string		Agent type

AI.bot.sendMessage()

Chat with an Agent.

Usage Example

const res = await wx.cloud.extend.AI.bot.sendMessage({
  data: {
    botId: 'xxx-bot-id',
    msg: "Who are you"
  }
})
for await (let x of res.textStream) {
  console.log(x)
}

Type Declaration

function sendMessage(props: {
  data: {
    botId: string;
    msg: string;
    history: Array<{
      role: string;
      content: string;
    }>;
    files?: Array<string>,
  },
  onText: OnText,
  onEvent: OnEvent,
  onFinish: OnFinish
});

Parameters

Parameter Name	Required	Type	Description
props.data.botId	Yes	string	Agent id
props.data.msg	Yes	string	Message to send in this conversation
props.data.history	Yes	boolean	Chat history before this conversation
props.data.history[n].role	Yes	string	Role of this chat message sender
props.data.history[n].content	Yes	string	Content of this chat message
props.data.files	No	Array<string>	Files attached to this message, need to fill in cloud storage file cloud id
props.onText	No	(text: string) => unknown;	Callback function triggered when new text is received, parameter is incremental text
props.onEvent	No	(prop: { data: string }) => unknown;	Callback function triggered when new event is received, parameter is event, prop.data is the string of data contained in this event
props.onFinish	No	(text: string) => unknown;	Callback function triggered when this call is completely finished, parameter is the complete text returned by this call

AI.bot.getChatRecords()

Get chat history.

Usage Example

await wx.cloud.extend.AI.bot.getChatRecords({
  botId: "botId-xxx",
  pageNumber: 1,
  pageSize: 10,
  sort: "asc",
});

Type Declaration

function getChatRecords(props: {
  botId: string;
  sort: string;
  pageSize: number;
  pageNumber: number;
});

Parameters

Parameter Name	Required	Type	Description
props.botId	Yes	string	Agent id
props.sort	Yes	string	Sort method
props.pageSize	Yes	number	Page size
props.pageNumber	Yes	number	Page number

Return Value

Property Name	Type	Description
total	number	Total conversations
recordList	Array<object>	Conversation list
recordList[n].botId	string	Agent ID
recordList[n].recordId	string	Conversation ID, generated by system
recordList[n].role	string	Role in conversation
recordList[n].content	string	Conversation content
recordList[n].conversation	string	User identifier
recordList[n].type	string	Conversation data type
recordList[n].image	string	Image link generated in conversation
recordList[n].triggerSrc	string	Conversation trigger source
recordList[n].replyTo	string	Record ID being replied to
recordList[n].createTime	string	Conversation time

AI.bot.sendFeedback()

Send feedback for a chat record.

Usage Example

const res = await wx.cloud.extend.AI.bot.sendFeedback({
  userFeedback: {
    botId: "botId-xxx",
    recordId: "recordId-xxx",
    comment: "Excellent",
    rating: 5,
    tags: ["Beautiful"],
    aiAnswer: "Falling petals in profusion",
    input: "Give me an idiom",
    type: "upvote",
  },
});

Type Declaration

function sendFeedback(props: { userFeedback: IUserFeedback, botId: string });

Parameters

Parameter Name	Required	Type	Description
props.userFeedback	Yes	IUserFeedback	User feedback, see IUserFeedback type definition
props.botId	Yes	string	Agent id to provide feedback for

AI.bot.getFeedBack()

Get existing feedback information.

Usage Example

const res = await wx.cloud.extend.AI.bot.getFeedBack({
  botId: "botId-xxx",
  from: 0,
  to: 0,
  maxRating: 4,
  minRating: 3,
  pageNumber: 1,
  pageSize: 10,
  sender: "user-a",
  senderFilter: "include",
  type: "upvote",
});

Type Declaration

function getFeedBack(props: {
  botId: string;
  type: string;
  sender: string;
  senderFilter: string;
  minRating: number;
  maxRating: number;
  from: number;
  to: number;
  pageSize: number;
  pageNumber: number;
});

Parameters

Parameter Name	Required	Type	Description
props.botId	Yes	string	Agent id
props.type	Yes	string	User feedback type, upvote or downvote
props.sender	Yes	string	User who created comment
props.senderFilter	Yes	string	User filter relation include:contains exclude:not contains equal:equals unequal:not equals prefix:prefix
props.minRating	Yes	number	Minimum rating
props.maxRating	Yes	number	Maximum rating
props.from	Yes	number	Start timestamp
props.to	Yes	number	End timestamp
props.pageSize	Yes	number	Page size
props.pageNumber	Yes	number	Page number

Return Value

Property Name	Type	Description
feedbackList	object[]	Feedback query results
feedbackList[n].recordId	string	Chat record ID
feedbackList[n].type	string	User feedback type, upvote or downvote
feedbackList[n].botId	string	Agent ID
feedbackList[n].comment	string	User comment
feedbackList[n].rating	number	User rating
feedbackList[n].tags	string[]	User feedback tags array
feedbackList[n].input	string	User input question
feedbackList[n].aiAnswer	string	Agent's answer
total	number	Total feedback

AI.bot.getRecommendQuestions()

Get recommended questions.

Usage Example

const res = await wx.cloud.extend.AI.bot.getRecommendQuestions({
  data: {
    botId: "xxx-bot-id",
    msg: "Who are you"
  }
})
for await (let x of res.textStream) {
  console.log(x)
}

Type Declaration

function getRecommendQuestions(props: {
  data: {
    botId: string;
    name: string;
    introduction: string;
    agentSetting: string;
    msg: string;
    history: Array<{
      role: string;
      content: string;
    }>;
  },
  onText: OnText,
  onEvent: OnEvent,
  onFinish: OnFinish
});

Parameters

Parameter Name	Required	Type	Description
props.data.botId	Yes	string	Agent id
props.data.name	Yes	string	Agent name
props.data.introduction	Yes	string	Agent introduction
props.data.agentSetting	Yes	string	Agent settings
props.data.msg	Yes	string	User sent message
props.data.history	Yes	Array	Historical conversation info
props.data.history[n].role	Yes	string	Role of historical message
props.data.history[n].content	Yes	string	Content of historical message
props.onText	No	(text: string) => unknown;	Callback function triggered when new text is received, parameter is incremental text
props.onEvent	No	(prop: { data: string }) => unknown;	Callback function triggered when new event is received, parameter is event, prop.data is the string of data contained in this event
props.onFinish	No	(text: string) => unknown;	Callback function triggered when this call is completely finished, parameter is the complete text returned by this call

AI.bot.uploadFiles()

Upload files from cloud storage to Agent for document chat.

Usage Example

await wx.cloud.extend.AI.bot.uploadFiles({
  botId: 'bot-xx',
  fileList: [{
      fileId: 'cloud://xxx.pdf',
      fileName: 'xxx.pdf',
      type: 'file'
  }]
})

Type Declaration

function uploadFiles(props: {
  botId: string,
  fileList: Array<{
    fileId: string;
    fileName: string;
    type: string;
  }>
});

Parameters

Parameter Name	Required	Type	Description
props.botId	Yes	string	Agent id
props.fileList	Yes	Array	File list
props.fileList[n].fileId	Yes	string	Cloud storage cloud id of file
props.fileList[n].fileName	Yes	string	File name
props.fileList[n].type	Yes	string	Currently only supports "file"