AI SDK

Initialize SDK

For initialization methods, please refer to Initialize SDK.

app.ai

After initialization, you can use the ai method mounted on the cloudbase instance to create an AI instance for subsequent model creation.

Usage Example

app = cloudbase.init({ env: "your-env" });
const ai = app.ai();

Type Declaration

function ai(): AI;

Return Value

AI

Returns a newly created AI instance.

AI

A class for creating AI models.

createModel()

Creates a specified AI model.

Usage Example

const model = ai.createModel("cloudbase");

Type Declaration

function createModel(model: string): ChatModel;

Returns a model instance that implements the ChatModel abstract class, providing AI text generation capabilities.

createImageModel()

Creates a specified image generation model.

Usage Example

const imageModel = ai.createImageModel("hunyuan-image");

Type Declaration

function createImageModel(provider: string): ImageModel;

Parameters

Parameter	Required	Type	Description
provider	Yes	string	Model provider name, e.g., "hunyuan-image"

Return Value

Returns an ImageModel instance that provides AI image generation capabilities.

bot

An instance of the Bot class mounted here, which includes a series of methods for interacting with Agents. For details, refer to the Bot class documentation.

Usage Example

const agentList = await ai.bot.list({ pageNumber: 1, pageSize: 10 });

registerFunctionTool()

Registers a function tool. When calling the LLM, you can inform it of available function tools. When the LLM's response is parsed as a tool call, the corresponding function tool will be automatically invoked.

Usage Example

// Omitting AI SDK initialization...

// 1. Define the weather tool, see FunctionTool type for details
const getWeatherTool = {
  name: "get_weather",
  description: "Returns weather information for a city. Example call: get_weather({city: 'Beijing'})",
  fn: ({ city }) => `The weather in ${city} is: Clear autumn skies!!!`, // Define the tool execution content here
  parameters: {
    type: "object",
    properties: {
      city: {
        type: "string",
        description: "The city to query",
      },
    },
    required: ["city"],
  },
};

// 2. Register the tool we just defined
ai.registerFunctionTool(getWeatherTool);

// 3. Send a message to the LLM and inform it that a weather tool is available
const model = ai.createModel("cloudbase");
const result = await model.generateText({
  model: "hy3-preview",
  tools: [getWeatherTool], // Here we pass in the weather tool
  messages: [
    {
      role: "user",
      content: "Please tell me the weather in Beijing",
    },
  ],
});

console.log(result.text);

Type Declaration

function registerFunctionTool(functionTool: FunctionTool);

Parameters

Parameter	Required	Type	Description
functionTool	Yes	FunctionTool	See FunctionTool for details

Return Value

undefined

Parameters

Parameter	Required	Type	Example	Description
data	Yes	BaseChatModelInput	{model: "deepseek-v4-flash", messages: [{ role: "user", content: "Hello, please introduce Li Bai" }]}	Parameter type is defined as BaseChatModelInput as the basic input definition. In practice, different LLM providers have their own unique input parameters. Developers can pass additional parameters not defined in this type based on the LLM's official documentation to fully utilize the LLM's capabilities. Other parameters will be passed through to the LLM interface, and the SDK does not perform additional processing on them.

Return Value

Property	Type	Example	Description
text	string	"Li Bai was a Tang Dynasty poet."	Text generated by the LLM.
rawResponses	unknown[]	[{"choices": [{"finish_reason": "stop","message": {"role": "assistant", "content": "Hello, is there anything I can help you with?"}}], "usage": {"prompt_tokens": 14, "completion_tokens": 9, "total_tokens": 23}}]	Complete response from the LLM, containing more detailed data such as message creation time. Since different LLMs have varying return values, please use according to your situation.
res.messages	ChatModelMessage[]	[{role: 'user', content: 'Hello'},{role: 'assistant', content: 'Hello! Nice to chat with you. Is there anything I can help you with? Whether it\'s about life, work, study, or other areas, I\'ll do my best to assist you.'}]	Complete message list for this call.
usage	Usage	{"completion_tokens":33,"prompt_tokens":3,"total_tokens":36}	Tokens consumed in this call.
error	unknown		Errors that occurred during the call.

streamText()

Calls the LLM to generate text in streaming mode. During streaming calls, the generated text and other response data are returned via SSE. The return value of this interface provides different levels of encapsulation for SSE, allowing developers to obtain text streams and complete data streams according to their needs.

Usage Example

const hy = ai.createModel("cloudbase"); // Create model
const res = await hy.streamText({
  model: "hy3-preview",
  messages: [{ role: "user", content: "Hello, please introduce Li Bai" }],
});

for await (let str of res.textStream) {
  console.log(str); // Print the generated text
}
for await (let data of res.dataStream) {
  console.log(data); // Print the complete data for each response
}

Type Declaration

function streamText(data: BaseChatModelInput): Promise<StreamTextResult>;

Parameters

Parameter	Required	Type	Example	Description
data	Yes	BaseChatModelInput	{model: "deepseek-v4-flash", messages: [{ role: "user", content: "Hello, please introduce Li Bai" }]}	Parameter type is defined as BaseChatModelInput as the basic input definition. In practice, different LLM providers have their own unique input parameters. Developers can pass additional parameters not defined in this type based on the LLM's official documentation to fully utilize the LLM's capabilities. Other parameters will be passed through to the LLM interface, and the SDK does not perform additional processing on them.

Return Value

StreamTextResult Property	Type	Description
textStream	ReadableStream<string>	LLM-generated text returned in streaming mode. Refer to the usage example to get the incremental generated text.
dataStream	ReadableStream<DataChunk>	LLM response data returned in streaming mode. Refer to the usage example to get the incremental generated data. Since different LLMs have varying response values, please use according to your situation.
messages	Promise<ChatModelMessage[]>	Complete message list for this call.
usage	Promise<Usage>	Tokens consumed in this call.
error	unknown	Errors that occurred during this call.

DataChunk Property	Type	Description
choices	Array<object>
choices[n].finish_reason	string	Reason for model inference termination.
choices[n].delta	ChatModelMessage	Message for this request.
usage	Usage	Tokens consumed in this request.
rawResponse	unknown	Raw response from the LLM.

Example

const hy = ai.createModel("cloudbase");
const res = await hy.streamText({
  model: "hy3-preview",
  messages: [{ role: "user", content: "What is 1+1" }],
});

// Text stream
for await (let str of res.textStream) {
  console.log(str);
}
// 1
// plus
// 1
// equals
// 2
// .

// Data stream
for await (let str of res.dataStream) {
  console.log(str);
}

// {created: 1723013866, id: "a95a54b5c5d2144eb700e60d0dfa5c98", model: "hy3-preview", version: "202404011000", choices: Array(1), …}
// {created: 1723013866, id: "a95a54b5c5d2144eb700e60d0dfa5c98", model: "hy3-preview", version: "202404011000", choices: Array(1), …}
// {created: 1723013866, id: "a95a54b5c5d2144eb700e60d0dfa5c98", model: "hy3-preview", version: "202404011000", choices: Array(1), …}
// {created: 1723013866, id: "a95a54b5c5d2144eb700e60d0dfa5c98", model: "hy3-preview", version: "202404011000", choices: Array(1), …}
// {created: 1723013866, id: "a95a54b5c5d2144eb700e60d0dfa5c98", model: "hy3-preview", version: "202404011000", choices: Array(1), …}
// {created: 1723013866, id: "a95a54b5c5d2144eb700e60d0dfa5c98", model: "hy3-preview", version: "202404011000", choices: Array(1), …}
// {created: 1723013866, id: "a95a54b5c5d2144eb700e60d0dfa5c98", model: "hy3-preview", version: "202404011000", choices: Array(1), …}
// {created: 1723013866, id: "a95a54b5c5d2144eb700e60d0dfa5c98", model: "hy3-preview", version: "202404011000", choices: Array(1), …}

ImageModel

This class describes the interface provided by AI image generation model classes.

generateImageSubUrlConfig

Configures the API sub-path for different provider and model combinations. When calling generateImage(), the SDK looks up the sub-path based on input.model. If not found, it uses the default path images/generations.

Type Declaration

generateImageSubUrlConfig: Record<string, Record<string, string>>

Default Value

{
  'hunyuan-image': {
    'hunyuan-image-v3.0-v1.0.4': 'images/ar/generations',
    'hunyuan-image-v3.0-v1.0.1': 'images/ar/generations',
  },
}

Usage Example

const imageModel = ai.createImageModel("hunyuan-image");

// Custom sub-path configuration
imageModel.generateImageSubUrlConfig['hunyuan-image']['custom-model'] = 'images/custom/generations';

generateImage()

Calls the LLM to generate images.

Usage Example

const imageModel = ai.createImageModel("hunyuan-image");
const res = await imageModel.generateImage({
  model: "hunyuan-image-v3.0-v1.0.4",
  prompt: "A cute cat playing on the grass",
});
console.log(res.data[0].url); // Print the generated image URL

Type Declaration

function generateImage(input: HunyuanARGenerateImageInput): Promise<HunyuanARGenerateImageOutput>;
function generateImage(input: HunyuanGenerateImageInput): Promise<HunyuanGenerateImageOutput>;

Parameters

Parameter	Required	Type	Description
input	Yes	HunyuanARGenerateImageInput | HunyuanGenerateImageInput	Image generation parameters, see HunyuanARGenerateImageInput or HunyuanGenerateImageInput for details

Return Value

Promise<HunyuanARGenerateImageOutput> or Promise<HunyuanGenerateImageOutput>

Property	Type	Description
id	string	ID of this request
created	number	Unix timestamp
data	Array<object>	Returned image generation content
data[n].url	string	Generated image URL, valid for 24 hours
data[n].revised_prompt	string	Text after prompt revision (if revise is false, it's the original prompt)

Bot

A class for interacting with Agents.

get()

Gets information about a specific Agent.

Usage Example

const res = await ai.bot.get({ botId: "botId-xxx" });
console.log(res);

Type Declaration

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

Parameters

Parameter	Required	Type	Description
props.botId	Yes	string	ID of the Agent to get info for

Return Value

Property	Type	Example	Description
botId	string	"bot-27973647"	Agent ID
name	string	"Translator"	Agent name
introduction	string		Agent introduction
welcomeMessage	string		Agent welcome message
avatar	string		Agent avatar URL
background	string		Agent chat background image URL
isNeedRecommend	boolean		Whether to recommend questions after Agent responds
type	string		Agent type

list()

Gets information about multiple Agents in batch.

Usage Example

await 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	Required	Type	Description
props.pageNumber	Yes	number	Page index
props.pageSize	Yes	number	Page size
props.enable	Yes	boolean	Whether the Agent is enabled
props.name	Yes	string	Agent name, for fuzzy search
props.information	Yes	string	Agent information, for fuzzy search
props.introduction	Yes	string	Agent introduction, for fuzzy search

Return Value

Property	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	"Translator"	Agent name
botList[n].introduction	string		Agent introduction
botList[n].welcomeMessage	string		Agent welcome message
botList[n].avatar	string		Agent avatar URL
botList[n].background	string		Agent chat background image URL
botList[n].isNeedRecommend	boolean		Whether to recommend questions after Agent responds
botList[n].type	string		Agent type

sendMessage()

Sends a message to an Agent for conversation. The response is returned via SSE, and this interface's return value provides different levels of encapsulation for SSE, allowing developers to obtain text streams and complete data streams according to their needs.

Usage Example

const res = await ai.bot.sendMessage({
  botId: "botId-xxx",
  history: [{ content: "You are Li Bai.", role: "user" }],
  msg: "Hello",
});
for await (let str of res.textStream) {
  console.log(str);
}
for await (let data of res.dataStream) {
  console.log(data);
}

Type Declaration

function sendMessage(props: {
  botId: string;
  msg: string;
  history: Array<{
    role: string;
    content: string;
  }>;
}): Promise<StreamResult>;

Parameters

Parameter	Required	Type	Description
props.botId	Yes	string	Agent ID
props.msg	Yes	string	Message to send in this conversation
props.history	Yes	[]	Chat history before this conversation
props.history[n].role	Yes	string	Role of the message sender
props.history[n].content	Yes	string	Content of the message

Return Value

Promise<StreamResult>

StreamResult Property	Type	Description
textStream	AsyncIterable<string>	Agent-generated text returned in streaming mode. Refer to the usage example to get the incremental generated text.
dataStream	AsyncIterable<AgentStreamChunk>	Agent-generated data returned in streaming mode. Refer to the usage example to get the incremental generated data.

AgentStreamChunk Property	Type	Description
created	number	Conversation timestamp
record_id	string	Conversation record ID
model	string	LLM type
version	string	LLM version
type	string	Reply type: text: main answer content, thinking: thinking process, search: search results, knowledge: knowledge base
role	string	Conversation role, fixed as assistant in responses
content	string	Conversation content
finish_reason	string	Conversation end flag, continue means conversation is ongoing, stop means conversation ended
reasoning_content	string	Deep thinking content (only non-empty for deepseek-r1)
usage	object	Token usage
usage.prompt_tokens	number	Number of prompt tokens, remains unchanged across multiple returns
usage.completion_tokens	number	Total completion tokens. In streaming returns, represents the cumulative total of all completion tokens so far
usage.total_tokens	number	Sum of prompt_tokens and completion_tokens
knowledge_base	string[]	Knowledge bases used in the conversation
search_info	object	Search result information, requires web search to be enabled
search_info.search_results	object[]	Search citation information
search_info.search_results[n].index	string	Search citation index
search_info.search_results[n].title	string	Search citation title
search_info.search_results[n].url	string	Search citation URL

getChatRecords()

Gets chat records.

Usage Example

await 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	Required	Type	Description
props.botId	Yes	string	Agent ID
props.sort	Yes	string	Sort order
props.pageSize	Yes	number	Page size
props.pageNumber	Yes	number	Page index

Return Value

Property	Type	Description
total	number	Total number of conversations
recordList	Array<object>	Conversation list
recordList[n].botId	string	Agent ID
recordList[n].recordId	string	Conversation ID, system-generated
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 URL 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

sendFeedback()

Sends feedback for a specific chat record.

Usage Example

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

Type Declaration

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

Parameters

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

getFeedback()

Gets existing feedback information.

Usage Example

const res = await 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 sendFeedback(props: {
  botId: string;
  type: string;
  sender: string;
  senderFilter: string;
  minRating: number;
  maxRating: number;
  from: number;
  to: number;
  pageSize: number;
  pageNumber: number;
});

Parameters

Parameter	Required	Type	Description
props.botId	Yes	string	Agent ID
props.type	Yes	string	User feedback type, upvote or downvote
props.sender	Yes	string	Feedback creator user
props.senderFilter	Yes	string	Feedback creator user filter: include, exclude, equal, unequal, 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 index

Return Value

Property	Type	Description
feedbackList	object[]	Feedback query results
feedbackList[n].recordId	string	Conversation 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 number of feedbacks

uploadFiles()

Uploads files from cloud storage to an Agent for document-based chat.

Usage Example

// Upload files
await ai.bot.uploadFiles({
  botId: "botId-xxx",
  fileList: [
    {
      fileId: "cloud://xxx.docx",
      fileName: "xxx.docx",
      type: "file",
    },
  ],
});

// Conduct document-based chat
const res = await ai.bot.sendMessage({
  botId: "your-bot-id",
  msg: "What is the content of this file",
  files: ["xxx.docx"], // Array of file fileIds
});

for await (let text of res.textStream) {
  console.let(text);
}

Type Declaration

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

Parameters

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

getRecommendQuestions()

Gets recommended questions.

Usage Example

const res = ai.bot.getRecommendQuestions({
  botId: "botId-xxx",
  history: [{ content: "Who are you", role: "user" }],
  msg: "Hello",
  agentSetting: "",
  introduction: "",
  name: "",
});

for await (let str of res.textStream) {
  console.log(str);
}

Type Declaration

function getRecommendQuestions(props: {
  botId: string;
  name: string;
  introduction: string;
  agentSetting: string;
  msg: string;
  history: Array<{
    role: string;
    content: string;
  }>;
}): Promise<StreamResult>;

Parameters

Parameter	Required	Type	Description
props.botId	Yes	string	Agent ID
props.name	Yes	string	Agent name
props.introduction	Yes	string	Agent introduction
props.agentSetting	Yes	string	Agent settings
props.msg	Yes	string	User message
props.history	Yes	Array	History messages
props.history[n].role	Yes	string	History message role
props.history[n].content	Yes	string	History message content

Return Value

Promise<StreamResult>

StreamResult Property	Type	Description
textStream	AsyncIterable<string>	Agent-generated text returned in streaming mode. Refer to the usage example to get the incremental generated text.
dataStream	AsyncIterable<AgentStreamChunk>	Agent-generated data returned in streaming mode. Refer to the usage example to get the incremental generated data.

AgentStreamChunk Property	Type	Description
created	number	Conversation timestamp
record_id	string	Conversation record ID
model	string	LLM type
version	string	LLM version
type	string	Reply type: text: main answer content, thinking: thinking process, search: search results, knowledge: knowledge base
role	string	Conversation role, fixed as assistant in responses
content	string	Conversation content
finish_reason	string	Conversation end flag, continue means conversation is ongoing, stop means conversation ended
reasoning_content	string	Deep thinking content (only non-empty for deepseek-r1)
usage	object	Token usage
usage.prompt_tokens	number	Number of prompt tokens, remains unchanged across multiple returns
usage.completion_tokens	number	Total completion tokens. In streaming returns, represents the cumulative total of all completion tokens so far
usage.total_tokens	number	Sum of prompt_tokens and completion_tokens
knowledge_base	string[]	Knowledge bases used in the conversation
search_info	object	Search result information, requires web search to be enabled
search_info.search_results	object[]	Search citation information
search_info.search_results[n].index	string	Search citation index
search_info.search_results[n].title	string	Search citation title
search_info.search_results[n].url	string	Search citation URL

createConversation()

Creates a new conversation with an Agent.

Usage Example

const res = await ai.bot.createConversation({
  botId: "botId-xxx",
  title: "My Conversation",
}): Promise<IConversation>;

Type Declaration

function createConversation(props: IBotCreateConversation);

Parameters

Parameter	Required	Type	Description
props.botId	Yes	string	Agent ID
props.title	No	string	Conversation title

Return Value

Promise<IConversation>

See related type: IConversation

getConversation()

Gets the conversation list.

Usage Example

const res = await ai.bot.getConversation({
  botId: "botId-xxx",
  pageSize: 10,
  pageNumber: 1,
  isDefault: false,
});

Type Declaration

function getConversation(props: IBotGetConversation);

Parameters

Parameter	Required	Type	Description
props.botId	Yes	string	Agent ID
props.pageSize	No	number	Page size, default 10
props.pageNumber	No	number	Page index, default 1
props.isDefault	No	boolean	Whether to only get default conversation

deleteConversation()

Deletes a specified conversation.

Usage Example

await ai.bot.deleteConversation({
  botId: "botId-xxx",
  conversationId: "conv-123",
});

Type Declaration

function deleteConversation(props: IBotDeleteConversation);

Parameters

Parameter	Required	Type	Description
props.botId	Yes	string	Agent ID
props.conversationId	Yes	string	ID of conversation to delete

speechToText()

Converts speech to text.

Usage Example

const res = await ai.bot.speechToText({
  botId: "botId-xxx",
  engSerViceType: "16k_zh",
  voiceFormat: "mp3",
  url: "https://example.com/audio.mp3",
});

Type Declaration

function speechToText(props: IBotSpeechToText);

Parameters

Parameter	Required	Type	Description
props.botId	Yes	string	Agent ID
props.engSerViceType	Yes	string	Engine type, e.g., "16k_zh"
props.voiceFormat	Yes	string	Audio format, e.g., "mp3"
props.url	Yes	string	Audio file URL
props.isPreview	No	boolean	Whether in preview mode

textToSpeech()

Converts text to speech.

Usage Example

const res = await ai.bot.textToSpeech({
  botId: "botId-xxx",
  voiceType: 1,
  text: "Hello, I am an AI assistant",
});

Type Declaration

function textToSpeech(props: IBotTextToSpeech);

Parameters

Parameter	Required	Type	Description
props.botId	Yes	string	Agent ID
props.voiceType	Yes	number	Voice type
props.text	Yes	string	Text to convert
props.isPreview	No	boolean	Whether in preview mode

getTextToSpeechResult()

Gets the text-to-speech result.

Usage Example

const res = await ai.bot.getTextToSpeechResult({
  botId: "botId-xxx",
  taskId: "task-123",
});

Type Declaration

function getTextToSpeechResult(props: IBotGetTextToSpeechResult);

Parameters

Parameter	Required	Type	Description
props.botId	Yes	string	Agent ID
props.taskId	Yes	string	Task ID
props.isPreview	No	boolean	Whether in preview mode

IBotCreateConversation

interface IBotCreateConversation {
  botId: string;
  title?: string;
}

IBotGetConversation

interface IBotGetConversation {
  botId: string;
  pageSize?: number;
  pageNumber?: number;
  isDefault?: boolean;
}

IBotDeleteConversation

interface IBotDeleteConversation {
  botId: string;
  conversationId: string;
}

IBotSpeechToText

interface IBotSpeechToText {
  botId: string;
  engSerViceType: string;
  voiceFormat: string;
  url: string;
  isPreview?: boolean;
}

IBotTextToSpeech

interface IBotTextToSpeech {
  botId: string;
  voiceType: number;
  text: string;
  isPreview?: boolean;
}

IBotGetTextToSpeechResult

interface IBotGetTextToSpeechResult {
  botId: string;
  taskId: string;
  isPreview?: boolean;
}

BaseChatModelInput

interface BaseChatModelInput {
  model: string;
  messages: Array<ChatModelMessage>;
  temperature?: number;
  topP?: number;
  tools?: Array<FunctionTool>;
  toolChoice?: "none" | "auto" | "custom";
  maxSteps?: number;
  onStepFinish?: (prop: IOnStepFinish) => unknown;
}

BaseChatModelInput Property	Type	Description
model	string	Model name.
messages	Array<ChatModelMessage>	Message list.
temperature	number	Sampling temperature, controls output randomness.
topP	number	Temperature sampling, model considers tokens with probability mass of top_p.
tools	Array<FunctionTool>	List of tools available to the LLM.
toolChoice	string	Specifies how the LLM selects tools.
maxSteps	number	Maximum number of LLM requests.
onStepFinish	(prop: IOnStepFinish) => unknown	Callback function triggered when an LLM request completes.

BotInfo

interface BotInfo {
  botId: string;
  name: string;
  introduction: string;
  agentSetting: string;
  welcomeMessage: string;
  avatar: string;
  background: string;
  tags: Array<string>;
  isNeedRecommend: boolean;
  knowledgeBase: Array<string>;
  type: string;
  initQuestions: Array<string>;
  enable: true;
}

IUserFeedback

interface IUserFeedback {
  recordId: string;
  type: string;
  botId: string;
  comment: string;
  rating: number;
  tags: Array<string>;
  input: string;
  aiAnswer: string;
}

ChatModelMessage

type ChatModelMessage =
  | UserMessage
  | SystemMessage
  | AssistantMessage
  | ToolMessage;

UserMessage

type UserMessage = {
  role: "user";
  content: string;
};

SystemMessage

type SystemMessage = {
  role: "system";
  content: string;
};

AssistantMessage

type AssistantMessage = {
  role: "assistant";
  content?: string;
  tool_calls?: Array<ToolCall>;
};

ToolMessage

type ToolMessage = {
  role: "tool";
  tool_call_id: string;
  content: string;
};

ToolCall

export type ToolCall = {
  id: string;
  type: string;
  function: { name: string; arguments: string };
};

FunctionTool

Tool definition type.

type FunctionTool = {
  name: string;
  description: string;
  fn: CallableFunction;
  parameters: object;
};

FunctionTool Property	Type	Description
name	string	Tool name.
description	string	Tool description. A clear tool description helps the LLM understand the tool's purpose.
fn	CallableFunction	Tool execution function. When the AI SDK parses the LLM's response as requiring this tool call, it calls this function and returns the result to the LLM.
parameters	object	Tool execution function parameters. Must be defined in JSON Schema format.

IOnStepFinish

Parameter type for the callback function triggered after LLM response.

interface IOnStepFinish {
  messages: Array<ChatModelMessage>;
  text?: string;
  toolCall?: ToolCall;
  toolResult?: unknown;
  finishReason?: string;
  stepUsage?: Usage;
  totalUsage?: Usage;
}

IOnStepFinish Property	Type	Description
messages	Array<ChatModelMessage>	Complete message list up to the current step.
text	string	Text from the current response.
toolCall	ToolCall	Tool called in the current response.
toolResult	unknown	Result of the corresponding tool call.
finishReason	string	Reason for LLM inference completion.
stepUsage	Usage	Tokens consumed in the current step.
totalUsage	Usage	Total tokens consumed up to the current step.

Usage

type Usage = {
  completion_tokens: number;
  prompt_tokens: number;
  total_tokens: number;
};

IConversation

Agent conversation.

interface IConversation {
  id: string;
  envId: string;
  ownerUin: string;
  userId: string;
  conversationId: string;
  title: string;
  startTime: string; // date-time format
  createTime: string;
  updateTime: string;
}

HunyuanGenerateImageInput

Hunyuan image generation input parameters.

interface HunyuanGenerateImageInput {
  model: 'hunyuan-image';
  /** Text description used to generate the image */
  prompt: string;
  /** Model version, supports v1.8.1 and v1.9, default version v1.8.1 */
  version?: 'v1.8.1' | 'v1.9' | (string & {});
  /** Image size, default "1024x1024" */
  size?: string;
  /** v1.9 only, negative prompt */
  negative_prompt?: string;
  /** v1.9 only, can specify style */
  style?: '古风二次元风格' | '都市二次元风格' | '悬疑风格' | '校园风格' | '都市异能风格' | (string & {});
  /** When true, rewrites the prompt, default is true */
  revise?: boolean;
  /** Number of images to generate, default is 1 */
  n?: number;
  /** Custom business watermark content, limited to 16 characters */
  footnote?: string;
  /** Generation seed, range [1, 4294967295] */
  seed?: number;
}

HunyuanGenerateImageInput Property	Type	Description
model	string	Model name, must be hunyuan-image
prompt	string	Text description used to generate the image
version	string	Model version, supports v1.8.1 and v1.9, default version v1.8.1
size	string	Image size, default "1024x1024"
negative_prompt	string	v1.9 only, negative prompt
style	string	v1.9 only, can specify style: Ancient Anime Style, Urban Anime Style, Suspense Style, Campus Style, Urban Fantasy Style
revise	boolean	When true, rewrites the prompt, default is true
n	number	Number of images to generate, default is 1
footnote	string	Custom business watermark content, limited to 16 characters
seed	number	Generation seed, range [1, 4294967295]

HunyuanGenerateImageOutput

Hunyuan image generation output.

interface HunyuanGenerateImageOutput {
  /** ID of this request */
  id: string;
  /** Unix timestamp */
  created: number;
  /** Returned image generation content */
  data: Array<{
    /** Generated image URL, valid for 24 hours */
    url: string;
    /** Text after original prompt revision. If revise is false, it's the original prompt */
    revised_prompt?: string;
  }>;
}

HunyuanGenerateImageOutput Property	Type	Description
id	string	ID of this request
created	number	Unix timestamp
data	Array<object>	Returned image generation content
data[n].url	string	Generated image URL, valid for 24 hours
data[n].revised_prompt	string	Text after original prompt revision. If revise is false, it's the original prompt

HunyuanARGenerateImageInput

Hunyuan image generation v3.0 input parameters, supports custom aspect ratio.

interface HunyuanARGenerateImageInput {
  /** Model name: hunyuan-image-v3.0-v1.0.4 (recommended) or hunyuan-image-v3.0-v1.0.1 */
  model: 'hunyuan-image-v3.0-v1.0.4' | 'hunyuan-image-v3.0-v1.0.1';
  /** Text for image generation, max 8192 characters */
  prompt: string;
  /**
   * Image size, format "${width}x${height}", default "1024x1024"
   * hunyuan-image-v3.0-v1.0.4: width/height range [512, 2048], area not exceeding 1024x1024
   * hunyuan-image-v3.0-v1.0.1: supports fixed size list
   */
  size?: string;
  /** Generation seed, only effective when generating 1 image, range [1, 4294967295] */
  seed?: number;
  /** Custom watermark content, max 16 characters, displayed at bottom-right */
  footnote?: string;
  /** Whether to rewrite prompt, enabled by default. Rewriting adds ~30s latency */
  revise?: { value: boolean };
  /** Whether to enable thinking mode for rewriting, enabled by default. Improves quality but adds latency (max 60s) */
  enable_thinking?: { value: boolean };
}

HunyuanARGenerateImageInput Property	Type	Description
model	string	Model name, hunyuan-image-v3.0-v1.0.4 (recommended) or hunyuan-image-v3.0-v1.0.1
prompt	string	Text for image generation, max 8192 characters
size	string	Image size, format "widthxheight", default "1024x1024", width/height range [512, 2048]
seed	number	Generation seed, only effective when generating 1 image, range [1, 4294967295]
footnote	string	Custom watermark content, max 16 characters, displayed at bottom-right
revise	{ value: boolean }	Whether to rewrite prompt, enabled by default. Adds ~30s latency
enable_thinking	{ value: boolean }	Whether to enable thinking mode, enabled by default. Improves quality but adds latency (max 60s)

HunyuanARGenerateImageOutput

Hunyuan image generation v3.0 output.

interface HunyuanARGenerateImageOutput {
  /** Request id */
  id: string;
  /** Unix timestamp */
  created: number;
  /** Generated image content */
  data: Array<{
    /** Generated image url, valid for 24 hours */
    url: string;
    /** Rewritten prompt */
    revised_prompt?: string;
  }>;
}

HunyuanARGenerateImageOutput Property	Type	Description
id	string	Request id
created	number	Unix timestamp
data	Array<object>	Generated image content
data[n].url	string	Generated image url, valid for 24 hours
data[n].revised_prompt	string	Rewritten prompt