SendAgentInstanceLLM

POST

https://aigc-aiagent-api.zegotech.cn/

This interface can be used to, as the user, actively call the LLM service, and based on the response content of the LLM, actively call the TTS service as the AI agent, and send voice messages to the user. (1. When this interface is called, if the AI agent in the conversation is speaking, the speaking process of the AI agent will be interrupted; 2. The text information passed into this interface will not be recorded in the conversation history message and will not be sent through the RTC room message. However, the reply generated by the LLM will be recorded in the conversation history message and sent through the RTC room message.)

Request

Query Parameters

Action stringrequired

Possible values: [SendAgentInstanceLLM]

API Prototype Parameter

https://aigc-aiagent-api.zegotech.cn?Action=SendAgentInstanceLLM

AppId uint32required

The unique Application ID assigned to your project by ZEGOCLOUD. Get it from the ZEGOCLOUD Admin Console.

SignatureNonce stringrequired

Random string.

Timestamp int64required

Unix timestamp, in seconds. The maximum allowed error is 10 minutes.

Signature stringrequired

Signature, used to verify the legitimacy of the request. Refer to Signing the requests for how to generate an API request signature.

SignatureVersion stringrequired

Possible values: [2.0]

Signature version number, default value is 2.0.

application/json

Body

required

AgentInstanceId stringrequired

The unique identifier of the AI agent instance, obtained through the response parameters of the Create AI Agent Instance interface.

Text stringrequired

The text content sent to the LLM service

SystemPrompt string

Whether to temporarily modify the system prompt of the AI agent for this conversation, if needed, fill in this field. If left blank, the system prompt of this conversation will not be changed.

AddQuestionToHistory boolean

Default value: false

Whether to add the question to the context

AddAnswerToHistory boolean

Default value: false

Whether to add the answer to the context

Responses

Success

application/json

Schema
Example (from schema)

Schema

Code integer

Return code. 0 indicates success, other values indicate failure. For more information on error codes and response handling recommendations, please refer to Return Codes.

Message string

Explanation of the request result

RequestId string

Request ID

{
  "Code": 0,
  "Message": "Success",
  "RequestId": "8825223157230377926"
}

{
  "Code": 0,
  "Message": "Success",
  "RequestId": "8825223157230377926"
}

CURL

RESPONSEClear

Click the "Send" button above and see the response here!