このページは現在英語版のみで提供されており、日本語版も近日中に提供される予定です。ご利用いただきありがとうございます。

大規模なモデル構成

This article mainly introduces how to configure the LLMConfig parameter in the StartAIConversation API.
Parameter Description
Name
Description
LLMType
Large language model types, if the model complies with the OpenAI API protocol, please fill in OpenAI.
Model
Specific model name, such as gpt-4o.
APIKey
API Key for large language models.
APIUrl
API URL for large language models.
Streaming
Whether to stream.
SystemPrompt
Prompt words.
Timeout
Timeout, default is 3 seconds (unit: seconds).
History
Set the context rounds for LLM, default value: 0 (no context management provided), maximum value: 50 (provides context management for the last 50 rounds).
MetaInfo
Custom Parameters will be passed through in the request body to the large language model.
LLMConfig Configuration Example
Openai
"LLMConfig": {
      "LLMType": "openai",  
      "Model":"gpt-4o",
      "APIKey":"api-key",
      "APIUrl":"https://api.openai.com/v1/chat/completions",
      "Streaming": true,
      "SystemPrompt": "You are a personal assistant"
      "Timeout": 3.0,
      "History": 5,
      "MetaInfo": {}
}
Minimax
"LLMConfig":{
    "LLMType": "openai",
    "Model": "abab6.5s-chat",
    "Streaming": true,
    "SystemPrompt": "You are a personal assistant"
    "APIKey": "eyJhbGcixxxx",
    "APIUrl": "https://api.minimax.chat/v1/text/chatcompletion_v2",
    "History": 5,
    "MetaInfo": {}
 }
Huan Yuan
"LLMConfig":{
      "LLMType": "openai",
      "Model": "hunyuan-standard", // hunyuan-turbo, hunyuan-standard
      "APIKey": "hunyuan-apikey",
      "APIUrl": "https://hunyuan.cloud.tencent.com/openai/v1/chat/completions",
      "Streaming": true,
      "History": 10,
      "MetaInfo": {}
}
Note:
If the large language model complies with the OpenAI API protocol, we can support it. Fill in LLMType with OpenAI, and fill in other parameters according to the actual situation.
Request For Large Model
In addition, we will add multiple parameters in the HTTP header to help users support more complex logic:
X-Task-Id: <task_id_value> // The ID of this task
X-Request-Id: <request_id> // The ID of this request; the same requestId will be carried on retry.
X-Sdk-App-Id: SdkAppId
X-User-Id: UserId
X-Room-Id: RoomId  
X-Room-Id-Type: "0" // "0" for digit room ID, "1" for string room ID

Name	Description
LLMType	Large language model types, if the model complies with the `OpenAI API` protocol, please fill in `OpenAI`.
Model	Specific model name, such as `gpt-4o`.
APIKey	API Key for large language models.
APIUrl	API URL for large language models.
Streaming	Whether to stream.
SystemPrompt	Prompt words.
Timeout	Timeout, default is 3 seconds (unit: seconds).
History	Set the context rounds for LLM, default value: 0 (no context management provided), maximum value: 50 (provides context management for the last 50 rounds).
MetaInfo	Custom Parameters will be passed through in the request body to the large language model.