知识库检索功能（retrieval）
开发环境
http://dev-cn.your-api-server.com
开发环境
http://dev-cn.your-api-server.com
POST
https://api.minimax.chat/v1/text/chatcompletion_pro
1.
2.
3.
import requests
group_id="请填写您的group_id"
api_key="请填写您的api_key"
url = "https://api.minimax.chat/v1/text/chatcompletion_pro?GroupId=" + group_id
payload = {
"bot_setting": [
{
"bot_name": "MM智能助理",
"content": "MM智能助理是一款由MiniMax自研的，没有调用其他产品的接口的大型语言模型。MiniMax是一家中国科技公司，一直致力于进行大模型相关的研究。",
}
],
"messages": [{"sender_type": "USER", "sender_name": "小明", "text": "帮我用英文翻译下面这句话：我是谁"}],
"reply_constraints": {"sender_type": "BOT", "sender_name": "MM智能助理"},
"model": "abab5.5-chat",
"tokens_to_generate": 1034,
"temperature": 0.01,
"top_p": 0.95,
"knowledge_base_param": {
"knowledge_base_id": ${knowledge_base_id}
}
}
headers = {"Content-Type": "application/json", "Authorization": "Bearer " + api_key}
response = requests.request("POST", url, headers=headers, json=payload)
print(response.status_code)
print(response.text)请求示例请求示例
Shell
JavaScript
Java
Swift
curl --location --request POST 'https://api.minimax.chat/v1/text/chatcompletion_pro' \
--header 'Authorization;' \
--header 'Content-Type: application/json' \
--data-raw '{
"model": "abab5.5-chat",
"tokens_to_generate": 1024,
"temperature": 0.9,
"top_p": 0.95,
"stream": false,
"beam_width": 1,
"reply_constraints": {
"sender_type": "BOT",
"sender_name": "MM智能助理"
},
"sample_messages": [],
"plugins": [],
"messages": [
{
"sender_type": "USER",
"sender_name": "用户",
"text": "齐天是谁"
}
],
"bot_setting": [
{
"bot_name": "MM智能助理",
"content": "MM智能助理是一款由MiniMax自研的，没有调用其他产品的接口的大型语言模型。MiniMax是一家中国科技公司，一直致力于进行大模型相关的研究。"
}
],
"knowledge_base_param": {
"knowledge_base_id": ${knowledge_base_id}
}
}'响应示例响应示例
{
"knowledge_base": {
"knowledge_base_id": {},
"chunks": {}
},
"chunks": {},
"content": 0,
"index": 0,
"document": "string"
}请求参数
Header 参数
Authorization
string
可选
Content-Type
string
可选
Body 参数application/json