全平台，多模态(语音/图片)理解，自维护套件，实时信息支持

If you don't have the instant messaging platform you need or you want to develop a new application, you are welcome to contribute to this repository. You can develop a new Controller by using Event.py.

We use the self-maintained llm framework llm-kira to implement the conversation client.

• Async
• Support for rate limiting
• Support for private chats, group chats
• Support for black and white list system
• Support for usage management, persona, custom words style 🤖
• Memory pool guarantees 1000 rounds of contextual memory 💾
• Multi-platform, universal use, also supports local voice assistant 🗣️
• Multiple Api key polling pools for easy management and overflow pop-ups 📊
• Active search for content to reply to and support for Sticker replies 😊
• Universal interface for multi-platform support, theoretically allows access to any chat platform 🌐
• Content security removable components, also supports official Api content filtering 🔒
• Real-time web indexing support, universal crawler (supports UrlQueryHtml url?q={}) 🕸️
• Multimodal interaction support, image Blip comprehension support, voice recognition 👂 , sticker support 😎

Make sure your server has 1GB of RAM and 10GB of free storage.

For Arm architecture servers: curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh

curl -LO http://raw.staticdn.net/aoaoemoji/Openaibot/main/setup.sh && sh setup.sh

• init

cp Config/app_exp.toml Config/app.toml

nano Config/app.toml

• Data

apt-get install redis
systemctl start redis.service

• Config/app.toml

# Comment out which part you don't want to start

# QQ Bot
[Controller.QQ]
master = [114, 514] # master user id
account = 0
http_host = 'http://localhost:8080'   # Mirai http Server
ws_host = 'http://localhost:8080'   # Mirai Websocket Server
verify_key = ""
trigger = false # Proactive response when appropriate
INTRO = "POWER BY OPENAI"  # Suffixes for replies
ABOUT = "Created by github.com/LLMKira/Openaibot" # /about
WHITE = "Group NOT in WHITE list" # Whitelist/Blacklist tips

# Proxy set, but does not proxy openai api, only bot
proxy = { status = false, url = "http://127.0.0.1:7890" }

# Telegram Bot
[Controller.Telegram]
master = [114, 514] # master user id
botToken = '' # Bot Token @botfather
trigger = false
INTRO = "POWER BY OPENAI"
ABOUT = "Created by github.com/LLMKira/Openaibot"
WHITE = "Group NOT in WHITE list"

# 设置的代理，但是不代理 openai api, 只代理 bot
proxy = { status = false, url = "http://127.0.0.1:7890" }

# 基础对话事件服务器，Web支持或者音箱用
[Controller.BaseServer]
host = "127.0.0.1"
port = 9559

• Telegram

Telegram BotToken Request

Make sure the bot is a group admin or privacy mode is turned off.

• QQ

Configuring the QQ bot

Our robots can be started in multiple processes.

apt install npm
npm install pm2@latest -g
# or
yarn global add pm2

# test bot
python3 main.py

# run bot
pm2 start pm.json

In addition to the robot, we also have a voice assistant.

Voice Assistant is a web-dependent voice assistant that you can easily run on small devices through Azure or Openai's recognition services.

• Run BaseEvent Server

# 基础对话事件服务器，Web支持或者音箱用
[Controller.BaseServer]
port = 9559

• Run Vits Server

https://github.com/LlmKira/MoeGoe

• Run Assistant

cd Assistant
cat install.md
pip3 install -r requirements.txt
python3 clinet.py

Use /add_api_key Command add OpenaiKey to Config/api_keys.json.

Details On Deploy Guide

Network Plugins/Proxy Settings/Custom Model Names/Speech Services/Picture Understanding/Censor Configuration Please see Service Configuration Guide

详细接口/服务配置/自定义 请查看文档 Deploy Guide

插件设置/代理设置/自定义模型名称/语音服务/图片理解/审查配置 请查看 服务配置

• QuickDev
• LLM Kira
• text_analysis_tools
• MoeGoe Voice

This project open source and available under
the [AGPL License](https://github.com/LLMKira/Openaibot/blob/main/LICENSE).

CLAUSE 说明了如何授权，声明，附加条款等内容。

You wouldn't believe it, but Ai also wrote part of this Readme