Repository files navigation

🍩 Deploy Docs &🧀 Dev Docs &🤝 Contribute

Don't hesitate to Star ⭐️, Issue 📝, and PR 🛠️

Python>=3.9

This project is not abandoned, just no new features are planned.If you encounter a problem, please raise an Issue

This project uses the ToolCall feature.

It integrates a message queuing and snapshot system, offering plugin mechanisms and authentication prior to pluginexecution.

The bot adheres to theOpenai Format Schema. Please adapt usinggatewayorone-api independently.

Demo	Vision With Voice	Code Interpreter

The program has iterated to its fourth generation.

• Removal of legacy code
• Deletion of metric system
• Deletion of model selection system, unified to OpenAI Schema
• Implementation of a more robust plugin system
• Project structure simplification
• Elimination of the Provider system
• Hook support
• Access to TTS
• Add standalone support for gpt-4-turbo and vision
• Add LLM reference support to the plugin environment. (extract && search in text)

• 🍪 A comprehensive plugin development ecosystem, adopting a classic design, and seamless integration with pluginsthroughpip installation
• 📝 Message system with no time or sender constraints, offering fully decoupled logics
• 📬 Offers Login via a URL mechanism, providing a flexible and expandable authentication development solution
• 🍰 Empowers users to authorize plugin execution. Users can configure plugin environment variables at their discretion
• 📦 Support for plugins to access files
• 🍟 Multi-platform support – extend new platforms by inheriting the base class
• 🍔 Plugins can determine their appearance in new sessions dynamically, preventing performance degradation despite largeamounts of plugins

• Login via url: Use/login <a token>$<something like https://provider.com/login> to Login. The program posts the token to the interface toretrieve configurationinformation,how to develop this.
• Login: Use/login https://<api endpoint>/v1$<api key>$<the model>$<tool model such as gpt-3.5-turbo> to login

Sticker Converter	Timer Function(built-in)

Refer to the🧀 Deployment Document for more information.

If you are using a brand-new server, you can use the following shell to automatically install this project.

curl -sSL https://raw.githubusercontent.com/LLMKira/Openaibot/main/deploy.sh| bash

# Install Voice dependenciesapt install ffmpeg# Install RabbitMQdocker pull rabbitmq:3.10-managementdocker run -d -p 5672:5672 -p 15672:15672 \  -e RABBITMQ_DEFAULT_USER=admin \  -e RABBITMQ_DEFAULT_PASS=8a8a8a \  --hostname myRabbit \  --name rabbitmq \  rabbitmq:3.10-managementdocker ps -l# Install Projectgit clone https://github.com/LlmKira/Openaibot/cd Openaibotpip install pdmpdm install -G botcp .env.exp .env&& nano .env# Testpdm run python3 start_sender.pypdm run python3 start_receiver.py# Hostapt install npmnpm install pm2 -gpm2 start pm2.json

Be sure to change the default password for the command, or disable open ports to prevent the database from beingscanned and attacked.

Build Hub:sudoskys/llmbot

Note that if you run this project using Docker, you will start Redis, MongoDB, and RabbitMQ. But if you're runninglocally, just RabbitMQ

git clone https://github.com/LlmKira/Openaibot.gitcd Openaibotcp .env.exp .env&&nano .envdocker-compose -f docker-compose.yml up -d

The Docker configuration filedocker-compose.yml contains all databases. In fact, Redis and MongoDB are not required.You can remove these databases yourself and use the local file system.

Update image usingdocker-compose pull.

Usedocker exec -it llmbot /bin/bash to view Shell in Docker, enterexit to exit.

clear - Deletes chat recordslogin - Login to the bothelp - Displays documentationchat - Conversationtask - Use afunctionto converseask - Disable function-based conversationstool - Lists all functionsauth - Authorize a functionenv - Environment variables of the functionlearn - Learn your instructions, /learn reset to clear

Refer to the example plugins in theplugins directory andthe🧀 Plugin Development Document for plugin development documentation.

Hooks control the EventMessage in sender and receiver. For example, we havevoice_hook in built-in hooks.

you can enable it by settingVOICE_REPLY_ME=true in.env.

/env VOICE_REPLY_ME=yes# must/env REECHO_VOICE_KEY=<keyin dev.reecho.ai># not must

use/env VOICE_REPLY_ME=NONE to disable this env.

check the source code inllmkira/extra/voice_hook.py, learn to write your own hooks.

This project, named OpenAiBot, signifying "Open Artificial Intelligence Robot", is not officially affiliated withOpenAI.