#python #ai #chatglm_4 #chatgpt #claude3 #dingtalk #feishu_bot #gemini #glm #gpt_4 #kimi #linkai #llm #openai #python3 #qwen #rag #wechat #wechat_bot #wenxinyiyan #xunfei_spark

This project, called "chatgpt-on-wechat" (CoW), is an intelligent chatbot based on large language models that can be integrated with various platforms like WeChat public accounts, enterprise WeChat apps, Feishu, and DingTalk. It supports multiple models such as GPT-3.5, GPT-4, Claude, Gemini, and more. The bot can handle text, voice, and image inputs and access external resources through plugins.

### Key Benefits Supports deployment on multiple platforms including WeChat public accounts, enterprise WeChat apps, Feishu, and DingTalk.
- **Advanced Conversations** Recognizes voice messages and generates images using various models.
- **Customizable Plugins** Enables custom AI applications using uploaded knowledge base files.

### How It Helps You:
This project helps you create a highly customizable AI chatbot that can be integrated into your existing communication platforms. It enhances customer service, personal assistance, and team efficiency by providing intelligent responses to text, voice, and image queries. The ability to customize knowledge bases and plugins makes it versatile for different business needs.

https://github.com/zhayujie/chatgpt-on-wechat

#python #agent #agentic_ai #grpo #kimi_ai #llms #lora #qwen #qwen3 #reinforcement_learning #rl

ART is a tool that helps you train smart agents for real-world tasks using reinforcement learning, especially with the GRPO method. The standout feature is RULER, which lets you skip the hard work of designing reward functions by using a large language model to automatically score how well your agent is doing—just describe your task, and RULER takes care of the rest. This makes building and improving agents much faster and easier, works for any task, and often performs as well as or better than hand-crafted rewards. You can install ART with a simple command and start training agents right away, even on your own computer or with cloud resources.

https://github.com/OpenPipe/ART