Skip to main content

Chain of Thought Agent Platform for Industrial-Grade Dialogue Systems

Project description

COTA

Chain of Thought Agent Platform for Industrial-Grade Dialogue Systems

Simple configuration, reliable performance, powered by annotated policy learning

License Python Documentation

GitHub Stars GitHub Issues

简体中文 | Documentation

简体中文

[!Note] 完整的用户文档请访问 COTA Documentation

COTA (Chain of Thought Agent) 是一个基于大语言模型的智能体平台,通过思维链推理标注式策略学习,让开发者以简单的方式构建可靠的工业级对话系统。

💡 核心特征

  • 🧠 Chain of Thought 驱动: 基于思维链推理机制,让AI具备类人的逻辑推理能力
  • 📝 标注式策略学习: 通过标注policies中的thought,训练可靠的对话策略(DPL)
  • 🎯 简单易用: 低代码配置,快速构建生产级智能体

📄 许可证

代码许可

代码使用 MIT License 发布,允许商业使用和修改。


🚀 快速开始

环境要求

  • Python 3.12+
  • Poetry (推荐) 或 pip
  • Git 用于代码管理

🔧 安装

方法1: 通过Poetry安装 (推荐)

# 1. 克隆仓库
git clone https://github.com/CotaAI/cota.git
cd cota

# 2. 安装Poetry
pip install poetry

# 3. 安装依赖
poetry install

# 4. 激活虚拟环境
poetry shell

方法2: 通过pip安装

# 1. 创建虚拟环境
python3 -m venv ./venv
source ./venv/bin/activate  # Linux/macOS
# 或 .\venv\Scripts\activate  # Windows

# 2. 克隆仓库
git clone https://github.com/CotaAI/cota.git
cd cota

# 3. 安装依赖
pip install -r requirements.txt
pip install -e .

⚡ 快速体验

确保你在项目根目录下执行以下命令

1. 初始化项目

# 创建示例机器人配置
cota init
cd cota_projects/simplebot

# 配置API密钥
cp endpoints.yml.example endpoints.yml
# 编辑 endpoints.yml,添加你的LLM API密钥

2. 启动命令行对话

# 启动交互式命令行
cota shell --config=.

# 或启动Web服务
cota run --channel=socket.io --port=5005

3. 启动Web界面

# 启动WebSocket服务
cota run --channel=websocket --host=localhost --port=5005

# 访问 http://localhost:5005 开始对话

📚 文档和教程

🤝 贡献指南

我们欢迎所有形式的贡献!

  1. Fork 本仓库
  2. 创建你的特性分支 (git checkout -b feature/AmazingFeature)
  3. 提交你的更改 (git commit -m 'Add some AmazingFeature')
  4. 推送到分支 (git push origin feature/AmazingFeature)
  5. 开启一个 Pull Request

📞 联系我们

GitHub Issues 和 Pull Requests 随时欢迎!

正式咨询

有关项目和商业合作的正式咨询,请联系:690714362@qq.com

社区讨论

1. GitHub Discussions

参与项目讨论:GitHub Discussions



⭐ 如果COTA对你有帮助,请给我们一个Star!

⭐ If COTA helps you, please give us a Star!

Visitor Count

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

cota-1.0.1.tar.gz (55.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

cota-1.0.1-py3-none-any.whl (79.8 kB view details)

Uploaded Python 3

File details

Details for the file cota-1.0.1.tar.gz.

File metadata

  • Download URL: cota-1.0.1.tar.gz
  • Upload date:
  • Size: 55.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.2.1 CPython/3.12.3 Darwin/24.5.0

File hashes

Hashes for cota-1.0.1.tar.gz
Algorithm Hash digest
SHA256 2afa8a99413fef78a7ae33d47bd02cc15c1ecd49e589f78e6302c3d5f79fad26
MD5 83681e07b34b2529abf2a34f307444bf
BLAKE2b-256 271d960d1eb4f15c0bd02e23bc7907b55138e5a0147d6adc3541b0ae10201c85

See more details on using hashes here.

File details

Details for the file cota-1.0.1-py3-none-any.whl.

File metadata

  • Download URL: cota-1.0.1-py3-none-any.whl
  • Upload date:
  • Size: 79.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.2.1 CPython/3.12.3 Darwin/24.5.0

File hashes

Hashes for cota-1.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 2cbb80fd3a7d636ce5731e8282912d9b7c7f0ff5acf2e34839d7e8769f337fdb
MD5 627a084118e150d7fb313713e50f976b
BLAKE2b-256 4549fe8489cd23fde48c78d03bb93c09d8636192e0299c9d3c52543083fc09b2

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page