Skip to main content

12-factor-agents - 为生产环境打造可靠的大语言模型（LLM）应用程序的12条原则

  1. 12-factor-agents - 为生产环境打造可靠的大语言模型（LLM）应用程序的12条原则

    https://github.com/humanlayer/12-factor-agents

    提供12条构建LLM应用的核心原则，助力开发者打造高质量软件；结合实际案例，帮助开发者避免常见陷阱

    1. 将自然语言转换为工具调用
    2. 掌控提示词
    3. 掌控上下文窗口
    4. 将工具视为结构化输出
    5. 统一执行状态和业务状态
    6. 提供简单的API进行启动、暂停和恢复
    7. 通过工具调用联系人类
    8. 掌控控制流
    9. 将错误压缩到上下文窗口
    10. 构建小型、专注的代理
    11. 从任何地方触发,满足用户需求
    12. 将代理设计为无状态的reducer

    #AI #GitHub #Doc #DevOps
    GitHub
    GitHub - humanlayer/12-factor-agents: What are the principles we can use to build LLM-powered software that is actually good enough…
    GitHub - humanlayer/12-factor-agents: What are the principles we can use to build LLM-powered software that is actually good enough…
    What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? - humanlayer/12-factor-agents
OKHK